基于轻量化YOLOv3的遥感军事目标检测算法

doi:10.3778/j.issn.1002-8331.2106-0026

摘要/Abstract

摘要：

在导弹智能突防的过程中，从海量的遥感图像数据中检测敌方反导阵地具有极大的应用价值。由于弹载部署环境算力有限，设计了一种兼顾轻量化，检测精确率以及检测速度的遥感目标检测算法。制作了典型遥感军事目标数据集，通过K-means算法对数据集聚类分析。利用MobileNetV2网络代替YOLOv3算法的主干网络，保证网络的轻量化和检测速度。提出了适用于遥感目标特性的轻量化高效通道协同注意力模块和目标旋转不变性检测模块，将其嵌入检测算法中，在网络轻量化的基础上提升检测精确率。实验结果表明，提出算法的精确率达到97.8%，提升了6.8个百分点，召回率达到95.7%，提升了3.9个百分点，平均检测精度达到95.2%，提升了4.4个百分点，检测速度达到了每秒34.19张图，而网络大小仅为17.5?MB。结果表明该算法能满足导弹智能突防的综合要求。

关键词: 目标检测, 轻量化网络, YOLOv3, 遥感图像, MobileNetV2

Abstract:

In the process of intelligent missile penetration, detecting enemy anti-missile positions from massive remote sensing image data has great application value. Due to the limited computing power of the missile-borne deployment environment, this paper designs a remote sensing target detection algorithm that takes into account lightweight, detection accuracy and detection speed. A typical remote sensing military target data set is produced, and the data set is clustered and analyzed by the K-means algorithm. The MobileNetV2 network is used to replace the backbone network of the YOLOv3 algorithm to ensure the lightweight and detection speed of the network. A lightweight and efficient channel coordinated attention module and a target rotation invariance detection module suitable for remote sensing target characteristics are proposed, and they are embedded in the detection algorithm to improve the detection accuracy on the basis of network lightweight. Experimental results show that the accuracy rate of the algorithm in this paper reaches 97.8%, an increase of 6.7 percentage points, the recall rate reaches 95.7%, an increase of 3.9 percentage points, the average detection accuracy reaches 95.2%, an increase of 4.4 percentage points, and the detection speed reached 34.19 images per, and the network size is only 17.5?MB. The results show that the algorithm in this paper can meet the comprehensive requirements of intelligent missile penetration.

Key words: target detection, lightweight network, YOLOv3, remote sensing image, MobileNetV2

秦伟伟，宋泰年，刘洁瑜，王洪伟，梁卓. 基于轻量化YOLOv3的遥感军事目标检测算法[J]. 计算机工程与应用, 2021, 57(21): 263-269.

QIN Weiwei, SONG Tainian, LIU Jieyu, WANG Hongwei, LIANG Zhuo. Remote Sensing Military Target Detection Algorithm Based on Lightweight YOLOv3[J]. Computer Engineering and Applications, 2021, 57(21): 263-269.

参考文献

[1] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[J].Computer Science，2013：580-587.
[2] 杜鹏，谌明，苏统华.深度学习与目标检测[M].北京：电子工业出版社，2020：16-31.
DU P，CHEN M，SU T H.Deep learning and object detection[M].Beijing：Publishing House of Electronics Industry，2020：16-31.
[3] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detecto[C]//European Conference on Computer Vision，2016：21-37.
[4] 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.LosAlamitos：IEEE Computer Society Press，2016：779-788.
[5] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[J].arXiv：1612.08242v1，2016.
[6] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767v1，2018.
[7] 董洪义.深度学习之PyTorch物体检测实战[M].北京：机械工业出版社，2020：4-23.
DONG H Y.Object detection by deep learning：core techonologies and practices[M].Beijing：China Machine Press，2020：4-23.
[8] 崔洲涓，安军社，张羽丰，等.面向无人机的轻量级Siamese注意力网络目标跟踪[J].光学学报，2020，40（19）：132-144.
CUI Z J，AN J S，ZHANG Y F，et al.Light-weight Siamese attention network object tracking for unmanned aerial vehicle[J].Acta Optica Sinica，2020，40（19）：132-144.
[9] 任坤，黄泷，范春奇，等.基于多尺度像素特征融合的实时小交通标志检测算法[J].信号处理，2020，36（9）：1457-1463.
REN K，HUANG L，FAN C Q，et al.Real-time small traffic sign detection algorithm based on multi-scale pixel feature fusion[J].Journal of Signal Processing，2020，36（9）：1457-1463.
[10] 马立，巩笑天，欧阳航空.Tiny YOLOV3目标检测改进[J].光学精密工程，2020，28（4）：988-995.
MA L，GONG X T，OUYANG H K.Improvement of tiny YOLOV3 target detection[J].Optics and Precision Engineering，2020，28（4）：988-995.
[11] 宋艳艳，谭励，马子豪，等.改进YOLOV3算法的视频目标检测[J].计算机科学与探索，2021，15（1）：163-172.
SONG Y Y，TAN L，MA Z H，et al.Video target detection based on improved YOLOV3 algorithm[J].Journal of Frontiers of Computer Science and Technology，2021，15（1）：163-172.
[12] SANDLER M，HOWARD A，ZHU M L，et al.MobileNetV2：inverted residuals and linear bottlenecks[J].arXiv：1801.04381v4，2018.
[13] 黄健，张钢.深度卷积神经网络的目标检测算法综述[J].计算机工程与应用，2020，56（17）：12-23.
HUANG J，ZHANG G.Survey of object detection algorithms for deep convolutional neural networks[J].Computer Engineering and Applications，2020，56（17）：12-23.
[14] SZEGEDY C，LIU W，JIA Y，et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2015：1-9.
[15] HAN J，DING J，XUE N，et al.ReDet：a rotation-equivariant detector for aerial object detection[J].arXiv：2103.07733v1，2021.
[16] HU J，SHEN L，SUN G，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2019，42（8）：367-375.
[17] WOO S，PARK J，LEE J，et al.CBAM：convolutional block attention module[C]//European Conference on Computer Vision，2018：3-19.
[18] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[J].arXiv：2103.02907v1，2021.