基于全景视觉的移动机器人的运动目标检测

doi:10.11896/j.issn.1002-137X.2015.11.064

摘要/Abstract

摘要： 在动态背景下的运动目标检测中,由于目标和背景两者都是各自独立运动的,在提取前景运动目标时需要考虑由移动机器人自身运动引起的背景变化。仿射变换是一种广泛用于估计图像间背景变换的方法。然而,在移动机器人上使用全方位视觉传感器(ODVS)时,由于全方位图像的扭曲变形会造成图像中背景运动不一致,无法通过单一的仿射变换描述全方位图像上的背景运动。将图像划分为网格窗口,然后对每个窗口分别进行仿射变换,从背景变换补偿帧差中得到运动目标的区域。最后,根据ODVS的成像特性,通过视觉方法解析出运动障碍物的距离和方位信息。实验结果表明,提出的方法能准确检测出移动机器人360°范围内的运动障碍物,并实现运动障碍物的精确定位,有效地提高了移动机器人的实时避障能力。

关键词: 全方位视觉传感器(ODVS),移动机器人,背景补偿,分块仿射变换

Abstract: For moving object detection in dynamic background,the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot.Affine transformation is widely used to estimate the background transformation between images.However,using omnidirectional vision sensors (ODVS) in mobile robot will cause inconsistencies in the background motion image due to distortion of the omnidirectional image.So only one affine transformation model can not represent the whole background changes.In this paper,the image was divided into grid windows and the area of moving objects were obtained from the background transformation-compensated frame difference using every affine transformation for each window.Finally,according to the imaging characteristics of ODVS,we obtained the distance and orientation information of moving obstacle by visual method.The results demonstrate that the proposed method is very efficient in moving object detection.It can also realize the precise localization of moving obstacles and greatly improve the ability of abstacle avoidance of mobile robot.

Key words: Omnidirectional vision sensor(ODVS),Mobile robot,Background compensated,Blocked affine transformation

汤一平,胡大卫,蔡盈梅,黄珂,姜荣剑. 基于全景视觉的移动机器人的运动目标检测[J]. 计算机科学, 2015, 42(11): 314-319. https://doi.org/10.11896/j.issn.1002-137X.2015.11.064

TANG Yi-ping, HU Da-wei, CAI Ying-mei, HUANG Ke and JIANG Rong-jian. Moving Object Detection in Omnidirectional Vision-based Mobile Robot[J]. Computer Science, 2015, 42(11): 314-319. https://doi.org/10.11896/j.issn.1002-137X.2015.11.064

参考文献

[1] 王亮亮,王黎,高晓蓉,等.基于视频图像的运动目标检测算法研究[J].微计算机信息,2010,26 (16):147-149 Wang L L,Wang L,Gao X R,et al.The research of moving object detection algorithm in video images[J].Control & Automation,2010,6(16):147-149
[2] 邬大鹏,程卫平,于盛林.基于帧间差分和运动估计的 Camshift 目标跟踪算法[J].光电工程,2010,37(1):55-60 Wu D P,Cheng W P,Yu S L.Camshift object tracking algorithm based on inter-frame difference and motion estimation[J].Optoelectronic engineering,2010,37(1):55-60
[3] Xu L,Jia J,Matsushita Y.Motion detail preserving optical flow estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(9):1744-1757
[4] 施家栋,王建中,王红茹.基于光流的人体运动实时检测方法[J].北京理工大学学报(自然科学版),2008,28(9):794-797 Shi J D,Wang J Z,Wang H R.Real-time detection method of human motion based on optical flow[J].Journal of Beijing Institute of Technology(Natural Science Edition),2008,8(9):794-797
[5] 逯新华,史忠科.基于动态模板匹配的空中运动目标检测与跟踪控制[J].电子测量与仪器,2010,24(10):935-941 Lu X H,Shi Z K.Method of detection and tracking control for air moving target based on dynamic template matching[J].Electronic Measurement and Instrument,2010,24(10):935-941
[6] 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 H B,Zhao Z Y,Gu B,et al.Research on multi-moving object detection algorithm based on global motion compensation[J].Application of Electronic Technique,2011,37(1):110-113
[7] Talukder A,Goldberg S,Matthies L,et al.Real-time detection of moving objects in a dynamic scene from moving robotic vehicles[C]∥Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems.2003:1308-1313
[8] Sawhney H S,Ayer S,Gorkani M.Model-based 2D&3D dominant motion estimation for mosaicing and video representation[C]∥Proceedings of the Fifth IEEE International Conference on Computer Vision.1995:583-590
[9] Araki S,Matsuoka T,Takemura H,et al.Real-time tracking of multiple moving objects in moving camera image sequences using robust statistics[C]∥Proceedings of the Fourteenth IEEE International Conference on Pattern Recognition.1998:1433-1435
[10] Jung B,Sukhatme G S.Detecting moving objects using a single camera on a mobile robot in an outdoor environment[C]∥ Proceedings of the International Conference on Intelligent Autonomous Systems.2004:980-987
[11] Vassallo R F,Santos-Victor J,Schneebeli H J.A general ap-proach for egomotion estimation with omnidirectional images[C]∥Proceedings of the Third IEEE Workshop on Omnidirectional Vision.2002:97-103
[12] Liu H,Pi W,Zha H.Motion detection for multiple moving targets by using an omnidirectional camera[C]∥Proceedings of the IEEE International Conference on Robotics,Intelligent Systems and Signal Processing.2003:422-426
[13] Liu H,Dong N,Zha H.Omni-directional vision based human motion detection for autonomous mobile robots[C]∥ Procee-dings of the IEEE International Conference on Systems,Man and Cybernetics.2005:2236-2241
[14] Tomasi C,Kanade T.Detection and tracking of point features[J].Technical Report,1991,9(21):9795-9802
[15] Moravec H P.Towards automatic visual obstacle avoidance[C]∥Proceedings of the International Conference on Artificial Intelligence.1977:584
[16] Marr D,Hildreth E.Theory of edge detection[J].Proceedings of the Royal Society of London(Series B:Biological Sciences),1980,207(1167):187-217
[17] Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]∥IJCAI.1981:674-679
[18] 汤一平,王庆,陈敏智,等.立体全方位视觉传感器的设计[J].仪器仪表学报,2010,1(7):1520-1527 Tang Y P,Wang Q,Chen M Z,et al.Design of stereo omni-directional vision sensor[J].Chinese Journal of scientific instrument,2010,1(7):1520-1527
[19] Scaramuzza D,Martinelli A,Siegwart R.A toolbox for easilycalibrating omnidirectional cameras[C]∥2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.2006:5695-5701
[20] Tang Y P,Wang Q,Zong M L,et al.Design of vertically aligned binocular omnistereo vision sensor[J].E urasip Journal on Image and Video Processing,2010,2010:6
[21] 汤一平,姜荣剑,林璐璐.基于主动式全景视觉的移动机器人障碍[J].计算机科学,2015,42(3):284-288 Tang Y P,Jian R J,Lin L L.Obstacle Detection Method for Mobile Robot Using Active Omnidirectional Vision Sensor[J].Computer Science,2015,2(3):284-288

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed