[1]侯毅苇,李林汉,王彦.结合红外显著性目标导引的改进YOLO网络的智能装备目标识别研究[J].红外技术,2020,42(7):644-650.[doi:10.11846/j.issn.1001_8891.202007007]
 HOU Yiwei,LI Linhan,WANG Yan.Intelligent Equipment Object Recognition Based on Improved YOLO Network Guided by Infrared Saliency Detection[J].Infrared Technology,2020,42(7):644-650.[doi:10.11846/j.issn.1001_8891.202007007]
点击复制

结合红外显著性目标导引的改进YOLO网络的智能装备目标识别研究

分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
42卷
期数:
2020年第7期
页码:
644-650
栏目:
出版日期:
2020-07-23

文章信息/Info

Title:
Intelligent Equipment Object Recognition Based on Improved YOLO Network Guided by Infrared Saliency Detection

文章编号:
1001-8891(2020)07-0644-07
作者:
侯毅苇12李林汉2王彦3
1. 河北金融学院, 大数据科学学院;
2. 河北金融学院, 金融创新与风险管理研究中心;
3. 中国电子科技集团公司第五十四所 信息传输与分发技术重点实验室

Author(s):
HOU Yiwei12LI Linhan2WANG Yan3
1. School of Big Data Science, Hebei Finance University;
2. Financial innovation and Risk Management Research Center, Hebei Finance University;
3. Key Laboratory of Information Transmission and Distribution Technology, The 54th Research Institute of CETC
关键词:
目标识别红外显著性目标导引深度学习YOLO-V3智能装备
Keywords:
object recognition infrared saliency object guidance deep learning YOLO-V3 intelligent equipment
分类号:
TN219
DOI:
10.11846/j.issn.1001_8891.202007007
文献标志码:
A
摘要:
为了提升实际作战环境下目标检测识别的性能,本文提出了一种基于红外显著性目标导引的改进YOLO(You Only Look Once)网络的智能装备目标识别算法,该算法利用红外图像提供目标可能的位置引导可见光图像中的深度自主学习,提升检测与识别的实时性。改进YOLO-V3识别网络是以Darknet-53为基础网络架构,利用Dense Net代替具有较低分辨率的原始转移层,同时采用分类网络预训练、多尺度检测网络训练等措施增强特征传播,复用和融合的性能。仿真实验结果表明,本文提出的模型可以有效地提高现有目标检测与识别的性能。
Abstract:
To improve the performance of object detection and recognition in a real-world combat environment, an improved intelligent object recognition algorithm based on infrared saliency object guidance is proposed. It uses the object information in an infrared image to guide deep self-learning in vision images. The improved YOLO-V3 recognition network is based on the Darknet-53 network architecture, using DenseNet instead of the original transfer layer with lower resolution. Classification network pretraining, multiscale detection network training, and other measures are used to enhance feature propagatio n and reuse and fusion performance. Simulation results show that the proposed model can effectively improve the performance of existing object detection and recognition networks.

参考文献/References:

[1] 张鑫, 李续武, 路艳丽. 双向S-优势粗集及其在意图识别中的应用[J]. 弹箭与制导学报, 2017, 37(3): 160-164.
ZHANG Xin, LI Xuwu, LU Yanli. Two-direction S-dominance Rough Sets and Its Application in Intention Recognition[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2017, 37(3): 160-164.
[2] 陈文英, 张兵志, 史力晨, 等. 新型智能装甲作战系统体系贡献率评估研究[J]. 兵工学报, 2018, 39(9): 1841-1849.?
CHEN Wenying, ZHANG Bingzhi, SHI Lichen, et al. Research on Evaluation of Contribution Rate of a New Intelligent Armoured Combat System to Army Weapon System-of-systems[J]. Acta Armamentarii, 2018, 39(9): 1841-1849.
[3] 刘从军, 嵇金荣, 杨辉. 智能监控中实时预警系统[J]. 计算机系统应用, 2014, 23(6):65-68.
LIU Congjun, JIN Jinrong, YANG Hui. Real-time Early Warning System in Intelligent Monitoring[J]. Computer Systems, 2014, 23(6): 65-68.
[4] 文雄志, 陈学工, 王晶, 等. 基于红外图像的桥梁目标自动识别方法[J]. 计算机与现代化, 2015(5): 62-66.
WEN Xiongzhi, CHEN Xuegong, WANG Jing, et al. Automatic Recognition Method of Bridge Target Based on Infrared Image[J]. Computer and Modernization, 2015(5): 62-66.
[5] YAO X, HAN J, GUO L, et al. A coarse-to-fine model for airport detection from remote sensing images using target-oriented visual saliency and CRF[J]. Neuro computing, 2015, 164: 162-172.
[6] Ross Girshick, Jeff Donahue, Trevor Darrell, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE? Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[7] HE K, ZHANG X, REN S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 37(9): 1904-16.
[8] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision, 2015: 1440-1448.
[9] REN S, HE K, 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, 2015, 39(6): 1137-1148.
[10] Redmon J,? Divvala S,? Girshick R, et al. You Only Look Once: Unified, Real-Time Object Detection[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 779-788.
[11] LIU W,? Anguelov D,? Erhan D, et al. SSD: Single Shot MultiBox Detector[J]. European Conference on Computer Vision, 2015: 21-37.
[12] Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6517-6525.
[13] Redmon J, Farhadi A. YOLOV3: An incremental improvement[R/OL]. arXiv preprint arXiv: 1804.02767, 2018.
[14] 黄伟, 曹宇剑, 徐国明. 基于Faster R-CNN模型的低空平台偏振高光谱目标检测[J]. 红外技术, 2019, 41(7): 600-606.?
HUANG Wei, CAO Yujian, XU Guoming. Polarized Hyperspectral Object Detection with Faster R-CNN for Low-Altitude Platforms[J]. Infrared Technology, 2019, 41(7): 600-606.
[15] Aguilar W G, Luna M A, Moya J F, et al. Pedestrian detection for UAVs using cascade classifiers with meanshift[C]//2017 IEEE 11th international conference on semantic computing (ICSC), 2017: 509-514.
[16] HUANG G, LIU Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition. 2017: 4700-4708.
[17] WU, Fei, Wang, ZHANG Zhongfei,et.al. Weakly Semi-Supervised Deep Learning for Multi-Label Image Annotation[J]. IEEE Transactions on Big Data, 1(3):109-122.
[18] CAI Z, Vasconcelos N. Cascade r-cnn: Delving into high quality object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition, 2018: 6154-6162.
[19] Singh B, Li H, Sharma A, et al. R-FCN-3000 at 30fps: Decoupling Detection and Classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1081-1090.
[20] HU H, GU J, ZHANG Z, et al. Relation networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 3588-3597.

