Unmanned Aerial Vehicles (UAV) have been widely used in various fields, and object detection has become one of the key technologies in the field of UAV vision. Considering the problems of complex scenes, variable scales and too many small targets in UAV images, an adaptive aerial object detection algorithm is proposed based on multi-scale convolution. Firstly, the multi-scale feature extraction network is constructed, and the multi-scale convolution method is introduced. Different types of convolution are used to check different sizes of targets to expand the receptive field effectively. Secondly, the convolution module is designed according to the advantages of attention mechanism, and the feature weight is adaptively optimized to obtain more representational features. Finally, a prediction network is constructed based on multi-scale feature fusion. According to the characteristics of small targets, multi-level feature maps are selected to fuse into high-resolution feature maps, and object classification and boundary box regression are carried out on a single scale. Experimental results show that the proposed algorithm improves the object detection accuracy of UAV aerial images, and has good robustness.
[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):524519. 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):524519(in Chinese).
[2] 刘芳, 杨安喆, 吴志威. 基于自适应Siamese网络的无人机目标跟踪算法[J]. 航空学报, 2020, 41(1):323423. LIU F, YANG A Z, WU Z W. Adaptive Siamese network based UAV target tracking algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(1):323423(in Chinese).
[3] 徐斌, 黎宁, 朱含杉, 等. 无人机平台下的行人目标检测[J]. 计算机与数字工程, 2019, 47(8):1935-1940. XU B, LI N, ZHU H S, et al. Pedestrian detection under micro UAV[J]. Computer & Digital Engineering, 2019, 47(8):1935-1940(in Chinese).
[4] 曹之君, 张良. 基于Faster-RCNN的快速目标检测算法[J]. 航天控制, 2020, 38(4):49-55. CAO Z J, ZHANG L. Fast object detection algorithm based on faster-RCNN[J]. Aerospace Control, 2020, 38(4):49-55(in Chinese).
[5] 陈丁, 吉哲. 基于改进Faster R-CNN的无人机航拍图像目标检测[J]. 海洋测绘, 2019, 39(5):51-55. CHEN D, JI Z. Object detection in UAV aerial images based on improved faster R-CNN[J]. Hydrographic Surveying and Charting, 2019, 39(5):51-55(in Chinese).
[6] 赵爽, 黄怀玉, 胡一鸣, 等. 基于深度学习的无人机航拍车辆检测[J]. 计算机应用, 2019, 39(S2):91-96. ZHAO S, HUANG H Y, HU Y M, et al. Vehicle detection in satellite imagery based on deep learning[J]. Journal of Computer Applications, 2019, 39(S2):91-96(in Chinese).
[7] WOO S, PARK J, LEE J Y, et al. CBAM:Convolutional block attention module[C]//In Proceedings of the European Conference on Computer Vision (ECCV), 2018:3-19.
[8] 黄梓桐, 阿里甫·库尔班. 无人机平台下的行人与车辆目标实时检测[J]. 计算机工程与应用, 2021, 57(17):169-174. HUANG Z T, ALIFU K. Real-time pedestrian and vehicle detection based on UAV[J]. Computer Engineering and Applications, 2021, 57(17):169-174(in Chinese).
[9] 刘芳, 吴志威, 杨安喆, 等. 基于多尺度特征融合的自适应无人机目标检测[J]. 光学学报, 2020, 40(10):1015002. LIU F, WU Z W, YANG A Z, et al. Multi-scale feature fusion based adaptive object detection for UAV[J]. Acta Optica Sinica, 2020, 40(10):1015002(in Chinese).
[10] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2015:1-9.
[11] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet:A new backbone that can enhance learning capability of CNN[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway:IEEE Press, 2020:1571-1580.
[12] ZHANG S, HE G H, CHEN H B, et al. Scale adaptive proposal network for object detection in remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(6):864-868.
[13] XIE X M, YANG W Z, CAO G M, et al. Real-time vehicle detection from UAV imagery[C]//2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM). Piscataway:IEEE Press, 2018:1-5.
[14] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[DB/OL]. arXiv preprint:1409.1556, 2014.
[15] 吕铄, 蔡烜, 冯瑞. 基于改进损失函数的YOLOv3网络[J]. 计算机系统应用, 2019, 28(2):1-7. LYU S, CAI X, FENG R. YOLOv3 network based on improved loss function[J]. Computer Systems & Applications, 2019, 28(2):1-7(in Chinese).
[16] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2017:2999-3007.
[17] 梁栋, 高赛, 孙涵, 等. 结合核相关滤波器和深度学习的运动相机中无人机目标检测[J]. 航空学报, 2020, 41(9):323733. LIANG D, GAO S, SUN H, et al. UAV detection in motion cameras combining kernelized correlation filters and deep learning[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(9):323733(in Chinese).
[18] ZHU P F, WEN L Y, BIAN X, et al. Vision meets drones:A challenge[DB/OL]. arXiv preprint:1804.07437, 2018.
[19] LIN T Y, MAIRE M, BELONGIE S J, et al. Microsoft COCO:Common objects in context[C]//Proceedings of 2014 European Conference on Computer Vision (ECCV), 2014:740-755.
[20] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[21] REDMON J, FARHADI A. YOLO9000:Better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2017:6517-6525.
[22] LAW H, DENG J. CornerNet:Detecting objects as paired keypoints[J]. International Journal of Computer Vision, 2020, 128(3):642-656.
[23] ZHOU X Y, WANG D Q, KRÄHENBVHL P. Objects as points[DB/OL]. arXiv preprint:1904.07850, 2019.
[24] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4:Optimal speed and accuracy of object detection[DB/OL]. arXiv preprint:2004.10934, 2020.
CJA