LI Yang, WU Lianquan, YANG Haitao, NIU Jinlin, CHU Xianteng, WANG Huapeng, ZOU Qinglong. A Small Target Detection Algorithm from UAV Perspective[J]. Infrared Technology , 2023, 45(9): 925-931.
Citation: LI Yang, WU Lianquan, YANG Haitao, NIU Jinlin, CHU Xianteng, WANG Huapeng, ZOU Qinglong. A Small Target Detection Algorithm from UAV Perspective[J]. Infrared Technology , 2023, 45(9): 925-931.

A Small Target Detection Algorithm from UAV Perspective

More Information
  • Received Date: July 01, 2022
  • Revised Date: January 17, 2023
  • The use of unmanned aerial vehicles (UAVs) for effective real-time monitoring of small targets, such as people, cars, and objects in the scene area, can help maintain public security. To address the problems of small-target occlusion, overlapping, and interference of complex environments in UAV images, a small-target detection algorithm is proposed from the UAV perspective. The algorithm uses the YOLOX network as the baseline system. First, the neck part of the network increases the output feature graph to reduce the receptive field, thereby improving the performance of the network details, and the detection head of the small-sized feature graph is deleted to improve the detection rate of small targets. Second, the anchor-free association mechanism is used to reduce the influence of noise in the truth tag while simultaneously reducing the parameter setting to speed up network operations. Finally, a true proportion coefficient is proposed for small targets to calculate position loss, thereby increasing the penalty for misjudging small targets, which makes the network more sensitive to small targets. Experiments on the VisDrone2021 dataset using this algorithm showed that the mAP value increased by 4.56%; the number of parameters decreased by 29.4%; the amount of computation decreased by 32.5%; and the detection speed increased by 19.7% compared with those of the baseline system, which is an advantage over other mainstream algorithms.
  • [1]
    武连全, 邹清龙. 警用无人机执法应用现状、问题与对策[J]. 北京警察学院学报, 2021(4): 36-43. DOI: 10.16478/j.cnki.jbjpc.20210507.002.

    WU L Q, ZOU Q L. Application status, problems and countermeasures of police UAV In law enforcement[J]. Journal of Beijing Police College, 2021(4): 36-43. DOI: 10.16478/j.cnki.jbjpc.20210507.002.
    [2]
    TONG K, WU Y, ZHOU F. Recent advances in small object detection based on deep learning: a review[J]. Image and Vision Computing, 2020, 97: 103910. DOI: 10.1016/j.imavis.2020.103910
    [3]
    Kisantal M, Wojna Z, Murawski J, et al. Augmentation for small object detection[J/OL]. arXiv preprint arXiv: 1902.07296, 2019. http://export.arxiv.org/abs/1902.07296.
    [4]
    Nguyen N D, Do T, Ngo T D, et al. An evaluation of deep learning methods for small object detection[J]. Journal of Electrical and Computer Engineering, 2020, 2020: 1-18.
    [5]
    Bharati P, Pramanik A. Deep learning techniques—R-CNN to mask R-CNN: a survey[J]. Computational Intelligence in Pattern Recognition, 2019, 999: 657-668.
    [6]
    CHEN C, LIU M Y, Tuzel O, et al. R-CNN for small object detection[C]//Asian Conference on Computer Vision, 2016: 214-230.
    [7]
    Keles M C, Salmanoglu B, Guzel M S, et al. Evaluation of YOLO models with sliced inference for small object detection[J/OL]. arXiv preprint arXiv: 2203.04799, 2022. https://arxiv.org/abs/2203.04799.
    [8]
    Ziming C, HAN Y, Lingjun K, et al. Multi-scene small object detection with modified YOLOv4[C]//Journal of Physics: Conference Series, 2022, 2253(1): 012027.
    [9]
    奉志强, 谢志军, 包正伟, 等. 基于改进YOLOv5的无人机实时密集小目标检测算法[J/OL]. 航空学报: 1-15. [2022-07-01]. http://kns.cnki.net/kcms/detail/11.1929.V.20220509.2316.010.html.

