Qualitative detection of 3D motion discontinuities

This paper presents a method for the detection of objects that move independently of the observer in a 3D dynamic scene. Independent motion detection is achieved through processing of stereoscopic image sequences acquired by a binocular, rigidly moving observer. A weak assumption is made about the observer's motion (egomotion), namely that the direction of the translational and rotational components of egomotion are constant in small image patches. This assumption facilitates the extraction of qualitative information on depth from motion, while additional qualitative depth information is independently computed from image stereo pairs acquired by the binocular vision system. Robust regression in the form of Least Median of Squares estimation is applied within each image patch to test for consistency between the depth functions computed from motion and stereo. Possible inconsistencies signal the presence of independently moving objects. In contrast to other existing approaches for independent motion detection, which are based on the ill-posed problem of optical flow computation, the proposed method relies on normal flow fields for both stereo and motion processing. By exploiting local constraints of qualitative nature, the problem of independent motion detection is approached directly, without relying on a solution to the general structure from motion problem. Experimental results indicate that the proposed method is both effective and robust. y Also in IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS'96), Tokyo, Japan, November 4-8 1996 Qualitative Detection of 3D Motion Discontinuities Antonis A. Argyros, Manolis I. A. Lourakis, Panos E. Trahanias and Stelios C. Orphanoudakis Computer Vision and Robotics Laboratory Institute of Computer Science (ICS) Foundation for Research and Technology --Hellas (FORTH) Science and Technology Park, Heraklio, Crete POBox 1385, GR-711-10 Greece E-mail: fargyros,lourakis,trahania,[email protected], Tel: +30 (81) 391705, Fax: +30 (81) 391601 Technical Report FORTH-ICS / TR-177 --October 1996 c Copyright 1996 by FORTH ABSTRACT:This paper presents amethod for the detection of objects thatmove independently of the observer in a 3D dynamic scene. Independent motion detection is achieved through processing of stereoscopic image sequences acquired by a binocular, rigidly moving observer. A weak assumption is made about the observer's motion (egomotion), namely that the direction of the translational and rotational components of egomotion are constant in small image patches. This assumption facilitates the extraction of qualitative information on depth from motion, while additional qualitative depth information is independently computed from image stereo pairs acquired by the binocular vision system. Robust regression in the form of Least Median of Squares estimation is applied within each image patch to test for consistency between the depth functions computed from motion and stereo. Possible inconsistencies signal the presence of independently moving objects. In contrast to other existing approaches for independent motion detection, which are based on the ill-posed problem of optical flow computation, the proposed method relies on normal flow fields for both stereo and motion processing. By exploiting local constraints of qualitative nature, the problem of independent motion detection is approached directly, without relying on a solution to the general structure from motion problem. Experimental results indicate that the proposed method is both effective and robust.This paper presents amethod for the detection of objects thatmove independently of the observer in a 3D dynamic scene. Independent motion detection is achieved through processing of stereoscopic image sequences acquired by a binocular, rigidly moving observer. A weak assumption is made about the observer's motion (egomotion), namely that the direction of the translational and rotational components of egomotion are constant in small image patches. This assumption facilitates the extraction of qualitative information on depth from motion, while additional qualitative depth information is independently computed from image stereo pairs acquired by the binocular vision system. Robust regression in the form of Least Median of Squares estimation is applied within each image patch to test for consistency between the depth functions computed from motion and stereo. Possible inconsistencies signal the presence of independently moving objects. In contrast to other existing approaches for independent motion detection, which are based on the ill-posed problem of optical flow computation, the proposed method relies on normal flow fields for both stereo and motion processing. By exploiting local constraints of qualitative nature, the problem of independent motion detection is approached directly, without relying on a solution to the general structure from motion problem. Experimental results indicate that the proposed method is both effective and robust. Qualitative Detection of 3D Motion Discontinuities 1