Search Results (314)

This paper presents a novel adversarial Convolutional Neural Network (ConvNet) method for generating adversarial perturbations in 3D point clouds, enabling gradient-free robustness evaluation of object detection systems at inference time. Unlike existing iterative gradient methods, our approach embeds the ConvNet directly into the detection pipeline at the voxel feature level. The ConvNet is trained to maximize detection loss while maintaining perturbations within sensor error bounds through multi-component loss constraints (intensity, bias, and imbalance terms). Evaluation on a Sparsely Embedded Convolutional Detection (SECOND) detector with the KITTI dataset shows 8% overall mean Average Precision (mAP) degradation, while CenterPoint on NuScenes exhibits 24% weighted mAP reduction across 10 object classes. Analysis reveals an inverse relationship between object size and adversarial vulnerability: smaller objects (pedestrians: 13%, cyclists: 14%) show higher vulnerability compared to larger vehicles (cars: 0.2%) on KITTI, with similar patterns on NuScenes, where barriers (68%) and pedestrians (32%) are most affected. Despite perturbations remaining within typical sensor error margins (mean L2 norm of 0.09% for KITTI, 0.05% for NuScenes, corresponding to 0.9–2.6 cm at typical urban distances), substantial detection failures occur. The key novelty is training a ConvNet to learn effective adversarial perturbations during a one-time training phase and then using the trained network for gradient-free robustness evaluation during inference, requiring only a forward pass through the ConvNet (1.2–2.0 ms overhead) instead of iterative gradient computation, making continuous vulnerability monitoring practical for autonomous driving safety assessment. Full article

In this paper, a target detection network algorithm based on a multi-branch convolution and attention improvement Cross-Stage Partial-Fusion Bottleneck with Two Convolutions (C2F) module is proposed for the difficult task of detecting small targets in unmanned aerial vehicles. A C2F module method consisting of fusing partial convolutional (PConv) layers was designed to improve the speed and efficiency of extracting features, and a method consisting of combining multi-scale feature fusion with a channel space attention mechanism was applied in the neck network. An FA-Block module was designed to improve feature fusion and attention to small targets’ features; this design increases the size of the miniscule target layer, allowing richer feature information about the small targets to be retained. Finally, the lightweight up-sampling operator Content-Aware ReAssembly of Features was used to replace the original up-sampling method to expand the network’s sensory field. Experimental tests were conducted on a self-complied mountain pedestrian dataset and the public VisDrone dataset. Compared with the base algorithm, the improved algorithm improved the mAP50, mAP50-95, P-value, and R-value by 2.8%, 3.5%, 2.3%, and 0.2%, respectively, on the Mountain Pedestrian dataset and the mAP50, mAP50-95, P-value, and R-value by 9.2%, 6.4%, 7.7%, and 7.6%, respectively, on the VisDrone dataset. Full article

Autonomous driving has emerged as a rapidly advancing field in both industry and academia over the past decade. Among the enabling technologies, computer vision (CV) has demonstrated high accuracy across various domains, making it a critical component of autonomous vehicle systems. However, CV tasks are computationally intensive and often require hardware accelerators to achieve real-time performance. Field Programmable Gate Arrays (FPGAs) have gained popularity in this context due to their reconfigurability and high energy efficiency. Numerous researchers have explored FPGA-accelerated CV solutions for autonomous driving, addressing key tasks such as lane detection, pedestrian recognition, traffic sign and signal classification, vehicle detection, object detection, environmental variability sensing, and fault analysis. Despite this growing body of work, the field remains fragmented, with significant variability in implementation approaches, evaluation metrics, and hardware platforms. Crucial performance factors, including latency, throughput, power consumption, energy efficiency, detection accuracy, datasets, and FPGA architectures, are often assessed inconsistently. To address this gap, this paper presents a comprehensive literature review of FPGA-accelerated, vision-based autonomous driving systems. It systematically examines existing solutions across sub-domains, categorizes key performance factors and synthesizes the current state of research. This study aims to provide a consolidated reference for researchers, supporting the development of more efficient and reliable next generation autonomous driving systems by highlighting trends, challenges, and opportunities in the field. Full article

