UAV Detection and Tracking in Urban Environments Using Passive Sensors: A Survey

Round 1

Reviewer 1 Report

The abstract provides a clear overview of the paper's content. However, I recommend ensuring a smooth transition between the introduction of passive UAV-monitoring technologies and the discussion of anti-UAV systems. The structure of the abstract could be improved to make it more cohesive.

What motivated the choice of passive UAV-monitoring technologies discussed in your review, and how representative are they of the broader field of UAV detection and tracking?

Mentioning the availability of datasets is a commendable effort. It would be helpful to specify where these datasets can be accessed, whether they come with documentation, and whether they have been used in any prior research.

Could you provide more specific examples or case studies where edge computing and deep learning have been successfully integrated into UAV detection and tracking systems, highlighting their impact on speed and cost reduction?

Can the authors clarify the specific passive UAV-monitoring technologies that were comprehensively reviewed in this paper, and whether there was a focus on certain types or applications?

When discussing the strengths and limitations of anti-UAV systems, can you offer quantitative data or performance metrics to support your assessment, and are there any emerging technologies or strategies that address these limitations?

In your suggestions for developing general-purpose UAV-monitoring systems, can you elaborate on the process of integrating detection and tracking with appropriate countermeasures and provide examples of how this integration has been achieved in practice?

How do edge computing and deep learning contribute to the acceleration and cost reduction of UAV detection and tracking, and can the abstract provide a brief explanation or context for these technologies?

Regarding the strengths and limitations of anti-UAV systems, could the manuscript provide concrete examples or metrics to illustrate these points, making them more tangible for readers?

The abstract mentions suggestions for developing general-purpose UAV-monitoring systems. Could it elaborate on how these suggestions can be practically implemented or provide real-world examples where they have been successfully applied?

Author Response

1. Response to Reviewer 1

Comment 1:The abstract provides a clear overview of the paper's content. However, I recommend ensuring a smooth transition between the introduction of passive UAV-monitoring technologies and the discussion of anti-UAV systems. The structure of the abstract could be improved to make it more cohesive.

Response: Thank you for the suggestion, we have re-organized the abstract. The modified text is listed below and highlighted in the revised manuscript.

(Modified text):

In this article, we provide a comprehensive review of passive UAV surveillance technologies, encompassing RF-based, acoustic-based, and vision-based methods for UAV detection, localization, and tracking. Our research reveals that certain lightweight UAV depth detection models have been effectively downsized for deployment on edge devices, facilitating the integration of edge computing and deep learning. In the city-wide anti-UAV, the integration of numerous urban infrastructure monitoring facilities presents a challenge in achieving a centralized computing center due to the large volume of data. To address this, calculations can be performed on edge devices, enabling faster UAV detection. Currently, there is a wide range of anti-UAV systems that have been deployed in both commercial and military sectors to address the challenges posed by UAVs. In this article, we provide an overview of the existing military and commercial anti-UAV systems.

Comment 2:What motivated the choice of passive UAV-monitoring technologies discussed in your review, and how representative are they of the broader field of UAV detection and tracking?

Response: Thank you for bringing this to my attention. In the original draft, this particular aspect was not mentioned. We have now rewritten a portion of the introduction to provide a clearer explanation of the research's motivation and purpose.

(Modified text):

In the past, UAV-monitoring systems were primarily deployed in critical military and civilian facilities such as airports and military bases. However, with the increasing popularity of UAVs, the need for UAV-monitoring systems has expanded to a wider range of settings, including construction sites, communities, shopping malls, schools, and other locations. This has created a demand for UAV-monitoring systems that are more cost-effective, scalable, and responsive. To meet this challenge, researchers have been exploring ways to detect UAVs using lower-cost and passive sensors [ 28]. The development of software-defined radio has greatly reduced the cost of RF detection, making it more accessible to a broader range of users. In recent years, neural network-enhanced RF-based detection, visual-based detection, and acoustic-based detection have emerged as promising options for general UAV-monitoring systems in urban environments. With the development of lightweight models, there are already some models that can obtain acceptable results with very little computing resources, which makes it possible to use edge computing for UAV detection. While radar surveillance is highly effective in detecting aircraft, its use is limited to specific locations due to the high cost and radiation associated with the technology. As a result, it may not be suitable for detecting illegal UAVs in urban areas.

Our findings indicate that within the research community, there is a notable divergence in focus regarding anti-UAV research. While some researchers prioritize the development of low-cost and lightweight anti-UAV solutions, the majority of researchers show a greater interest in enhancing the effectiveness of UAV detection and tracking. Our survey aims to address this disparity and raise awareness among researchers regarding the broader anti-UAV requirements in urban environments. We believe there is a pressing need for further exploration of low-cost and passive sensor-based anti-UAV systems. By directing attention towards these areas, we hope to foster increased research and innovation in developing comprehensive anti-UAV solutions that are both cost-effective and capable of meeting the specific challenges posed by urban environments.

Comment 3:Mentioning the availability of datasets is a commendable effort. It would be helpful to specify where these datasets can be accessed, whether they come with documentation, and whether they have been used in any prior research.

Response: Thank you for the suggestion. All the links to our listed datasets have been provided in the article. The RF datasets are linked in the references section, while the other datasets are linked in their respective locations within the article. All of the datasets mentioned in the article have been thoroughly documented and validated in at least one study. These measures ensure the reliability and credibility of the data used in our research.

(Modified text):

All of the datasets mentioned are linked in the text or in the references. Most of these datasets have been validated in multiple studies, and researchers can find more specific information in the corresponding papers or documents.

To evaluate the performance of acoustic-based detection, the following two datasets and metrics are usually used, i.e., DroneAudioDataset [58](can be found from GitHub repository: https://github.com/saraalemadi/DroneAudioDataset, accessed on June 1,2023) and theCasabianca’s Dataset [59 ](can be found from GitHub repository: https://github.com/pcasabianca/Acoustic-UAV-Identification, accessed on June 1,2023).

