移动视点下在线视频的动态阴影检测与跟踪

doi:10.16182/j.issn1004731x.joss.18-VR0714

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (7): 1439-1447.doi: 10.16182/j.issn1004731x.joss.18-VR0714

移动视点下在线视频的动态阴影检测与跟踪

张友鹏¹, 王淳², 刘艳丽²

1. 四川大学视觉合成图形图像国防重点实验室,四川成都 610065;
2. 四川大学计算机学院,四川成都 610065

收稿日期:2018-06-30 修回日期:2018-10-25 发布日期:2019-12-12
作者简介:张友鹏(1993-),男,河南信阳,硕士生,研究方向为图像处理和计算机视觉; 王淳(1995-),男,山东烟台,硕士生,研究方向为图像处理和计算机视觉。
基金资助:
国家自然科学基金(61572333), 国家“863”计划(2015AA016405)

Dynamic Shadow Detection and Tracking of Online Video from Mobile View

Zhang Youpeng¹, Wang Chun², Liu Yanli²

1. National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China;
2. College of Computer Science, Sichuan University, Chengdu 610065, China

Received:2018-06-30 Revised:2018-10-25 Published:2019-12-12

摘要/Abstract

摘要： 提出了一种基于光流跟踪的室外场景下的阴影边缘检测与跟踪框架。利用从已知结果中提取的边缘信息特征训练SVM,对前后两帧进行光流跟踪,利用SVM模型从不稳定跟踪点的邻域Canny置信边缘中识别符合阴影特征的点。针对视点移动带来的场景新材质问题,设计了动态更新SVM的方法。阴影投射区域的复杂性可能使得SVM失效,针对这种问题,使用了区域对比算法来提高结果的准确性。实验结果表明,算法可以准确的检测和跟踪移动视点下视频中移动物体如运动人体的投射阴影。

关键词: 阴影检测, 移动视点, 特征匹配, 区域对

Abstract: A shadow edge detection and tracking framework based on optical flow tracking in outdoor scenes is proposed. The SVM is trained by using the edge information features extracted from the known results; the optical flow tracking is performed on the two frames before and after; and the SVM model is used to identify the points corresponding to the shadow features from the neighborhood Canny confidence edges of the unstable tracking points. A method for dynamically updating the SVM is designed for the new material problem of the scene caused by the viewpoint movement. The complexity of the shadow projection area may invalidate the SVM. For this problem, a region comparison algorithm is used to improve the accuracy of the results. The experimental results show that the algorithm can accurately detect and track the projected shadows of moving objects such as moving humans in the video under the mobile view.

Key words: shadow detection, mobile view, feature matching, pair-wise region

中图分类号:

TP391

张友鹏, 王淳, 刘艳丽. 移动视点下在线视频的动态阴影检测与跟踪[J]. 系统仿真学报, 2019, 31(7): 1439-1447.

Zhang Youpeng, Wang Chun, Liu Yanli. Dynamic Shadow Detection and Tracking of Online Video from Mobile View[J]. Journal of System Simulation, 2019, 31(7): 1439-1447.