To address the limitation of receptive fields caused by the use of local convolutions in current point cloud object detection methods, this paper proposes a LiDAR point cloud object detection algorithm that integrates global features. The proposed method employs a Voxel Mapping Block (VMB) and a Global Feature Extraction Block (GFEB) to convert the point cloud data into a one-dimensional long sequence. It then utilizes non-local convolutions to model the entire voxelized point cloud and incorporate global contextual information, thereby enhancing the network’s receptive field and its capability to extract and learn global features. Furthermore, a Voxel Channel Feature Extraction (VCFE) module is designed to capture local spatial information by associating features across different channels, effectively mitigating the spatial information loss introduced during the one-dimensional transformation. The experimental results demonstrate that, compared with state-of-the-art methods, the proposed approach improves the average precision of vehicle, pedestrian, and cyclist targets on the Waymo subset by 0.64%, 0.71%, and 0.66%, respectively. On the nuScenes dataset, the detection accuracy for var targets increased by 0.7%, with NDS and mAP improving by 0.3% and 0.5%, respectively. In particular, the method exhibits outstanding performance in small object detection, significantly enhancing the overall accuracy of point cloud object detection. Full article

Over the past decade, researchers have advanced traffic monitoring using surveillance cameras, unmanned aerial vehicles (UAVs), loop detectors, LiDAR, microwave sensors, and sensor fusion. These technologies effectively detect and track vehicles, enabling robust safety assessments. However, pedestrian detection remains challenging due to diverse motion patterns, varying clothing colors, occlusions, and positional differences. This study introduces an innovative approach that integrates multiple surveillance cameras at signalized intersections, regardless of their types or resolutions. Two distinct convolutional neural network (CNN)-based detection algorithms accurately track road users across multiple views. The resulting trajectories undergo analysis, smoothing, and integration, enabling detailed traffic scene reconstruction and precise identification of vehicle–pedestrian conflicts. The proposed framework achieved 97.73% detection precision and an average intersection over union (IoU) of 0.912 for pedestrians, compared to 68.36% and 0.743 with a single camera. For vehicles, it achieved 98.2% detection precision and an average IoU of 0.955, versus 58.78% and 0.516 with a single camera. These findings highlight significant improvements in detecting and analyzing traffic conflicts, enhancing the identification and mitigation of potential hazards. Full article

The effective management of smart cities relies on real-time data from urban environments, where Unmanned Aerial Vehicles (UAVs) are critical sensing platforms. However, deploying high-performance detection models on resource-constrained UAVs presents a major challenge, particularly for identifying small, dense targets like pedestrians and vehicles from high altitudes. This study aims to develop a lightweight yet accurate detection algorithm to bridge this gap. We propose YOLOv10-DSNet, an improved architecture based on YOLOv10. The model integrates three key innovations: a parallel dual attention mechanism (CBAM-P) to enhance focus on small-target features; a novel lightweight feature extraction module (C2f-LW) to reduce model complexity; and an additional 160 × 160 detection layer to improve sensitivity to fine-grained details. Experimental results demonstrate that YOLOv10-DSNet significantly outperforms the baseline, increasing mAP50-95 by 4.1% while concurrently decreasing computational costs by 1.6 G FLOPs and model size by 0.7 M parameters. The proposed model provides a practical and powerful solution that balances high accuracy with efficiency, advancing the capability of UAVs for critical smart city applications such as real-time traffic monitoring and public safety surveillance. Full article