The datasets referenced, namely the Real World dataset, the Det-Fly dataset, the MIDGARD dataset, the USC-Drone dataset, and the DUT-Anti-UAV, can be accessed through the following provided links: https://github.com/Maciullo/DroneDetectionDataset, https://github.com/JakeWU/Det-Fly, https://mrs.felk.cvut.cz/midgard, https://github.com/chelicynly/A-Deep-Learning-Approach-to-Drone-Monitoring and https://github.com/wangdongdut/DUT-Anti-UAV, accessed on June 1,2023. The DUT-Anti-UAV … It is publicly available at https://github.com/ucas-vg/Anti-UAV, accessed on June 1,2023. Meanwhile, in USC-GRAD-STDdb dataset,there are 115 video segments, totally over 25,000 annotated frames in HD 720p resolution. The USC-GRAD-STDdb dataset is available at https://citius.usc.es/t/usc-grad-stddb, accessed on June 1,2023.

Comment 4:Could you provide more specific examples or case studies where edge computing and deep learning have been successfully integrated into UAV detection and tracking systems, highlighting their impact on speed and cost reduction?

Response: Thank you for the suggestion. To illustrate this point in more detail, we have added additional edge node deployment cases.

(Modified text):

Edge computing is to store and process data on edge devices. It has the characteristics of fast data processing and analysis speed and strong real-time performance. However, edge devices have limited computing power, so they can only perform lightweight operations. Currently, edge computing’s application in UAV detection and tracking primarily revolves around sensor data fusion. This approach effectively reduces data storage and bandwidth requirements while enhancing latency and response time. An example of a commercially available multi-sensor fusion networking device is Droneshield’s SmartHub Mk2. Furthermore, the literature has explored lightweight deep network models that enable quick and accurate UAV detection and tracking within the constraints of limited computational resources. These studies shed light on the potential of leveraging edge computing for UAV detection and tracking. Carolyn J. Swinney et al. [ 34] introduces a cost-effective early warning system for UAV detection and classification. The system is composed of a BladeRF software-defined radio (SDR), a wideband antenna, and a Raspberry Pi 4, which together form an edge node. Remarkably, this setup is designed to be affordable, with a total cost of under USD 540. This produced overall accuracy for a two-class detection system at 100% and 90.9% for UAV type classification on the UAVs tested.The inference times for two-class detection in this system range from 15 to 28 seconds, while for the six-class UAV type classification system, the inference times range from 18 to 28 seconds. RF-UAVNet [83 ] is a lightweight convolutional neural network based on RF. Its grouped convolution layer can significantly reduce network size and computing cost; multi-level skip connections and multi-gap mechanisms can effectively improve accuracy. Notably, it achieves remarkable performance withan accuracy of approximately 99.9% for UAV detection, 98.6% for UAV classification, and 95.3% for operation recognition. What sets RF-UAVNet apart is its low complexity, boasting a mere 11,000 parameters. TIB-Net [84] introduces a cyclic pathway in the iterative backbone to keep the model size lightweight while utilizing low-level feature information, and the integrated spatial attention module further improves the performance. TIB-Net, stands out not only for its compact size but also for its efficiency. With a model size of less than 700Kb and a remarkably low number of parameters at 0.1 million, TIB-Net demonstrates its ability to achieve notable results (approximately 89.2% for UAV detection) while maintaining a lightweight structure. In addition, there are other lightweight models available, such as the visual-based MOF-YOLO, which can be deployed on edge nodes. However, it is worth noting that the accuracy of MOF-YOLO is relatively lower at 49.62%. Nonetheless, it is reasonable to assume that this model can achieve higher accuracy if trained on a dedicated UAV dataset. It is essential to consider further research and training to potentially enhance the accuracy of MOF-YOLO for improved performance in UAV detection and classification tasks. According to our observation, the development of these lightweight models mainly considers taking certain measures to reduce the size and calculation amount of the model while retaining low-level information as much as possible, and using some mechanisms to improve accuracy.

In the future, city-wide anti-UAV systems are poised to become integral to the development of smart cities. However, the vast amount of surveillance data generated in the city’s airspace poses a significant challenge for a centralized computing center. To address this challenge, deploying detection models directly on edge devices and utilizing edge computing for UAV detection on these devices, can greatly reduce data transmission requirements and expedite UAV detection processes.

Comment 5:Can the authors clarify the specific passive UAV-monitoring technologies that were comprehensively reviewed in this paper, and whether there was a focus on certain types or applications?

Response: Thank you for the question. Our perspective is that each approach has its own distinct advantages and disadvantages that are challenging to overcome. As a result, there is no single detection method that can be universally suitable for all scenarios. We advocate for the selection of appropriate detection methods based on the specific application scenario. Where feasible, we recommend utilizing a combination of multiple detection methods, which aligns with the preferred approach of many commercial and military anti-UAV systems. By employing a combination of methods, it is possible to leverage the strengths of each approach and enhance overall detection capabilities.

Comment 6:When discussing the strengths and limitations of anti-UAV systems, can you offer quantitative data or performance metrics to support your assessment, and are there any emerging technologies or strategies that address these limitations?

Response: Thank you for the question. As we do not have direct access to anti-UAV systems for testing purposes, our information about these systems is obtained solely from their websites and other literature sources. We have included additional information regarding the detection rangeand the ability to record evidence as supplementary details. However, the accuracy of detection, which is a crucial concern for researchers, could not be obtained due to the lack of available data.

(Modified text):

Each system uses different surveillance techniques and implements various functions, as summarized in Table 8. The examples of these systems are shown in Figure 3. These systems have demonstrated their effectiveness in UAV detection and tracking. To enhance their detection capabilities, the majority of anti-UAV systems opt to utilize multiple types of sensors. These systems primarily find application in scenarios such as airport operations and military protection.

