Smart City Gnosys

Smart city article details

Title Fa-Yolo: A Pedestrian Detection Algorithm With Feature Enhancement And Adaptive Sparse Self-Attention
ID_Doc 25952
Authors Sui H.; Han H.; Cui Y.; Yang M.; Pei B.
Year 2025
Published Electronics (Switzerland), 14, 9
DOI http://dx.doi.org/10.3390/electronics14091713
Abstract Pedestrian detection technology refers to identifying pedestrians within the field of view and is widely used in smart cities, public safety surveillance, and other scenarios. However, in real-world complex scenes, challenges such as high pedestrian density, occlusion, and low lighting conditions lead to blurred image boundaries, which significantly impact accuracy of pedestrian detection. To address these challenges, we propose a novel pedestrian detection algorithm, FA-YOLO. First, to address issues of limited effective information extraction in backbone network and insufficient feature map representation, we propose a feature enhancement module (FEM) that integrates both global and local features of the feature map, thereby enhancing the network’s feature representation capability. Then, to reduce redundant information and improve adaptability to complex scenes, an adaptive sparse self-attention (ASSA) module is designed to suppress noise interactions in irrelevant regions and eliminate feature redundancy across both spatial and channel dimensions. Finally, to further enhance the model’s focus on target features, we propose cross stage partial with adaptive sparse self-attention (C3ASSA), which improves overall detection performance by reinforcing the importance of target features during the final detection stage. Additionally, a scalable intersection over union (SIoU) loss function is introduced to address the vector angle differences between predicted and ground-truth bounding boxes. Extensive experiments on the WiderPerson and RTTS datasets demonstrate that FA-YOLO achieves State-of-the-Art performance, with a precision improvement of 3.5% on the WiderPerson and 3.0% on RTTS compared to YOLOv11. © 2025 by the authors.
Author Keywords adaptive sparse self-attention; feature enhancement module; loss function; pedestrian detection


Similar Articles

Id Similarity Authors Title Published
62125 View0.874Song F.; Li P.Yolov5-Ms: Real-Time Multi-Surveillance Pedestrian Target Detection Model For Smart CitiesBiomimetics, 8, 6 (2023)
44268 View0.871Murthy C.B.; Hashmi M.F.Real Time Pedestrian Detection Using Robust Enhanced Yolov3+Proceedings - 2020 21st International Arab Conference on Information Technology, ACIT 2020 (2020)
62128 View0.871Sivaraman G.; Sophiya E.; Diviya M.Yolov8 For Pedestrian Detection: A Comparative Study For Pedestrian Detection2024 3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024 (2024)
45511 View0.871Zhao R.; Hao J.; Huo H.Research On Multi-Modal Pedestrian Detection And Tracking Algorithm Based On Deep LearningFuture Internet, 16, 6 (2024)
44267 View0.864Murthy C.B.; Farukh Hashmi M.Real Time Pedestrian Detection Using Robust Enhanced Tiny-Yolov32020 IEEE 17th India Council International Conference, INDICON 2020 (2020)
23647 View0.858Bhonde T.; Temare H.; Dadwhal Y.S.Enhanced Object Detection Using Yolov8: Identifying Vehicles And Pedestrians In Urban Environments2024 IEEE Pune Section International Conference, PuneCon 2024 (2024)
14521 View0.858Yuan G.; Ye T.; Fu H.; Wang L.; Wang Z.Clustering Based Detection Of Small Target Pedestrians For Smart CitiesSustainable Energy Technologies and Assessments, 52 (2022)
8535 View0.857Wang F.; Ni W.; Liu S.; Xu Z.; Wan Z.An Intelligent Pedestrian Tracking Algorithm Based On Sparse Models In Urban Road SceneIEEE Transactions on Intelligent Transportation Systems, 25, 3 (2024)
41532 View0.852Zhang J.; Chen X.; Li Y.; Chen T.; Mou L.Pedestrian Detection Algorithm Based On Improved Yolo V32021 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2021 (2021)