基于机器视觉的动态多目标识别

摘要/Abstract

摘要： 提出了一种基于机器视觉的实时动态多目标识别的方法.该方法首先根据前后帧之间像素的变化，分割出运动目标和样本图像，然后使用Gabor滤波器提取图像的特征，得到特征向量.最后使用Fisher判别准则分类识别，将得到的分类识别结果自动标注在输出图像中，并且将其连续输出，便能获得已经识别完成的输出视频.实验结果表明，在多个动态目标的情况下，综合运用Gabor特征与帧间差分法的动态目标识别方法能准确检测到动态目标区域，并能准确分类、识别和标注.

关键词: , 机器视觉, Fisher判别准则, 动态多目标识别, 目标分割

Abstract: This paper proposes a realtime dynamic multitarget recognition method based on machine vision. The method first segments the moving targets according to the pixel change between the front and rear frames, then extracts the features of the segmented moving targets and sample images using Gabor filter to obtain the eigenvector, and finally uses Fisher discriminant criterion for classification and recognition so as to automatically lable the classification and recognition results onto the output images. The images labeled with the recognition results are to be outputted continuously, and hence the output videos which have been recognized can be obtained. The experimental results show that in the circumstance of multiple targets, the proposed dynamic target recognition method integrating Gabor feature and interframe difference can accurately detect the dynamic target area, and realize classification, recognition and labeling.

Key words: machine vision, Fisher discriminant criterion, dynamic multitarget recognition, object segmentation

中图分类号:

TP 391.41

薛梦霞,刘士荣,王坚. 基于机器视觉的动态多目标识别[J]. 上海交通大学学报（自然版）, 2017, 51(6): 727-733.

XUE Mengxia,LIU Shirong,WANG Jian. Dynamic MultiTarget Recognition Based on Machine Vision[J]. Journal of Shanghai Jiaotong University, 2017, 51(6): 727-733.

参考文献

［1］DIAZ R, HALLMAN S, FOWLKERS C C. Detecting dynamic objects with multiview background subtraction［C］∥Proceedings of the IEEE International Conference on Computer Vision. Sydney, Australia: IEEE, 2013: 273280.
［2］MORO A, MUMOLO E, NOLICH M, et al. Realtime background modeling based on classified dynamic objects for human robot application［C］∥Proceedings of the IEEE International Conference on Networked Sensing Systems. Antwerp, Belgium: IEEE, 2012: 17.
［3］LTHOFF H H, WALLRAVEN C, GRAF A. Viewbased dynamic object recognition based on human perception［C］∥Proceedings of the IEEE International Conference on Pattern Recognition. Quebec, Canada: IEEE, 2002: 768776.
［4］邱雪娜, 刘斐, 刘士荣, 等. 基于双目视觉的移动机器人动态目标识别与定位［J］. 华东理工大学学报(自然科学版), 2010, 36(1): 103112.
QIU Xuena, LIU Fei, LIU Shirong, et al. Dynamic object recognition and localization of mobile robot based on binocular vision［J］. Journal of East China University of Science and Technology (Natural Science Edition), 2010, 36(1): 103112.
［5］KUNG C H, KUNG C M, WANG J P. High performance realtime object detecting and tracking system for multiple moving targets［C］∥Proceedings of IEEE Conference on Instrumentation and Measurement Technology. Warsaw, Poland: IEEE, 2007: 14.
［6］CHEN C H, CHENG C, PAGE D, et al. A moving object tracked by a mobile robot with realtime obstacles avoidance capacity［C］∥Proceedings of the IEEE International Conference on Pattern Recognition. Hong Kong: IEEE, 2006: 10911094.
［7］赵英男, 刘正东, 杨静宇. 基于Gabor滤波器和特征加权的红外图像识别［J］. 计算机工程与应用， 2004， 40(32): 2224.
ZHAO Yingnan, LIU Zhengdong, YANG Jinyu. Recognition for infrared images based on Gabor filters and feature weighting［J］. Computer Engineering and Applications, 2004， 40(32): 2224.
［8］马春庭, 郑坚, 陈东根, 等. 地面战场侦查系统多目标识别的评价指标［J］. 探测与控制学报, 2006, 28(1): 610.
MA Chunting, ZHENG Jian, CHEN Donggen, et al. The evaluation guideline of the multitarget recognition model of the battlefield reconnaissance［J］. Journal of Detection & Control, 2006, 28(1): 610.
［9］YANG T L, ZHANG W, ZHAO X F. A solution of rotation invariance based ESPRIT (SRIESPRIT) method approach to directionofarrival estimation［C］∥International Workshop on Microwave and Millimeter Wave Circuits and System Technology. Chengdu, Sichuan: IEEE, 2012: 14.