However, Dedrone stands out as a rare system provider that specifically addresses urban settings, including sports events and outdoor concerts. DeDrone and ARDRONIS are two anti-UAV systems that offer video evidence recording capabilities, although they employ different methods. DeDrone utilizes the visual monitor within the system to directly record video evidence when a UAV is detected. On the other hand, ARDRONIS obtains the UAV’s field of view by intercepting the visual transmission signal of the UAV. It is important to note that while DeDrone can record and save evidence whenever a UAV is detected, ARDRONIS can only achieve video recording when it successfully cracks the visual transmission signal of the UAV.

Comment 7:In your suggestions for developing general-purpose UAV-monitoring systems, can you elaborate on the process of integrating detection and tracking with appropriate countermeasures and provide examples of how this integration has been achieved in practice?

Response: Thank you for the question. We have added the details of this suggestion.

(Modified text):

Second, the detection and tracking components of the system should be integrated with appropriate countermeasure capabilities. One of the most prevalent countermeasure equipment against intruding drones is the use of RF jamming guns. These devices are designed to disrupt the communication and control signals of the UAVs, forcing them to either land or return to their point of origin. RF jamming guns are widely employed as a common UAV countermeasure.

Another commonly utilized countermeasure involves deploying UAVs to capture intruding UAVs. This approach involves using specially designed UAVs equipped with nets, cables, or other mechanisms to physically intercept and capture the unauthorized UAVs. Both RF jamming guns and UAV capture methods serve as effective countermeasures in mitigating the risks and potential threats posed by unauthorized drone activities.

Comment 8:How do edge computing and deep learning contribute to the acceleration and cost reduction of UAV detection and tracking, and can the abstract provide a brief explanation or context for these technologies?

Response: Thank you for the question. We have added the explanation in the abstract.

(Modified text):

Our research reveals that certain lightweight UAV depth detection models have been effectively downsized for deployment on edge devices, facilitating the integration of edge computing and deep learning. In the city-wide anti-UAV, the integration of numerous urban infrastructure monitoring facilities presents a challenge in achieving a centralized computing center due to the large volume of data. To address this, calculations can be performed on edge devices, enabling faster UAV detection.

Comment 9:Regarding the strengths and limitations of anti-UAV systems, could the manuscript provide concrete examples or metrics to illustrate these points, making them more tangible for readers?

Response: Thank you for the question. We've added a paragraph for a more detailed comparison of these anti-UAV systems.

(Modified text):

Each system uses different surveillance techniques and implements various functions, as summarized in Table 8. The examples of these systems are shown in Figure 3. These systems have demonstrated their effectiveness in UAV detection and tracking. To enhance their detection capabilities, the majority of anti-UAV systems opt to utilize multiple types of sensors. These systems primarily find application in scenarios such as airport operations and military protection.

However, Dedrone stands out as a rare system provider that specifically addresses urban settings, including sports events and outdoor concerts. DeDrone and ARDRONIS are two anti-UAV systems that offer video evidence recording capabilities, although they employ different methods.

DeDrone utilizes the visual monitor within the system to directly record video evidence when a UAV is detected. On the other hand, ARDRONIS obtains the UAV’s field of view by intercepting the visual transmission signal of the UAV. It is important to note that while DeDrone can record and save evidence whenever a UAV is detected, ARDRONIS can only achieve video recording when it successfully cracks the visual transmission signal of the UAV. Dedrone’s products and design concepts serve as a valuable source of inspiration for tackling the challenges of anti-UAV systems in urban environments. Their emphasis on scalable software platforms and leveraging existing infrastructure offers valuable insights for research and development in this field. By incorporating such approaches, it is possible to enhance the effectiveness and adaptability of anti-UAV systems in urban settings.

Comment 10:The abstract mentions suggestions for developing general-purpose UAV-monitoring systems. Could it elaborate on how these suggestions can be practically implemented or provide real-world examples where they have been successfully applied?

Response: Thank you for the question. We have enriched our suggestions with additional details and precautions to enhance their reference value.

(Modified text):

Inspired by the above anti-UAV systems, we propose several suggestions for developing effective and scalable general anti-UAV systems. First, it is essential to consider the specific needs and requirements of the application scenario when selecting and combining sensors. Indeed, various environmental factors can impact the effectiveness of different surveillance methods in urban environments. For instance, visual surveillance may face challenges in locations with low visibility caused by heavy fog, sand, or dust. Similarly, complex electromagnetic environments can negatively affect the performance of RF surveillance. Additionally, acoustic surveillance may not be suitable in areas with strong winds or high levels of ambient noise. It is essential to consider these factors when selecting the most appropriate surveillance method for UAV detection, ensuring optimal performance in diverse urban scenarios.

Second, the detection and tracking components of the system should be integrated with appropriate countermeasure capabilities. One of the most prevalent countermeasure equipment against intruding UAVs is the use of RF jamming guns. These devices are designed to disrupt the communication and control signals of the UAVs, forcing them to either land or return to their point of origin. RF jamming guns are widely employed as a common UAV countermeasure.

Another commonly utilized countermeasure involves deploying UAVs to capture intruding UAVs. This approach involves using specially designed UAVs equipped with nets, cables, or other mechanisms to physically intercept and capture the unauthorized UAVs.Both RF jamming guns and UAV capture methods serve as effective countermeasures in mitigating the risks and potential threats posed by unauthorized UAV activities.

Third, the system should be designed to be scalable and modular, allowing for easy deployment and adaptation to changing conditions. The design concept put forth by Dedrone Company offers valuable inspiration. It emphasizes the importance of creating scalable anti-UAV systems with a platform at the core. Such a design enables easier integration and maintenance of sensors in the future. By adopting a scalable approach, anti-UAV systems can adapt to evolving threats and technological advancements, ensuring flexibility and efficiency in the long run.

