Aerial military target detection algorithm based on multi-feature cross fusion and cross-layer concatenation

基于多特征交叉融合及跨层级联的航拍目标检测算法

¹ School of Computer Science and Engineering, Xi'an University of Technology, Xi'an 710021, China
² School of Weapon Science and Technology, Xi'an University of Technology, Xi'an 710021, China
³ School of Mechanical and Electrical Engineering, Xi'an University of Technology, Xi'an 710021, China

Received: 20 October 2022

Abstract

The precise detection of military targets under complex conditions is a key factor to enhance the ability of war situation generation and prediction. The current technology can not overcome the problems of smoke and occlusion interference, target height change, and different scales in aerial video. In this paper, a multi feature cross fusion and cross layer cascade aerial military target detection algorithm (YOLOv5-MFLC) is proposed. Firstly, aiming at the high confidentiality of the military targets and the shortage of battlefield aerial image resources, a real scene based aerial military target dataset is constructed, and the methods of random splicing and random extraction embedding are used for data enhancement in order to improve the diversity and generalization of targets. Secondly, aiming at the problem of complex background interference, a multi feature cross fusion attention mechanism is constructed to enhance the available information of target features. Finally, for the multi-scale problem of targets in aerial images, a cross layer cascaded multi-scale feature fusion pyramid is designed to improve the detection accuracy of cross scale targets. The experimental results show that, comparing with the existing advanced detection models, the detection accuracy of the algorithm in this paper has been greatly improved. The average accuracy of the algorithm can reach 81.0%, which is 5.2% higher than the original network. In particular, it has reached 55.9% in the smaller target category "person", which is 9.4% higher. And the experimental results further show the usefulness of the improved algorithm for small target detection. At the same time, the detection rate of this algorithm can reach 56 frame/s, which can effectively achieve accurate and fast detection of battlefield targets, and has certain experience value for guiding complex modern wars.

摘要

复杂条件下特殊目标的精确检测是增强特定场景态势生成和预测能力的关键因素。目前的技术不能克服航拍视频中出现的烟雾和遮挡干扰、目标高度变化、尺度不一等问题。因此, 提出一个多特征交叉融合及跨层级联的航拍特殊目标检测算法(YOLOv5-MFLC)。针对实际特殊目标保密性高、航拍图像资源匮乏的问题, 构建了一个基于真实场景的航拍特殊目标数据集, 并采用随机拼接和随机提取嵌入的方法进行数据增强以提高目标多样性和泛化性; 针对复杂背景干扰问题, 构建了多特征交叉融合注意力机制, 增强了目标特征的可用信息; 针对航拍图像中目标多尺度问题, 设计了跨层级联多尺度特征融合金字塔, 提高了跨尺度目标的检测准确率。实验结果表明, 与现有的先进检测模型相比, 所提算法的检测准确率有较大提升, 算法平均准确率可达到81.0%, 相比于原始网络提升了5.2%, 特别是, 在更小的目标类别"person"中达到了55.9%, 提升了9.4%, 进一步表明了所提改进算法对小目标检测的有用性。同时, 所提算法的检测速率可以达56 frame/s, 能够有效地实现实际复杂场景特殊目标的准确、快速检测, 对特殊目标的识别具有一定的指导意义。

