基于子块运动补偿的运动目标检测

doi:10.3969/j.issn.0372-2112.2017.01.024

摘要/Abstract

摘要：

鱼眼相机成像视角大，获得信息丰富，在车载应用中具有广阔应用前景.本文提出了一种适用于移动单目鱼眼相机的运动目标检测方法.首先，提出一种子块运动补偿模型补偿图像背景运动，解决了现有运动补偿模型对强视差背景补偿效果不好的问题.其次，在子块运动补偿模型参数求解时，通过引入自车运动参数简化模型参数个数，并结合直接方法求解，避免了传统基于特征点匹配方法求解参数时易受误匹配特征点影响的问题.然后，针对鱼眼相机的成像形变问题，本文提出了一种三平面校正方法获取鱼眼图像的子块运动补偿图像.最后，利用鱼眼图像的子块运动补偿图像和真实拍摄图像的差异信息实现运动目标检测.多种测试场景下的实验结果表明了本文方法的有效性.

关键词: 运动目标检测, 子块运动补偿, 单目视觉, 鱼眼相机

Abstract:

With its wide-angle imaging and information richness,the fish-eye camera has a brilliant prospect in application.This paper presents a moving object detection method for on-board monocular fish-eye cameras.Firstly,a sub-block motion compensation model is proposed to compensate image background motion,which solves the ineffective strong parallax scene compensation problem.Secondly,when it comes to solve the parameters of sub-block motion compensation model,ego-vehicle motion parameters are introduced to simplify the number of model parameters,and the direct method is used to avoid the problem that the traditional feature-point-based matching method is susceptible to mismatching feature points.Then for the image distortion problem,this paper proposes a three-plane rectification method to obtain sub-block motion compensation images.Finally,the moving object detection is realized using the difference between sub-block motion compensation images and captured images.Experimental results show the effectiveness of the proposed method.

Key words: moving object detection, sub-block motion compensation, monocular vision, fish-eye camera

中图分类号:

TP391

于红绯, 刘威, 袁淮, 赵宏. 基于子块运动补偿的运动目标检测[J]. 电子学报, 2017, 45(1): 173-180.

YU Hong-fei, LIU Wei, YUAN Huai, ZHAO Hong. Moving Object Detection Based on Sub-Block Motion Compensation[J]. Acta Electronica Sinica, 2017, 45(1): 173-180.