Fourth, data analytics and machine learning techniques can be employed to enhance the accuracy and efficiency of UAV detection and tracking. Indeed, machine learning techniques have already found extensive application in the field of UAV detection. The continuous advancements in machine learning algorithms and the availability of more comprehensive datasets are key factors in enhancing UAV detection capabilities. By leveraging more efficient learning methods and utilizing diverse and representative datasets, the accuracy and effectiveness of UAV detection systems can be significantly improved. This ongoing development in machine learning holds promise for further advancements in UAV detection technology.

Fifth, although accuracy is an important evaluation indicator, lightweight anti-UAV systems that sacrifice part of the accuracy seem to be more in demand in some non-important scenarios. In mobile scenarios or situations where budget constraints exist, lightweight anti-UAV systems that can operate on portable devices offer a more suitable solution. These systems, designed to be lightweight and portable, can be easily deployed and utilized in various environments. They provide flexibility and cost-effectiveness, making them a practical choice for scenarios where mobility and budget considerations are important factors. By leveraging lightweight anti-UAV systems, organizations can enhance their capabilities for UAV detection and mitigation while maintaining operational efficiency.Furthermore, compatibility with existing sensors, such as ubiquitous video surveillance equipment, could significantly reduce the cost of anti-UAV systems. This suggestion of leveraging existing video surveillance equipment, inspired by Dedrone's products, is indeed valuable. By ensuring compatibility and utilization of the already deployed video surveillance infrastructure, the deployment costs of anti-UAV systems can be significantly reduced. This approach aligns with the concept of using edge computing to assist in UAV detection, as previously discussed. By calibrating the physical locations of these monitoring devices, it becomes possible to detect and track illegally intruding UAVs effectively. This application scenario showcases the potential for cost-effective and efficient UAV detection by leveraging existing resources and edge computing capabilities.

Reviewer 2 Report

Clarity of Objectives: The paper starts by mentioning the importance of UAV detection and tracking but could benefit from a clearer statement of the specific objectives and goals of the review. What is the primary aim of this paper, and what are the expected outcomes?

Structural Organization: The paper's structure could be improved by providing a clear outline of how the content is organized. Consider adding a brief section or subsection headers to guide readers through the review effectively.

In-Depth Evaluation: While the paper mentions "emphasizing on those combining edge computing and deep learning," it would be beneficial to delve deeper into the advantages and disadvantages of combining these technologies. Providing specific use cases or examples could enhance the paper's content.

Comparative Analysis: To help readers make informed decisions, consider including a comparative analysis of different passive UAV-monitoring technologies. Highlight their strengths, weaknesses, and when each technology is most suitable.

Commercial and Military Systems: The section discussing existing anti-UAV systems is valuable, but it could be improved by providing more detailed insights into these systems, including case studies or real-world examples where possible.

Proposed Suggestions: The suggestions for developing general-purpose UAV-monitoring systems are important. However, they could be more actionable by providing practical steps or considerations for each suggestion.

Datasets: The collection of public datasets is a valuable resource. To enhance this section, provide more information about the datasets, such as their size, sources, and any specific challenges they address. Additionally, consider adding references or links to access these datasets.

Please avoid citing sources that were published before to 2019. Cite current research that are really pertinent to your topic. The study also lacks sufficient citations. Another critical step is to compare the topic of the article to other relevant recent publications or works in order to widen the research's repercussions beyond the issue. Authors can use and depend on these essential works while addressing the topic of their paper and current issues.

Heidari, A., Jafari Navimipour, N., Unal, M., & Zhang, G. (2023). Machine learning applications in internet-of-drones: systematic review, recent deployments, and open issues. ACM Computing Surveys, 55(12), 1-45.

Iftikhar, Sundas, et al. "Target Detection and Recognition for Traffic Congestion in Smart Cities Using Deep Learning-Enabled UAVs: A Review and Analysis." Applied Sciences 13.6 (2023): 3995.

A. Heidari, N. Jafari Navimipour and M. Unal, "A Secure Intrusion Detection Platform Using Blockchain and Radial Basis Function Neural Networks for Internet of Drones," in IEEE Internet of Things Journal, vol. 10, no. 10, pp. 8445-8454, 15 May15, 2023, doi: 10.1109/JIOT.2023.3237661.

Abbas, Nadir, Zeshan Abbas, Xiaodong Liu, Saad Saleem Khan, Eric Deale Foster, and Stephen Larkin. "A Survey: Future Smart Cities Based on Advance Control of Unmanned Aerial Vehicles (UAVs)." Applied Sciences 13, no. 17 (2023): 9881.

Minor editing of the English language required

Author Response

1. Response to Reviewer 2

Comment 1:Clarity of Objectives: The paper starts by mentioning the importance of UAV

detection and tracking but could benefit from a clearer statement of the specific objectives and

goals of the review. What is the primary aim of this paper, and what are the expected outcomes?

Response: Thank you for bringing this to my attention. In the original draft, this particular aspect was not mentioned. We have now rewritten a portion of the introduction to provide a clearer explanation of the research's motivation and purpose.

(Modified text):

In the past, UAV-monitoring systems were primarily deployed in critical military and civilian facilities such as airports and military bases. However, with the increasing popularity of UAVs, the need for UAV-monitoring systems has expanded to a wider range of settings, including construction sites, communities, shopping malls, schools, and other locations. This has created a demand for UAV-monitoring systems that are more cost-effective, scalable, and responsive. To meet this challenge, researchers have been exploring ways to detect UAVs using lower-cost and passive sensors [ 28]. The development of software-defined radio has greatly reduced the cost of RF detection, making it more accessible to a broader range of users. In recent years, neural network-enhanced RF-based detection, visual-based detection, and acoustic-based detection have emerged as promising options for general UAV-monitoring systems in urban environments. With the development of lightweight models, there are already some models that can obtain acceptable results with very little computing resources, which makes it possible to use edge computing for UAV detection. While radar surveillance is highly effective in detecting aircraft, its use is limited to specific locations due to the high cost and radiation associated with the technology. As a result, it may not be suitable for detecting illegal UAVs in urban areas.

