基于YOLO v5算法的迷彩伪装目标检测技术研究

doi:10.11896/jsjkx.210100058

计算机科学 ›› 2021, Vol. 48 ›› Issue (10): 226-232.doi: 10.11896/jsjkx.210100058

• 计算机图形学&多媒体 • 上一篇下一篇

基于YOLO v5算法的迷彩伪装目标检测技术研究

王杨¹, 曹铁勇¹, 杨吉斌¹, 郑云飞^1,2,3, 方正¹, 邓小桐¹, 吴经纬¹, 林嘉⁴

1 陆军工程大学指挥控制工程学院南京210007
2 陆军炮兵防空兵学院南京211100
3 安徽省偏振成像与探测重点实验室合肥230031
4 山东省军区数据信息室济南250000

收稿日期:2021-01-20 修回日期:2021-05-08 出版日期:2021-10-15 发布日期:2021-10-18
通讯作者: 曹铁勇(cty_ice@sina.com)
作者简介:wangy621@yeah.net
基金资助:
国家自然科学基金青年科学基金(61801512);国家自然科学基金(62071484);江苏省优秀青年基金项目(BK20180080)

Camouflaged Object Detection Based on Improved YOLO v5 Algorithm

WANG Yang¹, CAO Tie-yong¹, YANG Ji-bin¹, ZHENG Yun-fei^1,2,3, FANG Zheng¹, DENG Xiao-tong¹, WU Jing-wei¹, LIN Jia⁴

1 Insitute of Command and Control Engineering,Army Engineering University of PLA,Nanjing 210007,China
2 The Army Artillery and Defense Academy of PLA,Nanjing 211100,China
3 The Key Laboratory of Polarization Imaging Detection Technology,Hefei 230031,China
4 Shandong Military Region,Ji'nan 250000,China

Received:2021-01-20 Revised:2021-05-08 Online:2021-10-15 Published:2021-10-18
About author:WANG Yang,born in 1996,postgra-duate.His main research interests include object detection and image processing.
CAO Tie-yong,born in 1970,Ph.D,professor,Ph.D supervisor.His main research interests include computer vision and image processing.
Supported by:
National Science Fund for Distinguished Young Scholars of China(61801512),National Natural Science Foundation of China(62071484) and Natural Science Foundation of Jiangsu Province(BK20180080).

摘要/Abstract

摘要： 迷彩伪装目标与周围环境高度相似,对迷彩伪装目标的检测任务比普通的检测任务更具挑战性,常规的检测算法对迷彩伪装目标检测任务不完全适用。文中对现有方法进行分析,以YOLO v5算法为基础,提出了一种针对迷彩伪装目标的检测算法。该算法结合注意力机制设计了新的特征提取网络,突出了迷彩伪装目标的特征信息;并且对原有的聚合网络进行了改进,增大了检测的尺度,使用非对称卷积模块强化了目标语义信息。在一种公开的迷彩伪装目标数据集上将该算法与7种算法进行对比,所提算法的mAP值较原始算法提升了 4.4%,召回率提升了2.8%,在mAP值方面也比其他算法更具优势,从而验证了所提算法对迷彩伪装目标检测任务的有效性。

关键词: YOLO, 聚合网络, 迷彩伪装目标, 目标检测, 注意力机制

Abstract: Since the camouflage object is highly similar to the surrounding environment with a rather small size,the general detection algorithm is not fully applicable to the camouflaged object detection task,which makes the detection of camouflaged object more challenging than the general detection task.In order to solve this problem,the existing methods are analyzed in this paper and a detection algorithm for camouflage object is proposed based on the YOLO v5 algorithm.A new feature extraction network combined with attention mechanism is designed to highlight the feature information of the camouflage target.The original path aggregation network is improved so that the high,middle and lowly level feature map information is fully fused.The semantic information of the target is strengthened by nonlinear pool module,and the detection feature map size is increased to improve the detection recall rate of the small size target.On a public camouflage target dataset,the proposed algorithm is tested with 7 algorithms.The mAP of the proposed algorithm is 4.4% higher than that of the original algorithm,while the recall rate has improved 2.8%,which verifies the effectiveness of the algorithm for camouflaged object detection and the great advantage in accuracy compared with other algorithms.