[1]	孙棪伊, 范文晶, 曾远帆, 干兴业, 汤日佳, 韩锐. 基于Harris角点检测的装填靶标识别方法[J]. 空天防御, 2022, 5(4): 87-91.
[2]	王聚团, 戚晓宁, 黄志明. 水下生产管汇测试技术及其改进研究[J]. 海洋工程装备与技术, 2022, 9(2): 43-49.
[3]	袁振钦, 邹科, 孙亚峰, 刘刚, 屈衍, 李居跃. 基于时域分析法的动态电缆疲劳分析[J]. 海洋工程装备与技术, 2022, 9(2): 50-55.
[4]	王娟, 杨明旺, 郑茂尧, 刘凌云, 赵立君. 高强钢在大型半潜式平台组块建造中的应用[J]. 海洋工程装备与技术, 2022, 9(1): 27-31.
[5]	陈欣, 赵晓磊, 王立坤, 肖德明, 张腾月. 深水大型吸力锚建造技术研究[J]. 海洋工程装备与技术, 2022, 9(1): 32-36.
[6]	尹彦坤, 易涤非. 半潜式生产平台船体结构关键节点工程临界评估[J]. 海洋工程装备与技术, 2022, 9(1): 52-57.
[7]	周俊杰, 余建波. 基于机器视觉的加工刀具磨损量在线测量[J]. 上海交通大学学报, 2021, 55(6): 741-749.
[8]	ZHANG Shengfa (张胜发), TANG Na (唐纳), SHEN Guofeng (沈国峰), WANG Han (王悍), QIAO Shan (乔杉). Universal Software Architecture of Magnetic Resonance-Guided Focused Ultrasound Surgery System and Experimental Study[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(4): 471-481.
[9]	MA Qunsheng (马群圣), CEN Xingxing (岑星星), YUAN Junyi (袁骏毅), HOU Xumin (侯旭敏). Word Embedding Bootstrapped Deep Active Learning Method to Information Extraction on Chinese Electronic Medical Record[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(4): 494-502.
[10]	牛牧, 许黎明, 赵达, 范帆. 基于工件轮廓图像的砂轮磨损在线检测方法[J]. 上海交通大学学报, 2021, 55(3): 221-228.
[11]	安庆升, 孙立东, 武秋生. 碳纤维增强复合材料发射筒设计研究[J]. 空天防御, 2021, 4(2): 13-.
[12]	王旭烽, 汤日佳, 孙棪伊, 干兴业, 张玉鑫. 导弹自动装填技术研究综述[J]. 空天防御, 2021, 4(2): 34-.
[13]	KONG Xiangqiang (孔祥强), MENG Xiangxi (孟祥熙), LI Jianbo (李见波), SHANG Yanping (尚燕平), CUI Fulin (崔福林) . Comparative Study on Two-Stage Absorption Refrigeration Systems with Different Working Pairs[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(2): 155-162.
[14]	ZHUANG Weimin (庄蔚敏), WANG Pengyue (王鹏跃), AO Wenhong (熬文宏), CHEN Gang (陈刚) . Experiment and Simulation of Impact Response of Woven CFRP Laminates with Different Stacking Angles[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(2): 218-230.
[15]	ZHOU Xuhui (周旭辉), ZHANG Wenguang (张文光), XIE Jie (谢颉). Effects of Micro-Milling and Laser Engraving on Processing Quality and Implantation Mechanics of PEG-Dexamethasone Coated Neural Probe[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(1): 1-9.