    FENG Z Q, XIE Z J, BAO Z W, et al. Real-time dense small object detection algorithm for UAV based on improved YOLOv5[J/OL]. Acta Aeronautica et Astronautica Snica: 1-15. [2022-07-01]. http://kns.cnki.net/kcms/detail/11.1929.V.20220509.2316.010.html
    [10]
    Akyon F C, Onur Altinuc S, Temizel A. Slicing aided hyper inference and fine-tuning for small object detection[C]// IEEE International Conference on Image Processing (ICIP), 2022: 966-970, Doi: 10.1109/ICIP46576.2022.9897990.
    [11]
    GE Z, LIU S, WANG F, et al. YOLOX: Exceeding YOLO series in 2021[J/OL]. arXiv preprint arXiv: 2107.08430, 2021. https://doi.org/10.48550/arXiv.2107.08430
    [12]
    武连全, 楚宪腾, 杨海涛, 等. 基于改进YOLOX的X射线违禁物品检测[J]. 红外技术, 2023, 45(4): 427-435. http://hwjs.nvir.cn/article/id/7e45bcc9-aca9-49c9-8f88-0d8c22e5c7de

    WU L Q, CHU X T, YANG H T, et al. X-ray detection of prohibited items based on improved YOLOX[J]. Infrared Technology, 2023, 45(4): 427-435. http://hwjs.nvir.cn/article/id/7e45bcc9-aca9-49c9-8f88-0d8c22e5c7de
    [13]
    JIANG P, Ergu D, LIU F, et al. A Review of YOLO algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066-1073. DOI: 10.1016/j.procs.2022.01.135
    [14]
    WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: A new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 390-391.
    [15]
    ZHU P, WEN L, DU D, et al. Detection and tracking meet drones challenge[J/OL]. arXiv preprint arXiv: 2001.06303, 2020. https://doi.org/10.48550/arXiv.2001.06303
    [16]
    WAN J, ZHANG B, ZHAO Y, et al. Vistrongerdet: stronger visual information for object detection in VisDrone images[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 2820-2829.
    [17]
    ZHU X, LYU S, WANG X, et al. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 2778-2788.
    [18]
    Sineglazov V, Kalmykov V. Image processing from unmanned aerial vehicle using modified YOLO detector[J]. Electronics and Control Systems, 2021, 3(69): 37-42. DOI: 10.18372/1990-5548.69.16425
  • Related Articles

    [1]XU Haiyang, ZHAO Wei, LIU Jianye. Infrared and Visible Image Registration Algorithm Based on Edge Structure Features[J]. Infrared Technology , 2023, 45(8): 858-862.
    [2]LI Bicao, LU Jiaxi, LIU Zhoufeng, LI Chunlei, ZHANG Jie. Infrared and Visible Light Image Fusion Method Based on Swin Transformer and Hybrid Feature Aggregation[J]. Infrared Technology , 2023, 45(7): 721-731.
    [3]WANG Xiangjun, DU Zhiwei, GAO Chao. Small Scale Fire Identification Based on Constrained Inhomogeneous Deformation Feature[J]. Infrared Technology , 2021, 43(2): 145-152.
    [4]LI Ruidong, SUN Xiechang, LI Meng. Infrared Feature Extraction and Recognition Technology of Space Target[J]. Infrared Technology , 2017, 39(5): 427-435.
    [5]ZHANG Chen, ZHAO Hong-ying, QIAN Xu. Research on Object Feature Tracking Method Oriented to UAV Images[J]. Infrared Technology , 2015, (3): 224-228,239.
    [6]ZHAO De-li, ZHU You-pan, WU Cheng, LI Ze-min, ZENG Bang-ze, LUO Lin, YANG Peng-wei, WANG Bing, LI Yan. Investigation on Improved Infrared Image Registration Algorithm Based on Point Feature and Gray Feature[J]. Infrared Technology , 2014, (10): 820-826.
    [7]Study on Image Registration Method Based on Region Feature[J]. Infrared Technology , 2010, 32(3): 145-147,151. DOI: 10.3969/j.issn.1001-8891.2010.03.006
    [8]CHEN Ya-bing, WANG Yong-zhong, WANG Yan-hua. IR Feature Extraction Based on Imbalance Fisher Discrimination[J]. Infrared Technology , 2008, 30(7): 395-398. DOI: 10.3969/j.issn.1001-8891.2008.07.007
    [9]LUO Xiao-an, CAI Chao, ZHOU Cheng-ping, DING Ming-yue, ZHANG Yi-guang, ZHANG Tian-xu. A New Fast Algorithm for Contour Descriptor[J]. Infrared Technology , 2006, 28(8): 446-452. DOI: 10.3969/j.issn.1001-8891.2006.08.004
    [10]ZHAO Qin, ZHOU Tao, SHU Qin. Discussion of Image Registration Based on Feature Points[J]. Infrared Technology , 2006, 28(6): 327-330. DOI: 10.3969/j.issn.1001-8891.2006.06.005

Catalog

    Article views PDF downloads Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return