激光与光电子学进展, 2015, 52 (9): 091501, 网络出版: 2015-08-28   

强视差下的移动相机运动目标检测 下载: 715次

Moving Target Detection on Moving Camera with the Presence of Strong Parallax
作者单位
南京理工大学电子工程与光电技术学院, 江苏 南京 210094
摘要
为了降低强视差下移动相机运动目标检测的虚警率,提出了一种基于深度约束方程的运动目标检测方法。重点研究了二维图像坐标系到三维世界坐标系之间的关系,并根据图像深度信息和摄影几何原理,结合前后两帧图像和相机内部参数,提出了深度约束方程。深度约束方程包含了图像灰度信息和深度信息,利用深度约束方程可以有效地去除因相机移动产生的视差对目标检测的影响。利用该方法对实际的图像序列进行了分析与处理,并与相关算法进行了对比分析,实验结果表明该方法能够消除移动相机下由于视差造成的虚警,提高移动平台运动目标检测的准确性。
Abstract
In order to reduce the strong parallax false alarm rate of the moving target detection on a moving camera, a moving target detection method based on depth constraint equation is proposed. The relationship between twodimensional image coordinate and three-dimensional world coordinate is mainly studied. According to the image depth information and photography geometry theory, with the two frames image coordinates and the camera internal parameters, the depth constraint equation is established. The depth constraint equation includes gray value and depth information of image. Using the depth constraint equation to detect moving target can effective avoid the influence caused by moving camera. Experiments are performed based on actual image sequence, and related algorithm is compared and analyzed. Experimental results indicate that the proposed method can avoid the parallax false alarm and improve the precision of moving target detection on a moving camera is improved.
参考文献

[1] Zhang Y, Kiselewich S J, Bauson W A, et al.. Robust moving object detection at distance in the visible spectrum and beyond using a moving camera[C]. Computer Vision and Pattern Recognition Workshop, 2006, 1(1): 131-139.

[2] Kim W J, Kweon I S. Moving object detection and tracking from moving camera[C]. IEEE 2011 8th International Conference, 2011, 1(1): 758-759.

[3] Yu Q, Medioni G. Motion pattern interpretation and detection for tracking moving vehicles in airborne video[C]. IEEE Computer Vision and Pattern Recognition, 2009, 1(1): 2671-2678.

[4] Cheraghi S A, Sheikh U U. Moving object detection using image registration for a moving camera platform[C]. IEEE International Conference, 2012, 1(1): 355-359.

[5] Shen H, Li S, Zhu C, et al.. Moving object detection in aerial video based on spatiotemporal saliency[J]. Chinese Journal of Aeronautics, 2013, 26(5): 1211-1217.

[6] Salvador E, Cavallaro A, Ebrahimi T. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004, 95(2): 238-259.

[7] Zhou X, Yang C, Yu W. Moving object detection by detecting contiguous outliers in the low- rank representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(3): 597-610.

[8] Dey S, Reilly V, Saleemi I, et al.. Detection of Independently Moving Objects in Non- Planar Scenes via Multi- Frame Monocular Epipolar Constraint[M]. Heidelberg: Springer, 2012: 860-873.

[9] 何亮明, 覃荣华, 巩思亮, 等. 动态场景中的改进混合高斯背景模型[J]. 计算机工程, 2012, 38(8): 10-15.

    He Liangming, Tan Ronghua, Gong Siliang, et al.. Improved Gaussian mixture background model in dynamic scene[J]. Computer Engineering, 2012, 38(8): 10-15.

[10] Reilly V, Idrees H, Shah M. Detection and Tracking of Large Number of Targets in Wide Area Surveillance[M]. Heidelberg: Springer, 2010: 186-199.

[11] Vavilin A, Jo K H. Moving object detection and camera motion analysis from moving camera[C]. Annual Conference on IEEE Industrial Electronics Society, 2012, 1(1): 4171-4176.

[12] Chwa D, Dani A, Kim H, et al.. Camera motion estimation for 3-D structure reconstruction of moving objects[C]. 2012 IEEE International Conference, 2012, 1(1): 1788-1793.

[13] Hartley R, Zisserman A. Multiple View Geometry in Computer Vision[M]. Cambridge: Cambridge University Press, 2003.

[14] A Goldstein, R Fattal. Video stabilization using epipolar geometry[J]. ACM Transactions on Graphics. 2012, 31(5): 126.

[15] Newcombe R A, Davison A J. Live dense reconstruction with a single moving camera[C]. Computer Vision and Pattern Recognition, Conference on IEEE, 2010: 1498-1505.

[16] 郭黎, 廖宇, 陈为龙. 基于改进SIFT 的视频超分辨率重建快速配准算法研究[J]. 湖北民族学院学报, 2010, 28(2): 177-180.

    Guo Li, Liao Yu, Chen Weilong. An improved registration algorithm on video super resolution reconstruction[J]. Journal of Hubei University for Nationalities, 2010, 28(2): 177-180.

[17] Zhang Z. A flexible new technique for camera calibration[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2000, 22(11): 1330-1334.

[18] Harris C, Stephens M. A combined corner and edge detector[C]. Alvey Vision Conference, 1988, 15: 50.

[19] Derpanis K G. The harris corner detector[J]. York University, 2004.

[20] Orguner U, Gustafsson F. Statistical characteristics of harris corner detector[C]. Proceedings of IEEE/SP 14th Workshop on Statistical Signal Processing, 2007: 26-29.

[21] Kalal Z, Mikolajczyk K, Matas J. Forward- backward error: Automatic detection of tracking failures[C]. IEEE International Conference, 2010, 1(1): 2756-2759.

[22] Shi J, Tomasi C. Good features to track[C]. Computer Vision and Pattern Recognition, 1994 1(1): 593-600.

[23] 陈海欣, 顾国华, 钱惟贤, 等. 一种运动相机强视差下运动目标检测方法[J]. 中国激光, 2014, 41(5): 0509002.

    Chen Haixin, Gu Guohua, Qian Weixian, et al.. A method for moving target detection on a moving camera in the presence of a strong parallax[J]. Chinese J Lasers, 2014, 41(5): 0509002.

[24] Moisan L, Stival B. A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix[J]. International Journal of Computer Vision, 2004, 57(3): 201-218.

[25] Valgaerts L, Bruhn A, Mainberger M, et al.. Dense versus sparse approaches for estimating the fundamental matrix[J]. International Journal of Computer Vision, 2012, 96(2): 212-234.

[26] Eshel R, Moses Y. Homography based multiple camera detection and tracking of people in a dense crowd[C]. Computer Vision and Pattern Recognition, IEEE Conference on, 2008: 1-8.

[27] Nascimento J C, Marques J S. Performance evaluation of object detection algorithms for video surveillance[J]. IEEE Transactions on Multimedia, 2006, 8(4): 761-774.

丁祺, 顾国华, 徐富元, 任侃, 钱惟贤, 陈钱. 强视差下的移动相机运动目标检测[J]. 激光与光电子学进展, 2015, 52(9): 091501. Ding Qi, Gu Guohua, Xu Fuyuan, Ren Kan, Qian Weixian, Chen Qian. Moving Target Detection on Moving Camera with the Presence of Strong Parallax[J]. Laser & Optoelectronics Progress, 2015, 52(9): 091501.

本文已被 7 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!