Search Results (119)

Deep learning with unmanned aerial vehicles (UAVs) is transforming maritime search and rescue (SAR) by enabling rapid object identification in challenging marine environments. This study benchmarks the performance of YOLO models for maritime SAR under diverse weather conditions using the SeaDronesSee and AFO datasets. The results show that while YOLOv7 achieved the highest mAP@50, it struggled with detecting small objects. In contrast, YOLOv10 and YOLOv11 deliver faster inference speeds but compromise slightly on precision. The key challenges discussed include environmental variability, sensor limitations, and scarce annotated data, which can be addressed by such techniques as attention modules and multimodal data fusion. Overall, the research results provide practical guidance for deploying efficient deep learning models in SAR, emphasizing specialized datasets and lightweight architectures for edge devices. Full article

This paper aims to analyze the performance of a tilt-rotor fixed-wing RPAS (Remotely Piloted Aircraft System) using a segmented approach, focusing on a nominal mission for SAR (Search and Rescue) applications. The study employs optimization techniques tailored to each segment to meet power consumption requirements, and the results highlight the accuracy of the physical characterization, which incorporates nonlinear propulsive and aerodynamic models derived from wind tunnel test campaigns. Critical segments for this nominal mission, such as the vertical take off or the transition from vertical to horizontal flight regimes, are addressed to fully understand the performance response of the aircraft. The proposed framework integrates experimental models into trajectory optimization procedures for each segment, enabling a realistic and modular analysis of energy use and aerodynamic performance. This approach provides valuable insights for both flight control design and future sizing iterations of convertible UAVs (Uncrewed Aerial Vehicles). Full article

Accurate prediction of drifting trajectories is essential for improving the operational efficiency of maritime search and rescue (SAR), particularly within the complex geomorphological settings of island and reef regions, such as those in the South China Sea. This study investigates the drift characteristics of life rafts under varying loading conditions across both open-sea and island–reef regions. Comprehensive field experiments were conducted over 15 days in the waters around the Wanshan Archipelago, using advanced instruments to collect wind, current, and drift trajectory data. Based on these observations, two models—the AP98 leeway model and a BP neural network model—were developed and validated. The results show that the AP98 model performs better in open-sea conditions, whereas the BP neural network provides more accurate predictions in island and reef areas with complex environmental factors. A Monte Carlo simulation was also integrated to enhance the robustness of drift area predictions. These findings offer valuable insights into life raft drift behavior in complex marine environments and provide technical support for improving SAR operations in island–reef regions. Full article

With the global increase in maritime activities, the frequency of maritime accidents has risen, underscoring the urgent need for faster and more efficient search and rescue (SAR) solutions. This study presents an intelligent unmanned aerial vehicle (UAV)-based maritime rescue system that combines GPS-driven dynamic path planning with vision-based dual-target detection and tracking. Developed within the Gazebo simulation environment and based on modular ROS architecture, the system supports stable takeoff and smooth transitions between multi-rotor and fixed-wing flight modes. An external command module enables real-time waypoint updates. This study proposes three path-planning schemes based on the characteristics of drones. Comparative experiments have demonstrated that the triangular path is the optimal route. Compared with the other schemes, this path reduces the flight distance by 30–40%. Robust target recognition is achieved using a darknet-ROS implementation of the YOLOv4 model, enhanced with data augmentation to improve performance in complex maritime conditions. A monocular vision-based ranging algorithm ensures accurate distance estimation and continuous tracking of rescue vessels. Furthermore, a dual-target-tracking algorithm—integrating motion prediction with color-based landing zone recognition—achieves a 96% success rate in precision landings under dynamic conditions. Experimental results show a 4% increase in the overall mission success rate compared to traditional SAR methods, along with significant gains in responsiveness and reliability. This research delivers a technically innovative and cost-effective UAV solution, offering strong potential for real-world maritime emergency response applications. Full article

Search and rescue (SAR) missions require reliable search methods to locate survivors, especially in challenging environments. Introducing unmanned aerial vehicles (UAVs) can enhance the efficiency of SAR missions while simultaneously increasing the safety of everyone involved. Motivated by this, we experiment with autonomous UAV search for humans in Mediterranean karst environment. The UAVs are directed using the Heat equation-driven area coverage (HEDAC) ergodic control method based on known probability density and detection function. The sensing framework consists of a probabilistic search model, motion control system, and object detection enabling to calculate the target’s detection probability. This paper focuses on the experimental validation of the proposed sensing framework. The uniform probability density, achieved by assigning suitable tasks to 78 volunteers, ensures the even probability of finding targets. The detection model is based on the You Only Look Once (YOLO) model trained on a previously collected orthophoto image database. The experimental search is carefully planned and conducted, while recording as many parameters as possible. The thorough analysis includes the motion control system, object detection, and search validation. The assessment of the detection and search performance strongly indicates that the detection model in the UAV control algorithm is aligned with real-world results. Full article

