|
|
论文:2023,Vol:41,Issue(6):1179-1189 |
|
|
引用本文： |
|
|
高武奇, 杨婷, 李亮亮. 基于多特征交叉融合及跨层级联的航拍目标检测算法[J]. 西北工业大学学报 |
|
|
GAO Wuqi, YANG Ting, LI Liangliang. Aerial military target detection algorithm based on multi-feature cross fusion and cross-layer concatenation[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 基于多特征交叉融合及跨层级联的航拍目标检测算法 |
|
| 高武奇1, 杨婷2, 李亮亮3 |
|
1. 西安工业大学 计算机科学与工程学院, 陕西 西安 710021;
2. 西安工业大学 兵器科学与技术学院, 陕西 西安 710021;
3. 西安工业大学 机电工程学院, 陕西 西安 710021 |
| 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。 |
| 关键词:
航拍图像
目标检测
YOLOv5
融合注意力机制
多尺度特征金字塔
|
|
| Aerial military target detection algorithm based on multi-feature cross fusion and cross-layer concatenation |
|
| GAO Wuqi1, YANG Ting2, LI Liangliang3 |
|
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 |
| 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. |
| Key words:
aerial image
target detection
YOLOv5
fusion attention mechanism
multiscale characteristic pyramid
|
|
| 收稿日期: 2022-10-20
修回日期:
|
| DOI: 10.1051/jnwpu/20234161179 |
| 基金项目: 国家自然科学基金(62171360)与陕西省研究生教育教学综合改革项目(YJSYG2020073)资助 |
| 通讯作者:
Email： |
| 作者简介: 高武奇(1975-),西安工业大学副教授,主要从事图像处理及机器学习研究。e-mail:gaowuqi@xatu.edu.cn
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 高武奇 在本刊中的所有文章 |
| 杨婷 在本刊中的所有文章 |
| 李亮亮 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] HUI Pengyifan. Battlefield image situational awareness application based on deep learning[J]. IEEE Intelligent Systems, 2020, 35(1): 36-43
[2] 戴文君, 常天庆, 褚凯轩, 等. 基于时空卷积特征记忆模型的坦克火控系统视频目标检测方法[J]. 兵工学报, 2020, 41(9): 1708-1718 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)
[3] 张奔, 徐锋, 李晓婷, 等. 针对军事集群目标的YOLOv3改进算法研究[J]. 火力与指挥控制, 2021, 46(5): 81-85 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)
[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
[5] 汪烈兵, 姜雄飞, 石春光, 等. 基于图像滤波与Hough变换的红外弱小目标检测[J]. 红外技术, 2020, 42(7):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)
[6] 曾接贤, 王军婷, 符祥. K均值聚类分割的多特征图像检索方法[J]. 计算机工程与应用, 2013, 49(2): 226-230 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)
[7] 郝帅, 程咏梅, 马旭, 等. 无人直升机视觉着舰中合作目标角点检测算法[J]. 西北工业大学学报, 2013, 31(4): 653-659 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 (in Chinese)
[8] 王永学, 王双进. 基于蚁群优化与神经网络的坦克目标识别算法[J]. 物理实验, 2010, 30(5): 8-11 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)
[9] 段仲静, 李少波, 胡建军, 等. 深度学习目标检测方法及其主流框架综述[J]. 激光与光电子学进展, 2020, 57(12): 59-74 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)
[10] 戴文君, 常天庆, 张雷, 等. 图像目标检测技术在坦克火控系统中的应用[J]. 火力与指挥控制, 2020, 45(7): 147-152 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)
[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
[12] 刘芳, 韩笑. 基于多尺度深度学习的自适应航拍目标检测[J]. 航空学报, 2022, 43(5): 325270 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)
[13] 张瑞倩, 邵振峰, ALEKSEI Portnov, 等. 多尺度空洞卷积的无人机影像目标检测方法[J]. 武汉大学学报(信息科学版), 2020, 45(6): 108-116 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)
[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
[15] 王靖宇, 王霰禹, 张科, 等. 基于深度神经网络的低空弱小无人机目标检测研究[J]. 西北工业大学学报, 2018, 36(2): 258-263 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 (in Chinese)
[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
[17] 王全东, 常天庆, 张雷, 等. 面向多尺度坦克装甲车辆目标检测的改进Faster R-CNN算法[J]. 计算机辅助设计与图形学学报, 2018(12): 2278-2291 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)
[18] 陈科名. 基于SSD的多尺度目标检测算法研究[D]. 北京:北京交通大学, 2020: 61-62 CHEN Keming. Research on multi-scale target detection algorithm based on SSD[D]. Beijing: Beijing Jiaotong University, 2020: 61-62 (in Chinese)
[19] 舒朗, 张智杰, 雷波. 一种针对红外目标检测的Dense-Yolov5算法研究[J]. 光学与光电技术, 2021, 19(1): 69-75 SHU Lang, ZHANG Zhijie, LEI Bo. Research on Dense-Yolov5 algorithm for infrared target detection[J]. Optics and Optoelectronic Technology, 201,19(1): 69-75 (in Chinese) |
|
|
|
|
|
|
|