Key words: Aggregation network, Attention mechanism, Camouflaged object, Object detection, YOLO

中图分类号:

TP751

王杨, 曹铁勇, 杨吉斌, 郑云飞, 方正, 邓小桐, 吴经纬, 林嘉. 基于YOLO v5算法的迷彩伪装目标检测技术研究[J]. 计算机科学, 2021, 48(10): 226-232. https://doi.org/10.11896/jsjkx.210100058

WANG Yang, CAO Tie-yong, YANG Ji-bin, ZHENG Yun-fei, FANG Zheng, DENG Xiao-tong, WU Jing-wei, LIN Jia. Camouflaged Object Detection Based on Improved YOLO v5 Algorithm[J]. Computer Science, 2021, 48(10): 226-232. https://doi.org/10.11896/jsjkx.210100058

参考文献

[1]BHAJANTRI N U,NAGABHUSHAN P.CAmouflage DefectIdentification:A Novel Approach[C]//9th International Confe-rence on Information Technology.Bhubaneswar:IEEE Press,2007:145-148.
[2]TANKUS A,YESHURUN Y.Convexity-Based Visual Camouflage Breaking[J].Computer Vision and Image Understanding,2001,82(3):208-237.
[3]SENGOTTUVELAN P,WAHI A,SHANMUGAM A.Performanceof Decamouflaging Through Exploratory Image Analysis[C]//2008 First International Conference on EmergingTrends in Engineering & Technology.Nagpur:IEEE Press,2008:6-10.
[4]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 & Machine Intelligence,2017,39(6):1137-1149.
[5]CAIZ W,VASCONCELOS N.Cascade R-CNN:Delving intoHigh Quality Object De-tection[C]//2018 IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.Salt Lake:IEEE Press,2018:6154-6162.
[6]PANG M J,CHEN K,SHI J P,et al.Libra R-CNN:Towards Balanced Learning for Object Detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE Press,2019:821-830.
[7]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot MultiBox Detector[C]//2016 European Conference on Compu-ter Vision.Amsterdam:Springer,Cham,2016:21-37.
[8]REDMON J,FARHADI A.YOLO9000:Better,Faster,Stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:6517-6525.
[9]XU S K,NI C H,JI C C,et al.Image Caption of Safety Helmets Wearing in Construction Scene Based on YOLOv3[J].Computer Science,2020,47(8):233-240.
[10]LIN S Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection[J].IEEE Trans-actions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
[11]TIAN Z,SHEN C H,CHEN H,et al.FCOS:Fully Convolutio-nal One-Stage Object Detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul:IEEE Press,2019:9626-9635.
[12]YANG Z,LIU S H,HU H,et al.RepPoints:Point Set Representation for Object Detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul:IEEE Press,2019:9656-9665.
[13]ZHOU X Y,WANG D Q,KRÄHENBÜHL P.Object as Points [EL/OB].https://arxiv.org/pdf/1903.07850.
[14]HU J,SHEN L,ALBANIE S,et al.Squeeze-and-Excitation Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023.
[15]MISRA D,NALAMADA T,ARASANIPALAI A U,et al.Rotate to Attend:Convolutional Triplet Attention Module [EL/OB].https://arxiv.org/pdf/2010.03045.
[16]WANG C Y,LIAO H Y,WUY 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).Seattle:IEEE Press,2020:1571-1580.
[17]LIU S,QI L,QIN H F,et al.Path Aggregation Network for Instance Segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake:IEEE Press,2018:8759-8768.
[18]ZHENG Y F,ZHANG X W,WANG F,et al.Detection of People with Camouflage Pattern Via Dense Deconvolution Network[J].IEEE Signal Processing Letters,2019,26(1):29-33.
[19]CHEN K,WANG J Q,PANG J M,et al.MMDetection:Open MMLab Detection Tool-box and Benchmark [EL/OB].https://arxiv.org/pdf/1906.07155.

相关文章 15

[1]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[3]	戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[4]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[5]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[6]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[7]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[8]	刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉. 基于边框距离度量的增量目标检测方法 Incremental Object Detection Method Based on Border Distance Measurement 计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132
[9]	王灿, 刘永坚, 解庆, 马艳春. 基于软标签和样本权重优化的Anchor Free目标检测算法 Anchor Free Object Detection Algorithm Based on Soft Label and Sample Weight Optimization 计算机科学, 2022, 49(8): 157-164. https://doi.org/10.11896/jsjkx.210600240
[10]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[11]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[12]	汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[13]	金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[14]	熊罗庚, 郑尚, 邹海涛, 于化龙, 高尚. 融合双向门控循环单元和注意力机制的软件自承认技术债识别方法 Software Self-admitted Technical Debt Identification with Bidirectional Gate Recurrent Unit and Attention Mechanism 计算机科学, 2022, 49(7): 212-219. https://doi.org/10.11896/jsjkx.210500075
[15]	彭双, 伍江江, 陈浩, 杜春, 李军. 基于注意力神经网络的对地观测卫星星上自主任务规划方法 Satellite Onboard Observation Task Planning Based on Attention Neural Network 计算机科学, 2022, 49(7): 242-247. https://doi.org/10.11896/jsjkx.210500093

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于YOLO v5算法的迷彩伪装目标检测技术研究

Camouflaged Object Detection Based on Improved YOLO v5 Algorithm

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0