Maritime vision sensing can be applied to maritime unmanned systems to perform search and rescue (SAR) missions under complex marine environments, as multiple unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) are able to conduct vision sensing through the air, the water-surface, and underwater. However, in these vision-based maritime SAR systems, collaboration between UAVs and USVs is a critical issue for successful SAR operations. To address this challenge, in this paper, we propose a long-endurance collaborative SAR scheme which exploits the complementary strengths of the maritime unmanned systems. In this scheme, a swarm of UAVs leverages a multi-agent reinforcement-learning (MARL) method and probability maps to perform cooperative first-phase search exploiting UAV’s high altitude and wide field of view of vision sensing. Then, multiple USVs conduct precise real-time second-phase operations by refining the probabilistic map. To deal with the energy constraints of UAVs and perform long-endurance collaborative SAR missions, a multi-USV charging scheduling method is proposed based on MARL to prolong the UAVs’ flight time. Through extensive simulations, the experimental results verified the effectiveness of the proposed scheme and long-endurance search capabilities. Full article

The identification of vital signs is becoming increasingly important in various applications, including healthcare monitoring, security, smart homes, and locating entrapped persons after disastrous events, most of which are achieved using continuous-wave radars and ultra-wideband systems. Operating frequency and transmission power are important factors to consider when conducting earthquake search and rescue (SAR) operations in urban regions. Poor communication infrastructure can also impede SAR operations. This study proposes a method for vital sign detection using an integrated sensing and communication (ISAC) system where a unified orthogonal frequency division multiplexing (OFDM) signal was adopted, and it is capable of sensing life signs and carrying out communication simultaneously. An ISAC demonstration system based on software-defined radios (SDRs) was initiated to detect respiratory and heartbeat rates while maintaining communication capability in a typical office environment. The specially designed OFDM signals were transmitted, reflected from a human subject, received, and processed to estimate the micro-Doppler effect induced by the breathing and heartbeat of the human in the environment. According to the results, vital signs, including respiration and heartbeat rates, have been accurately detected by post-processing the reflected OFDM signals with a 1 MHz bandwidth, confirmed with conventional contact-based detection approaches. The potential of dual-function capability of OFDM signals for sensing purposes has been verified. The principle and method developed can be applied in wider ISAC systems for search and rescue purposes while maintaining communication links. Full article

Synthetic Aperture Radar (SAR) image ship detection faces challenges such as distinguishing ships from other terrains and structures, especially in specific marine complex environments. The motivation behind this work is to enhance detection accuracy while minimizing false positives, which is crucial for applications like defense vessel monitoring and civilian search and rescue operations. To achieve this goal, we propose several architectural improvements to You Only Look Once version 8 Nano (YOLOv8n) and present Small Target-YOLOv8(ST-YOLOv8)—a novel lightweight SAR ship detection model based on the enhance YOLOv8n framework. The C2f module in the backbone’s transition sections is replaced by the Conv_Online Reparameterized Convolution (C_OREPA) module, reducing convolutional complexity and improving efficiency. The Atrous Spatial Pyramid Pooling (ASPP) module is added to the end of the backbone to extract finer features from smaller and more complex ship targets. In the neck network, the Shuffle Attention (SA) module is employed before each upsampling step to improve upsampling quality. Additionally, we replace the Complete Intersection over Union (C-IoU) loss function with the Wise Intersection over Union (W-IoU) loss function, which enhances bounding box precision. We conducted ablation experiments on two widely used multimodal SAR datasets. The proposed model significantly outperforms the YOLOv8n baseline, achieving 94.1% accuracy, 82% recall, and 87.6% F1 score on the SAR Ship Detection Dataset (SSDD), and 92.7% accuracy, 84.5% recall, and 88.1% F1 score on the SAR Ship Dataset_v0 dataset (SSDv0). Furthermore, the ST-YOLOv8 model outperforms several state-of-the-art multi-scale ship detection algorithms on both datasets. In summary, the ST-YOLOv8 model, by integrating advanced neural network architectures and optimization techniques, significantly improves detection accuracy and reduces false detection rates. This makes it highly suitable for complex backgrounds and multi-scale ship detection. Future work will focus on lightweight model optimization for deployment on mobile platforms to broaden its applicability across different scenarios. Full article