相似文献/References:

[1]王世亮,杨帆,张志伟,等.基于目标红外特征与SIFT特征相结合的目标识别算法[J].红外技术,2012,34(09):503.
 WANG Shi-liang,YANG Fan,ZHANG Zhi-wei,et al.A Target Recognition Method Based on Infrared Features and SIFT[J].Infrared Technology,2012,34(7):503.
[2]李雪,陈勇,贾明永.多元红外双色导引头目标识别技术研究[J].红外技术,2013,35(06):373.
 LI Xue,CHEN Yong,JIA Ming-yong.The Target Recognition Technology for Multi-Element Dual-Band IR Seeker[J].Infrared Technology,2013,35(7):373.
[3]江友谊,余瑞星,宋军艳.基于ICM的局部不变特征提取方法[J].红外技术,2012,34(03):177.
 JIANG You-yi,YU Rui-xing,SONG Jun-yan.A Novel Method based on ICM for Local Invariant Feature Extraction[J].Infrared Technology,2012,34(7):177.
[4]杨永生,王民钢,侯美婵.基于SIFT特征匹配的地面背景下目标识别方法[J].红外技术,2010,32(12):713.
 YANG Yong-sheng,WANG Min-gang,HOU Mei-chan.Ground Target Recognition Method Based on SIFT[J].Infrared Technology,2010,32(7):713.
[5]张翔.基于光谱特征增强的高光谱图像地物目标识别[J].红外技术,2010,32(12):717.
 Target Recognition of Hyperspectral Image Based?on Enhanced Spectral Characteristics[J].Infrared Technology,2010,32(7):717.
[6]郑坤鹏,王普凯,周国印,等.基于MATLAB的红外图像中坦克特征量的提取方法[J].红外技术,2010,32(11):625.
 ZHENG Kun-peng,ZHOU Guo-yin,WANG Pu-kai,et al.The Extracting Method of Tank FeatureVector from Infrared Images Based on MATLAB[J].Infrared Technology,2010,32(7):625.
[7]王会鹏,王明忠,邱康.一种烟幕遮障下的伪装目标协同识别方法[J].红外技术,2014,36(5):404.[doi:10.11846/j.issn.1001_8891.201405013]
 WANG Hui-peng,WANG Ming-zhong,QIU Kang.A Cooperative Recognition method for the Smokescreen-cover Camouflage Target[J].Infrared Technology,2014,36(7):404.[doi:10.11846/j.issn.1001_8891.201405013]
[8]项建胜,孟卫华,潘国庆.一种红外多光谱成像光学系统设计[J].红外技术,2009,31(12):683.
 XIANG Jian-sheng,MENG Wei-hua,PAN Guo-qing.A Multi-spectral Infrared Optical System[J].Infrared Technology,2009,31(7):683.
[9]李林,张河.引信用声红外复合探测识别系统研究[J].红外技术,2008,30(四):205.
 LI Lin,ZHANG He.Study on the Sound-infrared Compound Detection and Identification System for Fuze[J].Infrared Technology,2008,30(7):205.
[10]赵芹,周涛,舒勤.飞机红外图像的目标识别及姿态判断[J].红外技术,2007,29(3):167.
 ZHAO Qin,ZHOU Tao,SHU Qin.Recognition and Pose Estimation of Airplane’s Infrared Image[J].Infrared Technology,2007,29(7):167.

备注/Memo

备注/Memo:
收稿日期:2019-09-08;修订日期:2020-07-06.
作者简介:侯毅苇(1980-),女,汉族,山东菏泽人,硕士,讲师,研究方向:计算数学、图像处理、智能计算应用、模式识别等。E-mail: hyiwei1983@126.com。
基金项目:河北省自然科学基金青年科学基金(A2015410006);2018年度河北省科学技术厅软科学研究专项项目(18454227);河北金融学院应用数学优秀基础学科基金项目(20190235A)。

更新日期/Last Update: 2020-07-16