Our findings indicate that within the research community, there is a notable divergence in focus regarding anti-UAV research. While some researchers prioritize the development of low-cost and lightweight anti-UAV solutions, the majority of researchers show a greater interest in enhancing the effectiveness of UAV detection and tracking. Our survey aims to address this disparity and raise awareness among researchers regarding the broader anti-UAV requirements in urban environments. We believe there is a pressing need for further exploration of low-cost and passive sensor-based anti-UAV systems. By directing attention towards these areas, we hope to fosterincreased research and innovation in developing comprehensive anti-UAV solutions that are both cost-effective and capable of meeting the specific challenges posed by urban environments.

Comment 2:Structural Organization: The paper's structure could be improved by providing a clear outline of how the content is organized. Consider adding a brief section or subsection headers to guide readers through the review effectively.

Response: Thank you for the question. We have added the section headers in the article.

(Modified text):

In this section, we will conduct a comprehensive analysis and comparison of RF-based, acoustic-based, and vision-based methods for the detection and identification of UAVs in urban IoT environments. We will explore these methods from various perspectives, including traditional methods, deep learning methods, and the available public and semi-public datasets. Additionally, we will discuss the specific challenges associated with identifying UAV intrusions in IoT environments and review recent research focused on leveraging edge devices for UAV detection.

Table 2 provides a performance comparison of various UAV detection methods, with the data obtained from literature research. The vision method based on deep learning demonstrates good accuracy even when experiments are conducted on public datasets that are not specifically optimized for UAVs. However, recent studies in the literature have shown that after fine-tuning, optimization, and training on specialized UAV datasets, the accuracy rate can exceed 90\%, indicating a high level of competitiveness.

UAV localization and tracking play a crucial role in anti-UAV research. This section provides  review of UAV localization and UAV tracking methods. UAV localization research primarily concentrates on utilizing RF and acoustic-based methods. These methods are preferred due to their ability to accurately determine the location of UAVs. Regarding UAV tracking, we categorize the studies into filter-based approaches and deep Siamese networks approaches. Filter-based methods utilize various filters for tracking UAVs, while deep Siamese networks approaches leverage deep learning techniques for tracking. The advancements made in these research areas are thoroughly discussed, highlighting the progress and innovations achieved in UAV tracking.

Comment 3:In-Depth Evaluation: While the paper mentions "emphasizing on those combining edge computing and deep learning," it would be beneficial to delve deeper into the advantages and disadvantages of combining these technologies. Providing specific use cases or examples could enhance the paper's content.

Response: Thank you for the question. We have rewritten this section and added more examples.

(Modified text):

Edge computing is to store and process data on edge devices. It has the characteristics of fast data processing and analysis speed and strong real-time performance. However, edge devices have limited computing power, so they can only perform lightweight operations. Currently, edge computing’s application in UAV detection and tracking primarily revolves around sensor datafusion. This approach effectively reduces data storage and bandwidth requirements while enhancing latency and response time. An example of a commercially available multi-sensor fusion networking device is Droneshield’s SmartHub Mk2. Furthermore, the literature has explored lightweight deep network models that enable quick and accurate UAV detection and tracking within the constraints of limited computational resources. These studies shed light on the potential of leveraging edge computing for UAV detection and tracking. Carolyn J. Swinney et al. [34 ] introduces a cost-effective early warning system for UAV detection and classification. The system is composed of a BladeRF software-defined radio (SDR), a wideband antenna, and a Raspberry Pi 4, which together form an edge node. Remarkably, this setup is designed to be affordable, with a total cost of under USD 540. This produced overall accuracy for a two-class detection system at 100% and 90.9% for UAV type classification on the UAVs tested.The inference times for two-class Version October 1, 2023 submitted to Journal Not Specified 15 of 27 detection in this system range from 15 to 28 seconds, while for the six-class UAV type classification system, the inference times range from 18 to 28 seconds. RF-UAVNet [83] is a lightweight convolutional neural network based on RF. Its grouped convolution layer can significantly reduce network size and computing cost; multi-level skip connections and multi-gap mechanisms can effectively improve accuracy. Notably, it achieves remarkable performance with an accuracy of approximately 99.9% for UAV detection, 98.6% for UAV classification, and 95.3% for operation recognition. What sets RF-UAVNet apart is its low complexity, boasting a mere 11,000 parameters. TIB-Net [ 84] introduces a cyclic pathway in the iterative backbone to keep the model size lightweight while utilizing low-level feature information, and the integrated spatial attention module further improves the performance. TIB-Net, stands out not only for its compact size but also for its efficiency. With a model size of less than 700Kb and a remarkably low number of parameters at 0.1 million, TIB-Net demonstrates its ability to achieve notable results (approximately 89.2% for UAV detection) while maintaining a lightweight structure. In addition, there are other lightweight models available, such as the visual-based MOB-YOLO [85 ], which can be deployed on edge nodes. However, it is worth noting that the accuracy of MOB-YOLO is relatively lower at 49.62%. Nonetheless, it is reasonable to assume that this model can achieve higher accuracy if trained on a dedicated UAV dataset. It is essential to consider further research and training to potentially enhance the accuracy of MOF-YOLO for improved performance in UAV detection and classification tasks. According to our observation, the development of these lightweight models mainly considers taking certain measures to reduce the size and calculation amount of the model while retaining low-level information as much as possible, and using some mechanisms to improve accuracy.

In the future, city-wide anti-UAV systems are poised to become integral to the development of smart cities. However, the vast amount of surveillance data generated in the city’s airspace poses a significant challenge for a centralized computing center. To address this challenge, deploying detection models directly on edge devices and utilizing edge computing for UAV detection on these devices, can greatly reduce data transmission requirements and expedite UAV detection processes.