The growth of maritime transportation has been accompanied by a gradual increase in accident rates, drawing greater attention to the critical issue of man-overboard incidents and drowning. Traditional maritime search-and-rescue (SAR) methods are often constrained by limited efficiency and high operational costs. Over the past few years, drones have demonstrated significant promise in improving the effectiveness of search-and-rescue operations. This is largely due to their exceptional ability to move freely and their capacity for wide-area monitoring. This study proposes an enhanced SR-DETR algorithm aimed at improving the detection of individuals who have fallen overboard. Specifically, the conventional multi-head self-attention (MHSA) mechanism is replaced with Efficient Additive Attention (EAA), which facilitates more efficient feature interaction while substantially reducing computational complexity. Moreover, we introduce a new feature aggregation module called the Cross-Stage Partial Parallel Atrous Feature Pyramid Network (CPAFPN). By refining spatial attention mechanisms, the module significantly boosts cross-scale target recognition capabilities in the model, especially offering advantages for detecting smaller objects. To improve localization precision, we develop a novel loss function for bounding box regression, named Focaler-GIoU, which performs particularly well when handling densely packed and small-scale objects. The proposed approach is validated through experiments and achieves an mAP of 86.5%, which surpasses the baseline RT-DETR model’s performance of 83.2%. These outcomes highlight the practicality and reliability of our method in detecting individuals overboard, contributing to more precise and resource-efficient solutions for real-time maritime rescue efforts. Full article

The civil and military use of autonomously or remotely controlled unmanned aerial vehicles (UAVs) has become standard in many sectors. However, their role as supplementary vehicles for helicopter emergency medical services (HEMS) or search and rescue (SAR)—particularly when aiding individuals in hard-to-reach terrains—remains underexplored and in need of further innovation. The feasibility of using UAVs in such operations depends on multiple factors, including legislative, economic, and market conditions. However, the most critical considerations are external factors that impact UAV flight, such as meteorological conditions (wind speed and direction), the designated operational area, the proficiency of the pilot–operator, and the classification and certification of the UAV, particularly if it has been modified for such missions. Additionally, the feasibility of the remote or autonomous control of the UAV in mountainous environments plays a crucial role in determining their effectiveness. Establishing a specialized simulation environment to address these challenges is essential for assessing UAV performance in mountainous regions. This is particularly relevant in the Slovak Republic, a very rugged landscape, where the planned expansion of UAV-assisted rescue operations must be preceded by thorough testing, flight verification, and operational planning within protected landscape areas. Moreover, significant legislative changes will be required, which can only be implemented after the comprehensive testing of UAV operations in these specific mountain environments. Full article

Search and rescue (SAR) operations in post-earthquake environments are hindered by unseen environment conditions and uncertain victim locations. While reinforcement learning (RL) has been used to enhance unmanned aerial vehicle (UAV) navigation in such scenarios, its limited generalisation to novel environments, such as post-disaster environments, remains a challenge. To deal with this issue, this paper proposes an RL-based framework that combines the principles of lifelong learning and eligibility traces. Here, the approach uses a shaping reward heuristic based on pre-training experiences obtained from similar environments to improve generalisation, and simultaneously, eligibility traces are used to accelerate convergence of the overall approach. The combined contributions allows the RL algorithm to adapt to new environments, whilst ensuring fast convergence, critical for rescue missions. Extensive simulation studies show that the proposed framework can improve the average reward return by 46% compared to baseline RL algorithms. Ablation studies are also conducted, which demonstrate a 23% improvement in the overall reward score in environments with different complexities and a 56% improvement in scenarios with varying numbers of trapped individuals. Full article