参考文献

[1] Zhu J, Samuel K, Masood S, et al.Learning to Recognize Shadows in Monochromatic Natural Images[C]. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2010.
[2] Dong Q, Liu Y, Zhao Q, et al.Detecting Soft Shadows in a Single Outdoor Image: From Local Edge-Based Models to Global Constraints[J]. Computers & Graphics (S0097-8493), 2014, 38: 310-319.
[3] Daniilidis K, Maragos P, Paragios N.Computer Vision-ECCV 2010[M]. Berlin, Heidelberg: Springer- Verlag Berlin Heidelberg, 2010: 322-335.
[4] Xiang Huang, Gang Hua, Tumblin J, et al.What Characterizes a Shadow Boundary Under The Sun and Sky?[C]. 2011 International Conference on Computer Vision. 2011.
[5] Guo R, Dai Q, Hoiem D.Single-Image Shadow Detection and Removal Using Paired Regions[C]. CVPR 2011.
[6] Amato A, Mozerov M, Bagdanov A, et al.Accurate Moving Cast Shadow Suppression Based on Local Color Constancy Detection[J]. IEEE Transactions on Image Processing (S1057-7149), 2011, 20(10): 2954-2966.
[7] Russell A, Zou J.Moving Shadow Detection Based on Spatial-Temporal Constancy[C]. 2013, 7^th International Conference on Signal Processing and Communication Systems (ICSPCS). IEEE,2013.
[8] Cuchiara R, Grana C, Piccardi M, et al.Detecting Moving Obects, Ghosts, and Shadows in Video Streams[J]. IEEE Tranactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2003, 25(10): 1337-1342.
[9] Yang M, Lo K, Chiang C, et al.Moving Cast Shadow Detection By Exploiting Multiple Cues[J]. IET Image Process (S1751-9659), 2008, 2(2): 95.
[10] Russell M, Fang G, Zou J.Real-Time Vehicle Shadow Detection[J]. Electronics Letters (S0013-5194), 2015, 51(16): 1253-1255.
[11] Khare M, Srivastava R, Khare A.Moving Shadow Detection and Removal-A Wavelet Transform Based Approach[J]. IET Computer Vision (S1751-9632), 2014, 8(6): 701-717.
[12] Gunnar Farneback.Two-Frame Motion Estimation Based on Polynomial Expansion[C]. Lecture Notes in Computer Science, 2003(2749): 363-370.
[13] Canny J.A Computational Approach to Edge Detection[J]. IEEE Trans. Pattern Analysis and Machine Intelligence (S0162-8828), 1986, 13(8): 679-714.
[14] Moeslund T B, Hilton A, Krüger V, et al.Visual Analysis of Humans[M]. Berlin, Germany: Springer-Verlag, 2011.
[15] Sanin A, Sanderson C, Lovell B C.Improved Shadow Removal for Robust Person Tracking in Surveillance Scenarios[C]. Proceedings of the 20th International Conference on Pattern Recognition. Washington D C. USA: IEEE Press, 2010: 141-144.
[16] Yin Baocai, Liu Yu, Wang Zengfu.Moving shadow detection combined with color and texture invariance[J]. Journal of Image and Graphics (S1006-8961), 2014, 45(19): 1593-1598.
[17] Tian Jiandong, Sun Jing, Tang Yandong.Tricolor Attenuation Model for Shadow Detection[J]. IEEE Transactions on Image Processing (S1057-7149), 2009, 18(10): 2355-2363.
[18] Lalonde J F, Efros A A, Narasimhan S G.Estimating the Natural Illumination Conditions from a Single Outdoor Image[J]. International Journal of Computer Vision (S0920-5691), 2012, 98(2): 123-145.
[19] Kalal Z, Mikolajczyk K, Matas J.Tracking-Learning- Detection[J]. IEEE Transactions on Software Engineering (S0098-5589), 2011, 34(7): 1409-1422.
[20] Choi J M, Yoo Y J, Choi J Y.Adaptive shadow estimator for removing shadow of moving object[J]. Computer Vision and Image Understanding (S1077-3142), 2010, 114(9): 1017-1029.
[21] Guo R, Dai Q, Hoiem D.Paired Regions for Shadow Detection and Removal[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence (S0162-8828), 2013, 35(12): 2956-2967.
[22] Tian J, Qi X, Qu L, et al.New spectrum ratio properties and features for shadow detection[J]. Pattern Recognition (S0031-3203), 2016, 51(C): 85-96.

移动视点下在线视频的动态阴影检测与跟踪

Dynamic Shadow Detection and Tracking of Online Video from Mobile View

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	杨敬辉, 刘德康, 杜万和, 邢立宁. 基于图像特征的双目测距系统的研究[J]. 系统仿真学报, 2022, 34(3): 624-632.
[2]	蔡鹏, 沈朝萍, 李红燕. 基于标定区域特征点组合匹配的位姿估计方法[J]. 系统仿真学报, 2021, 33(7): 1638-1646.
[3]	孙晶晶, 于佳骏, 李贝, 谢志峰, 丁友东. 基于人像字典集的卡通自动生成方法[J]. 系统仿真学报, 2015, 27(4): 682-688.