Comment 4:Comparative Analysis: To help readers make informed decisions, consider including a comparative analysis of different passive UAV-monitoring technologies. Highlight their strengths, weaknesses, and when each technology is most suitable.

Response: Thank you for the question. We have added the details of different technologies and a chart to show the strengths, weaknesses.

(Modified text):

Experimental results indicate that the detection range of radar rarely surpasses 10000 meters [23]. RF surveillance exhibit the capability to detect and locate UAVs within a range of 5000m. However, their performance can be influenced by factors such as multipath and non-line-of-sight propagation.

Vision-based methods encounter challenges in distinguishing UAVs from birds, particularly when the UAVs are situated at a considerable distance. In fact, identifying UAVs beyond a range of 1,000 meters becomes exceedingly arduous, if not nearly impossible. Nevertheless, acoustic monitoring is highly susceptible to ambient noise and possesses a constrained detection range. As per the conducted tests, the maximum detection range for UAVs oes not exceed 300m. Table 1 provides a comprehensive overview of the aforementioned monitoring techniques. It is crucial to acknowledge that the detection distances presented are derived from existing literature and systems, and may exhibit variations based on factors such as UAV type, hardware parameters, and associated algorithms.

Comment 5:Commercial and Military Systems: The section discussing existing anti-UAV systems is valuable, but it could be improved by providing more detailed insights into these systems, including case studies or real-world examples where possible.

Response: Thank you for the question. We've added a paragraph for a more detailed comparison of these anti-UAV systems.

(Modified text):

Each system uses different surveillance techniques and implements various functions, as summarized in Table 8. The examples of these systems are shown in Figure 3. These systems have demonstrated their effectiveness in UAV detection and tracking. To enhance their detection capabilities, the majority of anti-UAV systems opt to utilize multiple types of sensors. These systems primarily find application in scenarios such as airport operations and military protection.

However, Dedrone stands out as a rare system provider that specifically addresses urban settings, including sports events and outdoor concerts. DeDrone and ARDRONIS are two anti-UAV systems that offer video evidence recording capabilities, although they employ different methods. DeDrone utilizes the visual monitor within the system to directly record video evidence when a UAV is detected. On the other hand, ARDRONIS obtains the UAV’s field of view by intercepting the visual transmission signal of the UAV. It is important to note that while DeDrone can record and save evidence whenever a UAV is detected, ARDRONIS can only achieve video recording when it successfully cracks the visual transmission signal of the UAV. Dedrone’s products and design concepts serve as a valuable source of inspiration for tackling the challenges of anti-UAVsystems in urban environments. Their emphasis on scalable software platforms and leveraging existing infrastructure offers valuable insights for research and development in this field. By incorporating such approaches, it is possible to enhance the effectiveness and adaptability of anti-UAV systems in urban settings.

Comment 6:Proposed Suggestions: The suggestions for developing general-purpose UAV-monitoring systems are important. However, they could be more actionable by providing practical steps or considerations for each suggestion.

Response: Thank you for the question. We have enriched our suggestions with additional details and precautions to enhance their reference value.

(Modified text):

Inspired by the above anti-UAV systems, we propose several suggestions for developing effective and scalable general anti-UAV systems. First, it is essential to consider the specific needs and requirements of the application scenario when selecting and combining sensors. Indeed, various environmental factors can impact the effectiveness of different surveillance methods in urban environments. For instance, visual surveillance may face challenges in locations with low visibility caused by heavy fog, sand, or dust. Similarly, complex electromagnetic environments can negatively affect the performance of RF surveillance. Additionally, acoustic surveillance may not be suitable in areas with strong winds or high levels of ambient noise. It is essential to consider these factors when selecting the most appropriate surveillance method for UAV detection, ensuring optimal performance in diverse urban scenarios.

Second, the detection and tracking components of the system should be integrated with appropriate countermeasure capabilities. One of the most prevalent countermeasure equipment against intruding UAVs is the use of RF jamming guns. These devices are designed to disrupt the communication and control signals of the UAVs, forcing them to either land or return to their point of origin. RF jamming guns are widely employed as a common UAV countermeasure.

Another commonly utilized countermeasure involves deploying UAVs to capture intruding UAVs. This approach involves using specially designed UAVs equipped with nets, cables, or other mechanisms to physically intercept and capture the unauthorized UAVs.Both RF jamming guns and UAV capture methods serve as effective countermeasures in mitigating the risks and potential threats posed by unauthorized UAV activities.

Third, the system should be designed to be scalable and modular, allowing for easy deployment and adaptation to changing conditions. The design concept put forth by Dedrone Company offers valuable inspiration. It emphasizes the importance of creating scalable anti-UAV systems with a platform at the core. Such a design enables easier integration and maintenance of sensors in the future. By adopting a scalable approach, anti-UAV systems can adapt to evolving threats and technological advancements, ensuring flexibility and efficiency in the long run.

Fourth, data analytics and machine learning techniques can be employed to enhance the accuracy and efficiency of UAV detection and tracking. Indeed, machine learning techniques have already found extensive application in the field of UAV detection. The continuous advancements in machine learning algorithms and the availability of more comprehensive datasets are key factors in enhancing UAV detection capabilities. By leveraging more efficient learning methodsand utilizing diverse and representative datasets, the accuracy and effectiveness of UAV detection systems can be significantly improved. This ongoing development in machine learning holds promise for further advancements in UAV detection technology.

Fifth, although accuracy is an important evaluation indicator, lightweight anti-UAV systems that sacrifice part of the accuracy seem to be more in demand in some non-important scenarios. In mobile scenarios or situations where budget constraints exist, lightweight anti-UAV systems that can operate on portable devices offer a more suitable solution. These systems, designed to be lightweight and portable, can be easily deployed and utilized in various environments. They

provide flexibility and cost-effectiveness, making them a practical choice for scenarios where mobility and budget considerations are important factors. By leveraging lightweight anti-UAV systems, organizations can enhance their capabilities for UAV detection and mitigation while maintaining operational efficiency.

Furthermore, compatibility with existing sensors, such as ubiquitous video surveillance equipment, could significantly reduce the cost of anti-UAV systems. This suggestion of leveraging existing video surveillance equipment, inspired by Dedrone's products, is indeed valuable. By ensuring compatibility and utilization of the already deployed video surveillance infrastructure, the deployment costs of anti-UAV systems can be significantly reduced. This approach aligns with the concept of using edge computing to assist in UAV detection, as previously discussed. By calibrating the physical locations of these monitoring devices, it becomes possible to detect and track illegally intruding UAVs effectively. This application scenario showcases the potential for cost-effective and efficient UAV detection by leveraging existing resources and edge computing capabilities.

Comment 7:Datasets: The collection of public datasets is a valuable resource. To enhance this section, provide more information about the datasets, such as their size, sources, and any specific challenges they address. Additionally, consider adding references or links to access these datasets.

Response: Thank you for the suggestion. All the links to our listed datasets have been provided in the article. The RF datasets are linked in the references section, while the other datasets are linked in their respective locations within the article. All of the datasets mentioned in the article have been thoroughly documented and validated in at least one study. These measures ensure the reliability and credibility of the data used in our research.

(Modified text):

All of the datasets mentioned are linked in the text or in the references. Most of these datasets have been validated in multiple studies, and researchers can find more specific information in the corresponding papers or documents.

To evaluate the performance of acoustic-based detection, the following two datasets and metrics are usually used, i.e., DroneAudioDataset [58](can be found from GitHub repository:

https://github.com/saraalemadi/DroneAudioDataset, accessed on June 1,2023) and the asabianca’s Dataset [59 ](can be found from GitHub repository: https://github.com/pcasabianca/Acoustic-UAV-Identification, accessed on June 1,2023).The datasets referenced, namely the Real World dataset, the Det-Fly dataset, the MIDGARD dataset, the USC-Drone dataset, and the DUT-Anti-UAV, can be accessed through the following provided links: https://github.com/Maciullo/DroneDetectionDataset,

https://github.com/JakeWU/Det-Fly, https://mrs.felk.cvut.cz/midgard,

https://github.com/chelicynly/A-Deep-Learning-Approach-to-Drone-Monitoring and https://github.com/wangdongdut/DUT-Anti-UAV, accessed on June 1,2023.

The DUT-Anti-UAV … It is publicly available at https://github.com/ucas-vg/Anti-UAV, ccessed on June 1,2023. Meanwhile, in USC-GRAD-STDdb dataset,there are 115 video segments, totally over 25,000 annotated frames in HD 720p resolution. The USC-GRAD-STDdb dataset is available at https://citius.usc.es/t/usc-grad-stddb, accessed on June 1,2023.

Comment 8:Please avoid citing sources that were published before to 2019. Cite current research that are really pertinent to your topic. The study also lacks sufficient citations. Another critical step is to compare the topic of the article to other relevant recent publications or works in order to widen the research's repercussions beyond the issue. Authors can use and depend on these essential works while addressing the topic of their paper and current issues.

Heidari, A., Jafari Navimipour, N., Unal, M., & Zhang, G. (2023). Machine learning applications in internet-of-drones: systematic review, recent deployments, and open issues. ACM Computing Surveys, 55(12), 1-45.

Iftikhar, Sundas, et al. "Target Detection and Recognition for Traffic Congestion in Smart Cities Using Deep Learning-Enabled UAVs: A Review and Analysis." Applied Sciences 13.6 (2023):3995

Heidari, N. Jafari Navimipour and M. Unal, "A Secure Intrusion Detection Platform Using Blockchain and Radial Basis Function Neural Networks for Internet of Drones," in IEEE Internet of Things Journal, vol. 10, no. 10, pp. 8445-8454, 15 May15, 2023, doi: 10.1109/JIOT.2023.3237661.

Abbas, Nadir, Zeshan Abbas, Xiaodong Liu, Saad Saleem Khan, Eric Deale Foster, and Stephen Larkin. "A Survey: Future Smart Cities Based on Advance Control of Unmanned Aerial Vehicles (UAVs)." Applied Sciences 13, no. 17 (2023): 9881.

Response: Thank you for your suggest. We have conducted a thorough review of the cited references. We have made the necessary adjustments to ensure that the majority of the references now consist of papers published after 2019. A small number of older references have been retained specifically for the purpose of explaining academic terms.

The references you have given are of great reference significance. Thank you for your recommendation.

(Modified text):

RBFNNs [82 ], which stands for Radial Basis Function Neural Networks, is a blockchain-based model that enhances data integrity and storage capabilities, enabling intelligent decision making across different Internet of Drone (IoD) environments. By leveraging blockchain technology, this model facilitates decentralized predictive analytics and the application of deep learning methods in a distributed manner. It proves to be a feasible and effective approach for the IoD environment.

The utilization of blockchain in developing decentralized predictive analytics and models ensures data integrity and enables secure sharing of deep learning methods. This approach aligns well with the requirements and constraints imposed by network intrusion detection, making RBFNNs a suitable choice for developing classifiers in such scenarios. By combining the strengths of blockchain and deep learning, RBFNNs provide a robust and secure framework for intelligent decision making in the IoD environment. It offers the potential for reliable and efficient network intrusion detection while maintaining data integrity and compliance with the constraints of the system.

Reviewer 3 Report

Dear Authors,

This paper reviews passive UAV-monitoring technologies, focusing on edge computing and deep learning. It discusses anti-UAV systems and suggests general-purpose systems for urban IoT environments. The paper also discusses anti-UAV systems and proposes suggestions for developing such systems. It suggests considering application scenarios, integrating detection and tracking with countermeasures, designing for scalability, and using advanced data analytics. Public datasets of visual, acoustic, and radio frequency data are collected for further research.

However, there are some minor comments that is are required to be considered for improving this work as follows:

General Comments:

1.       The publication offers a comprehensive survey for scientists and engineers working on edge computing and deep learning-based UAV tracking techniques.

2.       The overall organization, language use, style, methodology, comparisons, tables, and figures of the work are excellent. The readers may find this review to be very helpful.

3.       It is advised to update or revise the survey's title from "Urban IoT Environments" to "Urban Environments" in order to better reflect the wide range of applications in urban environments, such as VANET or MANET, IoT, WSN, etc.

4.       Some acronyms, like IoT ecosystems, are not defined. (in Abstract); GNSS for operation... (line 54 P.2),...of EESP cells... (line 165 P.4), RCNN... (line 556 P.8), SiamFC [99], SiamRPN++ [100], and LTMU... etc. Please add Abbreviations/Acronyms at the end of paper.

5.       To enhance this survey's quality and appeal, it is suggested that two or three taxonomy and classification diagrams be added to certain sections to clearly illustrate the methods; for instance, according to the type of methods, such as RF-based, Vision-based, and Acoustic-based.

6.       Lines 49–50 of P.2 Introduction: The authors list a number of radar innovations, including Non-line-of-sight radar, ultra-wideband radar, and millimeter-wave radar are further radar technologies that might be used. For secure communications, there are additionally chaotic mono-static, bi-static, and multi-static radars available. Here are some recent and suggested literary works, including:

[x]   Synchronization of Monostatic Radar Using a Time-Delayed Chaos-Based FM Waveform, remote sensing 2022

[x] Chaos Based Frequency Modulation for Joint Monostatic and Bistatic Radar-Communication Systems. Remote Sens. 2021

 [x] Low Observable Principles, Stealth Aircraft and Anti-Stealth Technologies. J. Comput. Model. 2014,

Thank you

Author Response

III. Response to Reviewer 3

Comment 1:The publication offers a comprehensive survey for scientists and engineers working on edge computing and deep learning-based UAV tracking techniques.

Response: Thank you very much for the comment. This positive assessment reinforces the value of our work in addressing the needs of researchers and practitioners in these fields.

Comment 2:The overall organization, language use, style, methodology, comparisons, tables, and figures of the work are excellent. The readers may find this review to be very helpful.

Response: Thank you for your positive feedback on our work. Your feedback serves as encouragement to continue delivering high-quality research and meaningful contributions to the field.

Comment 3:It is advised to update or revise the survey's title from "Urban IoT Environments" to "Urban Environments" in order to better reflect the wide range of applications in urban environments, such as VANET or MANET, IoT, WSN, etc.

Response:Thank you for your suggestion, we have rename our article.

Comment 4:Some acronyms, like IoT ecosystems, are not defined. (in Abstract); GNSS for operation... (line 54 P.2),...of EESP cells... (line 165 P.4), RCNN... (line 556 P.8), SiamFC [99], SiamRPN++ [100], and LTMU... etc. Please add Abbreviations/Acronyms at the end of paper.

Response:Thank you for your suggestion. These are errors that we overlooked in our writing, but we have since rectified them in the article.

(Modified text):

UAVs emiting RF wave signals can be intercepted and analyzed to track and locate them [24 ]. In many cases, manually operated UAVs communicate with a ground station and a GNSS (Global Navigation Satellite System) for operation, making it possible to intercept signals and obtain information such as coordinates and video feeds.

S. Lu et al. [ 35 ] tried to use time-frequency waterfall map directly to extract features by utilizes a network architecture comprising of EESP cells (According to the description in this literature, EESP may refer to the ESP, efficient spatial pyramid [21 ]) and employs the VGG feature extraction method, and achieved good results.

It is easy to understand how RCNN (Regions with CNN features) [ 62 ] works. Over the years, several advanced Siamese-based trackers have been proposed, such as SiamFC (Fully-Convolutional Siamese Networks) [109 ], SiamRPN++ (Siamese region proposal network plus plus) [ 110 ], and LTMU (High-Performance Long-Term Tracking with Meta-Updater) [ 111 ].

Comment 5:To enhance this survey's quality and appeal, it is suggested that two or three taxonomy and classification diagrams be added to certain sections to clearly illustrate the methods; for instance, according to the type of methods, such as RF-based, Vision-based, and Acoustic-based.

Response:Thank you for your suggestion. We have add a chart to illustrate the methods.

Comment 6: Lines 49–50 of P.2 Introduction: The authors list a number of radar innovations, including Non-line-of-sight radar, ultra-wideband radar, and millimeter-wave radar are further radar technologies that might be used. For secure communications, there are additionally chaotic mono-static, bi-static, and multi-static radars available. Here are some recent and suggested literary works, including:

[x]Synchronization of Monostatic Radar Using a Time-Delayed Chaos-Based FM Waveform, remote sensing 2022

[x] Chaos Based Frequency Modulation for Joint Monostatic and Bistatic Radar-Communication Systems. Remote Sens. 2021

[x] Low Observable Principles, Stealth Aircraft and Anti-Stealth Technologies. J. Comput. Model. 2014,

Response: Thank you for your suggest.The references you have given are of great reference significance. Thank you for your recommendation.(Modified text):

Other radar technologies that may be applicable include non-line-of-sight radar, ultra-wideband radar, millimeter-wave radar [18 ], chaotic mono-static, bi-static [ 19], and multi-static radars [20].

Summary: In addition to above changes, we have also corrected spelling and grammar errors, readded some descriptions to make the paper clearer, as highlighted in the revised manuscript.

Round 2

Reviewer 1 Report

The author has addressed all my comments in a professional manner. I am happy with the authors attitude. 

Reviewer 2 Report

The authors did a good revision, no more comments.