Ship detection in synthetic aperture radar (SAR) images holds significant importance for both military and civilian applications, including maritime traffic supervision, marine search and rescue operations, and emergency response initiatives. Although extensive research has been conducted in this field, the interference of speckle noise in SAR images and the potential discontinuity of target contours continue to pose challenges for the accurate detection of multi-directional ships in complex scenes. To address these issues, we propose a novel ship detection method for SAR images that leverages edge deformable convolution combined with point set representation. By integrating edge deformable convolution with backbone networks, we learn the correlations between discontinuous target blocks in SAR images. This process effectively suppresses speckle noise while capturing the overall offset characteristics of targets. On this basis, a multi-directional ship detection module utilizing radial basis function (RBF) point set representation is developed. By constructing a point set transformation function, we establish efficient geometric alignment between the point set and the predicted rotated box, and we impose constraints on the penalty term associated with point set transformation to ensure accurate mapping between point set features and directed prediction boxes. This methodology enables the precise detection of multi-directional ship targets even in dense scenes. The experimental results derived from two publicly available datasets, RSDD-SAR and SSDD, demonstrate that our proposed method achieves state-of-the-art performance when benchmarked against other advanced detection models. Full article

Ontology engineering (OE) plays a critical role in modeling and managing structured knowledge across various domains. This study examines the performance of fine-tuned large language models (LLMs), specifically GPT-4 and Mistral 7B, in efficiently automating OE tasks. Foundational OE textbooks are used as the basis for dataset creation and for feeding the LLMs. The methodology involved segmenting texts into manageable chapters, generating question–answer pairs, and translating visual elements into description logic to curate fine-tuned datasets in JSONL format. This research aims to enhance the models’ abilities to generate domain-specific ontologies, with hypotheses asserting that fine-tuned LLMs would outperform base models, and that domain-specific datasets would significantly improve their performance. Comparative experiments revealed that GPT-4 demonstrated superior accuracy and adherence to ontology syntax, albeit with higher computational costs. Conversely, Mistral 7B excelled in speed and cost efficiency but struggled with domain-specific tasks, often generating outputs that lacked syntactical precision and relevance. The presented results highlight the necessity of integrating domain-specific datasets to improve contextual understanding and practical utility in specialized applications, such as Search and Rescue (SAR) missions in wildfire incidents. Both models, despite their limitations, exhibited potential in understanding OE principles. However, their performance underscored the importance of aligning training data with domain-specific knowledge to emulate human expertise effectively. This study, based on and extending our previous work on the topic, concludes that fine-tuned LLMs with targeted datasets enhance their utility in OE, offering insights into improving future models for domain-specific applications. The findings advocate further exploration of hybrid solutions to balance accuracy and efficiency. Full article

In this article, the authors present contemporary problems in search and rescue operations at sea. The research focuses on the detection of the SART (Search and Rescue Transponder) device. This device is used to call for help and assist the rescuing vessel in tracking. Issues with their functionality may reduce the likelihood of finding a survivor. The authors designed an experiment to assess the effectiveness of using the device. The research conducted is a real-world experiment that involved a ship radar, a liferaft, a SART device, and a radar reflector. The experiment consisted of multiple trials to detect, locate, and track the device, as well as to assess the radar image features. Four scenarios were developed, considering different distances and radar settings. Performance evaluation indicators were also developed. The results are presented both graphically and numerically. A brief discussion of the obtained results and concise conclusions are provided. Along with the research findings, recommendations for the use of SART and radar on ships are also presented, as well as recommendations for improving training. The results are applicable to improving the effectiveness of SAR operations. Full article

Natural disasters create complex environments where effective human detection is both critical and challenging, especially when individuals are partially occluded. While recent advancements in computer vision have improved detection capabilities, there remains a significant need for efficient solutions that can enhance search-and-rescue (SAR) operations in resource-constrained disaster scenarios. This study modified the original DINO (Detection Transformer with Improved Denoising Anchor Boxes) model and introduced the visibility-enhanced DINO (VE-DINO) model, designed for robust human detection in occlusion-heavy environments, with potential integration into SAR system. VE-DINO enhances detection accuracy by incorporating body part key point information and employing a specialized loss function. The model was trained and validated using the COCO2017 dataset, with additional external testing conducted on the Disaster Occlusion Detection Dataset (DODD), which we developed by meticulously compiling relevant images from existing public datasets to represent occlusion scenarios in disaster contexts. The VE-DINO achieved an average precision of 0.615 at IoU 0.50:0.90 on all bounding boxes, outperforming the original DINO model (0.491) in the testing set. The external testing of VE-DINO achieved an average precision of 0.500. An ablation study was conducted and demonstrated the robustness of the model subject when confronted with varying degrees of body occlusion. Furthermore, to illustrate the practicality, we conducted a case study demonstrating the usability of the model when integrated into an unmanned aerial vehicle (UAV)-based SAR system, showcasing its potential in real-world scenarios. Full article