计算机科学 ›› 2015, Vol. 42 ›› Issue (11): 305-309.doi: 10.11896/j.issn.1002-137X.2015.11.062
李艳萍,林建辉,杨宁学
LI Yan-ping, LIN Jian-hui and YANG Ning-xue
摘要: 针对传统光流跟踪算法计算复杂度高、受噪声影响大的问题,提出了一种基于尺度不变特征变换(Scale Invariant Feature Transform,SIFT)和卡尔曼滤波器的特征点光流跟踪算法。首先,利用SIFT算法提取图像中的特征点;然后,根据最小绝对值误差准则对运动目标的特征点进行匹配,建立卡尔曼滤波器方程来计算特征点光流;最后,通过光流特征聚类实现运动目标的识别与跟踪。实验结果表明,算法对自然场景中的运动目标具有良好的跟踪特性,稳定性好,计算量小,易于实现。
[1] 胡琼,秦磊,黄庆明.基于视觉的人体动作识别综述[J].计算机学报,2013,36(12):2512-2524 Hu Qiong,Qin Lei,Huang Qing-ming.A Survey on Visual Human Action Recognition[J].Chinese Journal of Computers,2013,36(12):2512-2524 [2] Gauglitz S,Hollerer T.Evaluation of interest point detectorsand feature descriptors for visual tracking[J].International Journal of Computer Vision,2011,94(3):335-360 [3] Brown M,Lowe D G.Automatic panoramic image stitching using invariant features[J].International Journal of Computer Vision,2007,74(1):59-73 [4] 杨叶梅.基于改进光流法的运动目标检测[J].计算机与数字工程,2011,39(9):108-110,160 Yang Ye-mei.Moving objects trackong based on improved optical flow method[J].Computer & Digital Engineering,2011,39(9):108-110,160 [5] 袁国武,陈志强,龚健,等.一种结合光流法与三帧差分法的运动目标检测算法[J].小型微型计算机系统,2013,34(3):668-671 Yuan Guo-wu,Chen Zhi-qiang,Gong Jian,et al.A moving object detection algorithm based on a combination of optical flow and three-frame difference[J].Journal of Chinese Computer Systems,2013,34(3):668-671 [6] 吴垠,李良福,肖樟树,等.基于尺度不变特征的光流法目标跟踪技术研究[J].计算机工程与应用,2013,49(15):157-161 Wu Yin,Li Liang-fu,Xiao Zhang-shu,et al.Optical flow motion tracking algorithm based on SIFT feature[J].Computer Engineering and Applications,2013,49(15):157-161 [7] Lowe D G.Object recognition from local scale-invariant features[C]∥Proceeding of the 7th IEEE International Conference on Computer Vision.1999:1150-1157 [8] Lowe D G.Distinctive Image Features From Scale-invariantKeypoints[J].International Journal of Computer Vision,2004,60(2):91-110 [9] 韩烨,刘志刚,韩志伟,等.基于SIFT特征匹配的高速铁路接触网支撑装置耳片断裂检测研究[J].铁道学报,2014,36(2):31-36 Han Ye,Liu Zhi-gang,Han Zhi-wei,et al.Fracture detection of ear pieces of catenary support devices of high-speed railway based on SIFT feature matching[J].Journal of The Chinese Railway Society,2014,36(2):31-36 [10] Mikolajezyk K,Schimid C.A performance evaluation of local descriptors[J].IEEE Trans.Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630 [11] 向友君,雷娜,余卫宇,等.运动估计算法匹配准则研究[J].计算机科学,2009,36(9):278-280 Xiang You-jun,Lei Na,Yu Wei-yu,et al.Research of block matching criterion for motion estimation[J].Computer Science,2009,36(9):278-280 [12] 张秀杰,张建忠,谭云福.自适应Kalman滤波的运动物体跟踪算法研究[J].燕山大学学报,2012,36(5):428-432,4 Zhang Xiu-jie,Zhang Jian-zhong,Tan Yun-fu.Research on algorithm of moving object tracking using adaptive Kalman filter[J].Journal of Yanshan University,2012,36(5):428-432,464 [13] Lean G,Moshe B,Eli S,et al.Actions as Space-Time Shapes.http://www.wisdom.weizmann.ac.il/~vision/SpaceTimeActions.html [14] 杨杨,张田文.一种基于特征光流的运动目标跟踪方法[J].宇航学报,2000,21(2):8-15 Yang Yang,Zhang Tian-wen.Moving target tracking based on feature-optical-flow[J].Journal of Astronautics,2000,21(2):8-15 [15] 王晋疆,刘阳,吴明云.基于快速鲁棒特征的Camshift跟踪算法[J].计算机应用,2013,33(2):499-502 Wang Jin-jiang,Liu Yang,Wu Ming-yun.CamShift tracking algorithm based on speed-up robust features[J].Journal of Computer Applications,2013,33(2):499-502 [16] 汪鑫,刘嘉敏,李敏,等.基于SIFT特征匹配算法的目标跟踪及视频采集与传输研究[J].重庆理工大学学报(自然科学版) ,2014,8(11):89-93 Wang Xin,Liu Jia-min,Li Min,et al.Target Tracking Video Information Acquisition and Transmission Based on SIFT Feature Matching Algorithm[J].Journal of Chongqing University of Technology(Natural Science),2014,8(11):89-93 |
No related articles found! |
|