Communications in intelligent transportation systems (ITS) face explosive data growth from applications such as autonomous driving, remote diagnostics, and real-time monitoring, imposing severe challenges on limited spectrum, bandwidth, and latency. Reliable semantic image reconstruction under noisy channel conditions is critical for ITS perception tasks, since noise directly impacts the recognition of both static infrastructure and dynamic obstacles. Unlike traditional approaches that aim to transmit all image data with equal fidelity, effective ITS communication requires prioritizing task-relevant dynamic elements such as vehicles and pedestrians while filtering out largely static background features such as buildings, road signs, and vegetation. To address this, we propose an Offline Knowledge Base and Attention-Driven Semantic Communication (OKBASC) framework for image-based applications in ITS scenarios. The proposed framework performs offline semantic segmentation to build a compact knowledge base of semantic masks, focusing on dynamic task-relevant regions such as vehicles, pedestrians, and traffic signals. At runtime, precomputed masks are adaptively fused with input images via sparse attention to generate semantic-aware representations that selectively preserve essential information while suppressing redundant background. Moreover, we introduce a further Bi-Level Routing Attention (BRA) module that hierarchically refines semantic features through global channel selection and local spatial attention, resulting in improved discriminability and compression efficiency. Experiments on the VOC2012 and nuPlan datasets under varying SNR levels show that OKBASC achieves higher semantic reconstruction quality than baseline methods, both quantitatively via the Structural Similarity Index Metric (SSIM) and qualitatively via visual comparisons. These results highlight the value of OKBASC as a communication-layer enabler that provides reliable perceptual inputs for downstream ITS applications, including cooperative perception, real-time traffic safety, and incident detection. Full article

The advancement of Artificial Intelligence (AI) and the Internet of Things (IoT) has accelerated the development of Intelligent Transportation Systems (ITS) in smart cities, playing a crucial role in optimizing traffic flow, enhancing road safety, and improving the driving experience. With urban traffic becoming increasingly complex, timely detection and response to congestion and accidents are critical to ensuring safety and situational awareness. This paper presents Passable, an intelligent and adaptive traffic light control system that monitors traffic conditions in real time using deep learning and computer vision. By analyzing images captured from cameras at traffic lights, Passable detects road incidents and dynamically adjusts signal timings based on current vehicle density. It also employs wireless communication to alert drivers and update a centralized dashboard accessible to traffic management authorities. A working prototype integrating both hardware and software components was developed and evaluated. Results demonstrate the feasibility and effectiveness of designing an adaptive traffic signal control system that integrates incident detection, instantaneous communication, and immediate reporting to the relevant authorities. Such a design can enhance traffic efficiency and contribute to road safety. Future work will involve testing the system with real-world vehicular communication technologies on multiple coordinated intersections while integrating pedestrian and emergency vehicle detection. Full article

Pedestrian safety at signalized intersections remains a pressing concern in rapidly urbanizing cities. This study introduces a trajectory–signal behavior spectrum, grounded in Behavior Spectrum Theory (BST), to quantify crossing risk using readily observable data. Unmanned aerial vehicle (UAV) video is employed to record pedestrian movements, which are then detected with YOLOv8 and tracked with ByteTrack, producing frame-level trajectories without dependence on line-of-sight instrumentation. Five spatiotemporal features—speed, acceleration, crossing time, remaining pedestrian-signal green time, and red-phase duration—are compiled into the spectrum. Features are normalized using the interquartile range (IQR) method, and objective weights are determined with an improved CRITIC (Criteria Importance Through Intercriteria Correlation) scheme that incorporates a median-based coefficient of variation and absolute correlation for conflict measurement. The resulting risk eigenvalues are clustered with K-means into four levels: no risk, low, medium, and high. A case study of 1210 crossings at a two-way eight-lane intersection in Harbin, China (576 compliant, 634 non-compliant) demonstrates the approach. Results show greater variability among non-compliant speeds (mean 1.29 m/s) compared with compliant crossings (mean 1.40 m/s), with more extreme deviations. Clustering achieved silhouette coefficients of 0.60 for compliant and 0.69 for non-compliant groups, while expert validation on 20 samples yielded substantial agreement (Fleiss’ Kappa = 0.87). This study provides a systematic and interpretable method for risk classification, which supports both theoretical understanding and applied traffic safety management. Full article