参考文献

[1] Broggi A,Cardarelli E,Cattani S,et al.Vehicle detection for autonomous parking using a Soft-Cascade AdaBoost classifier[A].Proceedings of Intelligent Vehicles Symposium[C].New Jersey,USA:IEEE,2014.912-917.
[2] 魏志强,纪筱鹏,冯业伟.基于自适应背景图像更新的运动目标检测方法[J].电子学报,2005,33(12):2261-2264. Wei Zhi-qiang,Ji Xiao-peng,Feng Ye-wei.A moving object detection method based on self-adaptive updating of background[J].Acta Electronica Sinica,2005,33(12):2261-2264.(in Chinese)
[3] 李宏友,汪同庆,叶俊勇,蒋昀赟.基于3D OGHM的视频运动目标检测算法[J].电子学报,2008,36(3):604-608. Li Hong-you,Wang Tong-qing,Ye Jun-yong,Jiang Yun-yun.An approach based on 3D orthogonal gassian-hermite moments for detecting moving objects[J].Acta Electronica Sinica,2008,36(3):604-608.(in Chinese)
[4] Sato I,Yamano C,Yanagawa H.Crossing obstacle detection with a vehicle-mounted camera[A].Proceedings of Intelligent Vehicles Symposium[C].New Jersey,USA:IEEE,2011.60-65.
[5] 张泽旭,李金宗,李宁宁.基于光流场分割和Canny边缘提取融合算法的运动目标检测[J].电子学报,2003,31(9):1299-1302. Zhang Ze-xu,Li Jin-zong,Li Ning-ning.Detection of moving object using a fusion method based on segmentation of optical flow field and edge extracted by Canny s operator[J].Acta Electronica Sinica,2003,31(9):1299-1302.(in Chinese)
[6] Yamaguchi K,Kato T,Ninomiya Y.Moving obstacle detection using monocular vision[A].Proceedings of Intelligent Vehicles Symposium[C].New Jersey,USA:IEEE,2006.288-293.
[7] Kundu A,Krishna K M,Sivaswamy J.Moving object detection by multi-view geometric techniques from a single camera mounted robot[A].Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems[C].New Jersey,USA:IEEE,2009.4306-4312.
[8] Schueler K,Raaijmakers M,Neumaier S,et al.Detecting parallel moving vehicles with monocular omnidirectional side cameras[A].Proceedings of Intelligent Vehicles Symposium[C].New Jersey,USA:IEEE,2013.567-572.
[9] Hartley R,Vidal R.The multibody trifocal tensor:Motion segmentation from 3 perspective views[A].Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C].New Jersey,USA:IEEE,2004.769-775.
[10] Zhang G,Jia J,Xiong W,et al.Moving object extraction with a hand-held camera[A].Proceedings of IEEE 11th International Conference on Computer Vision[C].New Jersey,USA:IEEE,2007.1-8.
[11] Ozden K E,Schindler K,Van Gool L.Simultaneous segmentation and 3d reconstruction of monocular image sequences[A].Proceedings of IEEE 11th International Conference on Computer Vision[C].New Jersey,USA:IEEE,2007.1-8.
[12] Sheikh Y,Javed O,Kanade T.Background subtraction for freely moving cameras[A].Proceedings of IEEE 12th International Conference on Computer Vision[C].New Jersey,USA:IEEE,2009.1219-1225.
[13] 王洪斌,赵振涌,顾彪,等.基于全局运动补偿的多运动目标检测方法研究[J].电子技术应用,2011,37(1):110-113. Wang Hong-bin,Zhao Zhen-yong,GU Biao,et al.Research on multi-moving object detection algorithm based on global motion compensation[J].Computer Technology and Its Applications,2011,37(1):110-113.(in Chinese)
[14] 吴思,林守勋,张勇东.基于动态背景构造的视频运动对象自动分割[J].计算机学报,2005,28(8):1386-1392. Wu Si,Lin Shou-xun,Zhang Yong-Dong.Automatic segmentation of moving objects in video sequences based on dynamic background construction[J].Chinese Journal of Computers,2005,28(8):1386-1392.(in Chinese)
[15] 郑世友,费树岷,刘怀,等.动态场景图像序列中运动目标检测新方法[J].中国图象图形学报,2007,12(9):1590-1597. Zheng Shi-you,Fei Shu-min,Liu Huai,et al.A novel approach to moving object detection in image sequence acquired by a mobile camera[J] Journal of Image and Graphics,2007,12(9):1590-1597.(in Chinese)
[16] Jung B,Sukhatme G S.Real-time motion tracking from a mobile robot[J].International Journal of Social Robotics,2010,2(1):63-78.
[17] Lin C C,Wolf M.Detecting moving objects using a camera on a moving platform[A].Proceedings of 20th International Conference on Pattern Recognition[C].New Jersey,USA:IEEE,2010.460-463.
[18] 金俣欣,陶霖密,徐光祐,等.摄像机自由运动环境下的背景建模[J].中国图象图形学报,2008,13(2):359-364. Jin Yu-xin,Tao Lin-mi,Xu Guang-you,et al.Background modeling under free moving camera environment[J].Journal of Image and Graphics,2008,13(2):359-364.(in Chinese)
[19] Yuan C,Medioni G,Kang J,et al.Detecting motion regions in the presence of a strong parallax from a moving camera by multiview geometric constraints[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(9):1627-1641.
[20] Kim J,Ye G,Kim D.Moving object detection under free-moving camera[A].Proceedings of 17th IEEE International Conference on Image Processing[C].New Jersey,USA:IEEE,2010.4669-4672.
[21] Einhorn E,Filzhuth M,Schröter C,et al.Monocular detection and estimation of moving obstacles for robot navigation[A].Proceedings of the 5th European Conference on Mobile Robots[C].USA:IEEE,2011.121-126.
[22] Cuevas C,Mohedano R,Garcia N.Statistical moving object detection for mobile devices with camera[A].Proceedings of IEEE International Conference on Consumer Electronics[C].New Jersey,USA:IEEE,2015.15-16.
[23] Hold S,Nunny C,Kummert A,et al.Efficient and robust extrinsic camera calibration procedure for lane departure warning[A].Proceedings of the 2009 IEEE Intelligent Vehicles Symposium[C].New Jersey,USA:IEEE,2009.382-387.
[24] 于红绯,刘威,袁淮,赵宏.基于鱼眼相机的自运动参数异步估计[J].电子学报,2013,41(9):1831-1835. Yu Hong-fei,Liu Wei,Yuan Huai,Zhao Hong.Ego-motion asynchronous estimation based on fish-eye camera[J].Acta Electronica Sinica,2013,41(9):1831-1835.(in Chinese)
[25] Xu M,Lu J.Distributed RANSAC for the robust estimation of three-dimensional reconstruction[J].Computer Vision,IET,2012,6(4):324-333.
[26] Tomasi C,Kanade T.Detection and Tracking of Point Features[R].USA:Carnegie Mellon University,1991.
[27] Kannala J,Brandt S S.A generic camera model and calibration method for conventional,wide-angle,and fish-eye lenses[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(8):1335-1340.
[28] 黎胜亮,刘昆,张峰,肖龙龙,韩大鹏.基于压缩感知在线稀疏的红外视频遥感凝视成像[J].电子学报,2015,43(3):518-522. Li Sheng-liang,Liu Kun,Zhang Feng,Xiao Long-long,Han Da-peng.Infrared remote sensing video staring imagery based on compressed sensing online sparse[J].Acta Electronica Sinica,2015,43(3):518-522.(in Chinese)
[29] 孙瑾,顾宏斌,郑吉平.一种基于梯度方向信息的运动目标检测算法[J].中国图象图形学报,2008,13(3):571-579. Sun Jin,Gu Hong-bin,Zheng Ji-ping.A gradient direction based moving object detection[J].Journal of Image and Graphics,2008,13(3):571-579.(in Chinese)