基于上下文信息与特征细化的无人机小目标检测算法

doi:10.3778/j.issn.1002-8331.2305-0401

摘要/Abstract

摘要： 无人机航拍图像中的目标检测是近年来研究的热点，针对无人机视角下目标小而密集、背景复杂导致检测精度低的问题，提出一种基于上下文信息与特征细化的无人机小目标检测算法。通过上下文特征增强模块，利用多尺度扩张卷积捕获与周围区域像素点的潜在关系，为网络补充上下文信息，并根据不同尺度的特征层自适应生成各层级特征图的输出权重，动态优化特征图表达能力；由于不同特征图细粒度不同，使用特征细化模块来抑制特征融合中冲突信息的干扰，防止小目标特征淹没在冲突信息中；设计了一种带权重的损失函数，加快模型收敛速度，进一步提高小目标检测精度。在VisDrone2021数据集进行大量实验表明，改进后的模型较基准模型mAP50提高8.4个百分点，mAP50：95提高5.9个百分点，FPS为42，有效提高了无人机航拍图像中小目标的检测精度。

关键词: 无人机, 小目标检测, 上下文信息, 特征细化, 损失函数

Abstract: Object detection in UAV aerial images is a research hotspot in recent years, aiming at the problem of low detection accuracy caused by small and dense objects and complex background from the perspective of UAV, a UAV small object detection algorithm based on context information and feature refinement is proposed. Firstly, through the context feature enhancement module, the multi-scale dilated convolution is used to capture the potential relationship with the pixels in the surrounding area, which complements the context information of the network. According to the feature layers of different scales, the output weights of each level of feature maps are adaptively generated, and the expression ability of the feature map is dynamically optimized. Secondly, due to different fineness of different feature maps, the feature refinement module is used to suppress the interference of conflict information in feature fusion to prevent the small object features from drowning in conflict information. Finally, a weighted loss function is designed to accelerate the convergence speed of the model and further improve the accuracy of small object detection. Extensive experiments on the VisDrone2021 dataset show that the improved model improves 8.4 percentage points over the benchmark model mAP50, 5.9 percentage points over mAP50：95, and the FPS is 42, which effectively improves the detection accuracy of small objects in UAV aerial images.

Key words: unmanned aerial vehicle (UAV), small object detection, context information, feature refinement, loss function

彭晏飞, 赵涛, 陈炎康, 袁晓龙. 基于上下文信息与特征细化的无人机小目标检测算法[J]. 计算机工程与应用, 2024, 60(5): 183-190.

PENG Yanfei, ZHAO Tao, CHEN Yankang, YUAN Xiaolong. UAV Small Object Detection Algorithm Based on Context Information and Feature Refinement[J]. Computer Engineering and Applications, 2024, 60(5): 183-190.

参考文献

[1] 江波, 屈若锟, 李彦冬, 等. 基于深度学习的无人机航拍目标检测研究综述[J]. 航空学报 , 2021, 42(4): 137-151.
JIANG B, QU R K, LI Y D, et al. Object detection in UAV imagery based on deep learning: review[J]. Acta Aeronautica ET Astronautica Sinica, 2021, 42(4): 137-151.
[2] 朱学岩, 张新伟, 顾梦梦, 等. 基于无人机可见光图像的云杉计数方法[J]. 林业工程学报, 2021, 6(4): 140-146.
ZHU X Y, ZHANG X W, GU M M, et al. Spruce counting method based on UAV visible images[J]. Journal of Forestry Engineering, 2021, 6(4): 140-146.
[3] 张艳, 张明路, 吕晓玲, 等. 深度学习小目标检测算法研究综述[J]. 计算机工程与应用, 2022, 58(15): 1-17.
ZHANG Y, ZHANG M L, LYU X L, et al. Review of research on small target detection based on deep learning[J]. Computer Engineering and Applications, 2022, 58(15): 1-17.
[4] 张静, 农昌瑞, 杨智勇. 基于卷积神经网络的目标检测算法综述[J]. 兵器装备工程学报, 2022, 43(6): 37-47.
ZHANG J, NONG C R, YANG Z Y. Review of object detection algorithms based on convolutional neural network[J]. Journal of Ordnance Equipment Engineering, 2022, 43(6): 37-47.
[5] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[6] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2017: 1137-1149.
[7] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision Amsterdam, October 11-14, 2016: 21-37.
[8] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[9] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6517-6525.
[10] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767,2018.
[11] BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.
10934,2020.
[12] 宋谱怡, 陈红, 苟浩波. 改进YOLOv5s的无人机目标检测算法[J]. 计算机工程与应用, 2023, 59(1): 108-116.
SONG P Y, CHEN H, GOU H B. Improving UAV object detection algorithm for YOLOv5s[J]. Computer Engineering and Applications, 2023, 59(1): 108-116.
[13] 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.
[14] 贾天豪, 彭力, 戴菲菲. 引入残差学习与多尺度特征增强的目标检测器[J]. 计算机科学与探索, 2023, 17(5): 1102-1111.
JIA T H, PENG L, DAI F F. Object detector with residual learning and multi-scale feature enhancement[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(5): 1102-1111.
[15] 邓姗姗, 黄慧, 马燕. 基于改进Faster R-CNN的小目标检测算法[J]. 计算机工程与科学, 2023, 45(5): 869-877.
DENG S S, HUANG H, MA Y. ?A small object detection algorithm?based on improved Faster R-CNN[J]. Computer Enginee-
ring & Science, 2023, 45(5): 869-877.
[16] 李晨, 张辉, 张邹铨, 等. 融合多尺度特征与全局上下文信息的X光违禁物品检测[J]. 中国图象图形学报, 2022, 27(10): 3043-3057.
LI C, ZHANG H, ZHANG Z Q, et al. 2022. Integrated multi-scale features and global context in X-ray detection for prohibited items[J]. Journal of Image and Graphics, 2022, 27(10): 3043-3057.
[17] NIE J, PANG Y, ZHAO S, et al. Efficient selective context network for accurate object detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(9): 3456-3468.
[18] 徐坚, 谢正光, 李洪均. 特征平衡的无人机航拍图像目标检测算法[J]. 计算机工程与应用, 2023, 59(6): 196-203.
XU J, XIE Z G, LI H J. Feature-balanced UAV aerial image target detection algorithm[J]. Computer Engineering and Applications, 2023, 59(6): 196-203.
[19] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 936-944.
[20] ZHENG Z, WANG P, REN D, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J]. IEEE Transactions on Cybernetics, 2021, 52(8): 8574-8586.
[21] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[22] ZHU P, WEN L, DU D, et al. Detection and tracking meet drones challenge[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44(11): 7380-7399.
[23] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[24] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[25] RUKHOVICH D. Iterdet: iterative scheme for object detection in crowded environments[C]//Joint IAPR International Workshops on Structural, Syntactic, and Statistical Pattern Recognition, Padua, January 21-22, 2021: 344-354.
[26] YANG T, ZHANG Z Y, JUN Z, et al. Low-altitude small-sized object detection using lightweight feature-enhanced convolutional neural network[J]. Journal of Systems Engineering and Electronics, 2021, 32(4): 841-853.
[27] SUNKARA R, LUO T. No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects[C]//European Conference on Machine Learning and Knowledge Discovery in Databases, 2023: 443-459.