With the recent 5G communication technology deployment, Cellular Vehicle-to-Everything (C-V2X) significantly enhances road safety by enabling real-time exchange of critical traffic information among vehicles, pedestrians, infrastructure, and networks. However, further research is required to address real-time application latency and communication reliability challenges. This paper explores integrating cutting-edge C-V2X technology with environmental perception systems to enhance safety at intersections and crosswalks. We propose a multi-module architecture combining C-V2X with state-of-the-art perception technologies, GPS mapping methods, and the client–server module to develop a co-operative perception system for collision avoidance. The proposed system includes the following: (1) a hardware setup for C-V2X communication; (2) an advanced object detection module leveraging Deep Neural Networks (DNNs); (3) a client–server-based co-operative object detection framework to overcome computational limitations of edge computing devices; and (4) a module for mapping GPS coordinates of detected objects, enabling accurate and actionable GPS data for collision avoidance—even for detected objects not equipped with C-V2X devices. The proposed system was evaluated through real-time experiments at the GMMRC testing track at Kettering University. Results demonstrate that the proposed system enhances safety by broadcasting critical obstacle information with an average latency of 9.24 milliseconds, allowing for rapid situational awareness. Furthermore, the proposed system accurately provides GPS coordinates for detected obstacles, which is essential for effective collision avoidance. The technology integration in the proposed system offers high data rates, low latency, and reliable communication, which are key features that make it highly suitable for C-V2X-based applications. Full article

This study investigates the use of Autonomous Sensing Infrastructure and Connected and Autonomous Vehicles (CAV) technologies to support infrastructure-to-vehicle (I2V) and infrastructure-to-everything (I2X) communications, including the alerting of drivers and pedestrians. It describes research findings in the following CAV functionalities: (1) Intersection-based object detection and tracking; (2) Basic Safety Message (BSM) generation and transmission; and (3) In-Vehicle BSM receipt and display, including handheld (smartphone) application BSM receipt and user presentation. The study summarizes the various software and hardware components used to create the I2V and I2X prototype solutions, which include open-source and commercial software as well as industry-standard transportation infrastructure hardware, e.g., Signal Controllers. Results from in-lab testing demonstrate effective object detection (e.g., pedestrians, bicycles) based on sample traffic camera video feeds as well as successful BSM message generation and receipt using the leveraged software and hardware components. The I2V and I2X solutions created as part of this research are scheduled to be deployed in a real-world intersection in coordination with state and local transportation agencies. Full article

In recent years, generative AI and autonomous driving have been highly popular topics. Additionally, with the increasing global emphasis on carbon emissions and carbon trading, integrating autonomous driving technologies that can instantly perceive environ-mental changes with vehicle-based generative AI would enable vehicles to better under-stand their surroundings and provide drivers with recommendations for more energy-efficient and comfortable driving. This study employed You Only Look Once version11 (YOLOv11) for visual detection of the driving environment, integrating it with vehicle speed data received from the OBD-II system. All information is integrated and processed using the embedded Nvidia Jetson AGX Orin platform. For visual detection validation, part of the test set includes standard Taiwanese road signs. Experimental results show that incorporating Squeeze-and-Excitation Attention (SEAttention), into YOLOv11 improves the mAP50–95 accuracy by 10.1 percentage points. Generative AI processed this information in real time and provided the driver with appropriate driving recommendations, such as gently braking, detecting a pedestrian ahead, or warning of excessive speed. These recommendations are delivered through voice output to prevent driver distraction caused by looking at an interface. When a red light or pedestrian is detected, early deceleration is suggested, effectively reducing fuel consumption while also enhancing driving comfort, ultimately achieving the goal of energy-efficient driving. Full article