1. HUI Pengyifan. Battlefield image situational awareness application based on deep learning[J]. IEEE Intelligent Systems, 2020, 35(1): 36–43. [Article] [Google Scholar]
2. DAI Wenjun, CHANG Tianqing, CHU Kaixuan, et al. Video target detection method for Tank fire control system based on spatio-temporal convolution feature memory model[J]. Acta Armamentarii, 2020, 41(9): 1708–1718 (in Chinese) [Google Scholar]
3. ZHANG Ben, XU Feng, LI Xiaoting, et al. Research on improved YOLOv3 algorithm for military cluster target[J]. Fire Control & Command Control, 2021, 46(5): 81–85 (in Chinese) [Google Scholar]
4. GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision & Pattern Recognition, 2014: 580–587 [Google Scholar]
5. WANG Liebing, JIANG Xiongfei, SHI Chunguang, et al. Infrared dim small target detection based on image filtering and Hough transform[J]. Infrared Technology, 2020, 42(7): 5 (in Chinese) [Google Scholar]
6. ZENG Jiexian, WANG Junting, FU Xiang. Multi-feature image retrieval method based on K-means clustering segmentation[J]. Computer Engineering and Applications, 2013, 49(2): 226–230 (in Chinese) [Google Scholar]
7. HAO Shuai, CHENG Yongmei, MA Xu, et al. Corner detection algorithm for cooperative target with visual landing of unmanned helicopter[J]. Journal of Northwestern Polytechnical University, 2013, 31(4): 653–659. [Article] (in Chinese) [Google Scholar]
8. WANG Yongxue, WANG Shuangjin. Tank target recognition algorithm based on ant colony optimization and neural network[J]. Physical Experiment, 2010, 30(5): 8–11 (in Chinese) [Google Scholar]
9. DUAN Zhongjing, LI Shaobo, HU Jianjun, et al. Review of deep learning based object detection methods and their mainstream frameworks[J]. Laser & Optoelectronics Progress, 2020, 57(12): 59–74 (in Chinese) [Google Scholar]
10. DAI Wenjun, CHANG Tianqing, ZHANG Lei, et al. Application of image target detection technology in tank fire control system[J]. Fire Control & Command Control, 2020, 45(7): 147–152 (in Chinese) [Google Scholar]
11. GONG Y, YU X, DING Y, et al. Effective fusion factor in FPN for tiny object detection[C]//IEEE Winter Conference on Applications of Computer Vision, 2021: 1159–1167 [Google Scholar]
12. LIU Fang, HAN Xiao. Adaptive aerial object detection based on multi-scale deep learning[J]. Acta Aeronauticaet Astronautica Sinica, 2022, 43(5): 325270 (in Chinese) [Google Scholar]
13. ZHANG Ruiqian, SHAO Zhrngfeng, ALEKSEI Portnov, et al. Multi-scale cavity convolution for UAV image target detection[J]. Geomatics and Information Science of Wuhan University, 2020, 45(6): 108–116 (in Chinese) [Google Scholar]
14. YANG X, SUN H, SUN X, et al. Position detection and direction prediction for arbitrary-oriented ships via multitask rotation region convolutional neural network[J]. IEEE Access, 2018, 6: 50839–50849. [Article] [NASA ADS] [CrossRef] [Google Scholar]
15. WANG Jingyu, WANG Xianyu, ZHANG Ke, et al. Research on low altitude dim small UAV target detection based on deep neural network[J]. Journal of Northwestern Polytechnical University, 2018, 36(2): 258–263. [Article] (in Chinese) [CrossRef] [EDP Sciences] [Google Scholar]
16. NEAGOE V E, CARATA S V, CIOTEC A D. An advanced neural network-based approach for military ground vehicle recognition in SAR aerial imagery[J]. International Scientific Committee, 2016, 18: 41–48 [Google Scholar]
17. WANG Quandong, CHANG Tianqing, ZHANG Lei, et al. Improved Faster R-CNN algorithm for multi-scale tank and armored vehicle target detection[J]. Journal of Computer Aided Design and Graphics, 2018, 30(12): 2278–2291 (in Chinese) [CrossRef] [Google Scholar]
18. CHEN Keming. Research on multi-scale target detection algorithm based on SSD[D]. Beijing: Beijing Jiaotong University, 2020: 61–62 (in Chinese) [Google Scholar]
19. SHU Lang, ZHANG Zhijie, LEI Bo. Research on Dense-Yolov5 algorithm for infrared target detection[J]. Optics and Optoelectronic Technology, 2021, 19(1): 69–75 (in Chinese) [Google Scholar]