Pedestrian accidents involving heavy vehicles such as trucks and buses remain a critical safety issue, primarily due to structural blind spots. While existing systems like radar-based FCW and BSD have been adopted, they are not fully optimized for pedestrian detection, particularly under adverse weather conditions. This study focused on the empirical validation of a 360-degree pedestrian collision avoidance system using multichannel ultrasonic sensors specifically designed for heavy-duty vehicles. Eight sensors were strategically positioned to ensure full spatial coverage, and scenario-based field experiments were conducted under controlled rain (50 mm/h) and fog (visibility <30 m) conditions. Pedestrian detection performance was evaluated across six distance intervals (50–300 cm) using indicators such as mean absolute error (MAE), coefficient of variation (CV), and false-negative rate (FNR). The results demonstrated that the system maintained average accuracy of 97.5% even under adverse weather. Although rain affected near-range detection (FNR up to 17.5% at 100 cm), performance remained robust at mid-to-long ranges. Fog conditions led to lower variance and fewer detection failures. These empirical findings demonstrate the system’s effectiveness and robustness in real-world conditions and emphasize the importance of evaluating both distance accuracy and detection reliability in pedestrian safety applications. Full article

To address the challenges of real-time monitoring via highway vehicle-mounted cameras—specifically, the difficulty in detecting distant pedestrians and vehicles in real time—this study proposes an enhanced object detection algorithm, YOLOv5s-F. Firstly, the FasterNet network structure is adopted to improve the model’s runtime speed. Secondly, the attention mechanism BRA, which is derived from the Transformer algorithm, and a 160 × 160 small-object detection layer are introduced to enhance small target detection performance. Thirdly, the improved upsampling operator CARAFE is incorporated to boost the localization and classification accuracy of small objects. Finally, Focal EIoU is employed as the localization loss function to accelerate model training convergence. Quantitative experiments on high-speed sequences show that Focal EIoU reduces bounding box jitter by 42.9% and improves tracking stability (consecutive frame overlap) by 11.4% compared to CIoU, while accelerating convergence by 17.6%. Results show that compared with the YOLOv5s baseline network, the proposed algorithm reduces computational complexity and parameter count by 10.1% and 24.6%, respectively, while increasing detection speed and accuracy by 15.4% and 2.1%. Transfer learning experiments on the VisDrone2019 and Highway-100k dataset demonstrate that the algorithm outperforms YOLOv5s in average precision across all target categories. On NVIDIA Jetson Xavier NX, YOLOv5s-F achieves 32 FPS after quantization, meeting the real-time requirements of in-vehicle monitoring. The YOLOv5s-F algorithm not only meets the real-time detection and accuracy requirements for small objects but also exhibits strong generalization capabilities. This study clarifies core challenges in highway small-target detection and achieves accuracy–speed improvements via three key innovations, with all experiments being reproducible. If any researchers need the code and dataset of this study, they can consult the author through email. Full article

Simultaneous Localization and Mapping (SLAM) is a fundamental technique in mobile robotics, enabling autonomous navigation and environmental reconstruction. However, dynamic elements in real-world scenes—such as walking pedestrians, moving vehicles, and swinging doors—often degrade SLAM performance by introducing unreliable features that cause localization errors. In this paper, we define dynamic regions as areas in the scene containing moving objects, and dynamic features as the visual features extracted from these regions that may adversely affect localization accuracy. Inspired by biological perception strategies that integrate semantic awareness and geometric cues, we propose Instance-level Point-Line SLAM (IPL-SLAM), a robust visual SLAM framework for dynamic environments. The system employs YOLOv8-based instance segmentation to detect potential dynamic regions and construct semantic priors, while simultaneously extracting point and line features using Oriented FAST (Features from Accelerated Segment Test) and Rotated BRIEF (Binary Robust Independent Elementary Features), collectively known as ORB, and Line Segment Detector (LSD) algorithms. Motion consistency checks and angular deviation analysis are applied to filter dynamic features, and pose optimization is conducted using an adaptive-weight error function. A static semantic point cloud map is further constructed to enhance scene understanding. Experimental results on the TUM RGB-D dataset demonstrate that IPL-SLAM significantly outperforms existing dynamic SLAM systems—including DS-SLAM and ORB-SLAM2—in terms of trajectory accuracy and robustness in complex indoor environments. Full article