Several methods have been proposed for independent motion detection. They all rely on the computation of normal flow fields by a stereoscopic observer. No restrictive assumptions are made regarding the structure of the environment or the parameters of the observers’ motion.

**Method 1 (Independent 3D Motion Detection Based on Depth Elimination in Normal Flow Fields) :**In this work, independent motion detection is formulated as robust parameter estimation applied to the visual input acquired by a binocular, rigidly moving observer. Depth and motion measurements are combined in a linear model. The parameters of this model are related to the parameters of self-motion (egomotion) and the parameters of the stereoscopic configuration of the observer. The robust estimation of this model leads to a segmentation of the scene based on 3D motion. The method avoids the correspondence problem by employing only normal flow fields. Experimental results demonstrate the effectiveness of this method in detecting independent motion in scenes with large depth variations, without any constraints imposed on observer motion.**Method 2 (Independent 3D Motion Detection Using Residual Parallax Normal Flow Fields):**In this work, independent motion detection is formulated as a problem of robust parameter estimation applied to the visual input acquired by a rigidly moving observer. The proposed method automatically selects a planar surface in the scene and the residual planar parallax normal flow field with respect to the motion of this surface is computed at two successive time instants. The two resulting normal flow fields are then combined in a linear model. The parameters of this model are related to the parameters of self-motion (ego- motion) and their robust estimation leads to a segmentation of the scene based on 3D motion. The method avoids a complete solution to the correspondence problem by selectively matching subsets of image points and by employing normal flow fields. Experimental results demonstrate the effectiveness of the proposed method in detecting independent motion in scenes with large depth variations and unrestricted observer motion.**Method 3 (Qualitative Detection of 3D Motion Discontinuities):**In this work, 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.**Method 4 (Independent 3D Motion Detection Through Robust Regression in Depth Layers):**In this work, the qualitative analysis of images acquired by a parallel stereo configuration yields a segmentation of a scene into depth layers. A depth layer consists of points of the 3D space for which depth variations are small compared to the distance from the observer. Robust regression is applied to each depth layer in order to segment the latter into coherently moving regions. Finally, a combination stage is applied across all layers in order to come up with an integrated view of independent motion in the whole 3D scene. 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. Experimental results show the effectiveness and robustness of the proposed scheme, which is capable of discriminating independent 3D motion in scenes with large depth variations.**Method 5 (Fast Visual Detection of Changes in 3D Motion):**A method is proposed for the fast detection of objects that maneuver in the visual field of a monocular observer. Such cases are common in natural environments where the 3D motion parameters of certain objects (e.g. animals) change considerably over time. The approach taken conforms with the theory of {\em purposive vision}, according to which vision algorithms should solve many, specific problems under loose assumptions. The method can effectively answer two important questions: (a) whether the observer has changed his 3D motion parameters, and (b) in case that the observer has constant 3D motion, whether there are any maneuvering objects (objects with non-constant 3D motion parameters) in his visual field. Essentially, the method relies on a pointwise comparison of two normal flow fields which can be robustly computed from three successive frames. Thus, it by-passes the ill-posed problem of optical flow computation. Experimental results demonstrate the effectiveness and robustness of the proposed scheme. Moreover, the computational requirements of the method are extremely low, making it a likely candidate for real-time implementation.

*Sample frames (top to bottom, left to right) of an image sequence acquired by TALOS. Results of independent motion detection. Green areas of the image correspond to the static background, independently moving areas appear in their original intensity.*

Antonis Argyros, Manolis Lourakis, Panos Trahanias, Stelios Orphanoudakis

- A.A. Argyros, P.E. Trahanias, S.C. Orphanoudakis, “Robust Regression for the Detection of Independent 3D Motion by a Binocular Observer”, Journal of Real Time Imaging, Vol. 4, pp. 125-141, April 1998.
- M.I.A. Lourakis, A.A. Argyros, S.C. Orphanoudakis, “Independent 3D Motion Detection Using Residual Parallax Normal Flow Fields”, in proceedings of the International Conference on Computer Vision (ICCV'98), pp. 1012-1017, Bombay, India, January 4-7, 1998.
- A.A. Argyros, S.C. Orphanoudakis, “Independent 3D Motion Detection Based on Depth Elimination in Normal Flow Fields”, in proceedings of the Computer Vision and Pattern Recognition Conference (CVPR'97), pp. 672, San Juan, Puerto Rico, June 17-19, 1997.
- A.A. Argyros, M.I.A. Lourakis, P.E. Trahanias, S.C. Orphanoudakis, “Independent 3D Motion Detection Through Robust Regression in Depth Layers”, in proceedings of the British Machine Vision Conference (BMVC'96), Edinburgh, UK, September 9-12, 1996.
- A.A. Argyros, M.I.A. Lourakis, P.E. Trahanias, S.C. Orphanoudakis, “Qualitative Detection of 3D Motion Discontinuities”, in proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'96), Osaka, Japan, November 4-8, 1996.
- A.A. Argyros, M.I.A. Lourakis, P.E. Trahanias, S.C. Orphanoudakis, “Fast Visual Detection of Changes in 3D Motion”, in proceedings of the IAPR Workshop on Machine Vision Applications (MVA'96), Tokyo, Japan, November 12-14, 1996.
- A.A. Argyros, S.C. Orphanoudakis, “Detecting Independently Moving Objects by Eliminating Depth in Normal Flow Fields”, TR-189, ICS-FORTH, March 1997.
- P.E. Trahanias, M.I.A. Lourakis, A.A. Argyros, S.C. Orphanoudakis “Vision-Based Assistive Navigation for Robotic Wheelchair Platforms”, TR-178, ICS-FORTH, Oct. 1996.
- A.A. Argyros, M.I.A. Lourakis, P.E. Trahanias, S.C. Orphanoudakis, “Qualitative Detection of 3D Motion Discontinuities”, TR-177, ICS-FORTH, Oct. 1996.
- A.A. Argyros, M.I.A. Lourakis, P.E. Trahanias, S.C. Orphanoudakis, “Real-time Detection of Maneuvering Objects by a Monocular Observer”, TR-160, ICS-FORTH, Feb. 1996.
- A.A. Argyros, M.I.A. Lourakis, P.E. Trahanias, S.C. Orphanoudakis, “Independent 3D Motion Detection Through Robust Regression in Depth Layers”, TR-159, ICS-FORTH, Feb. 1996.

**The electronic versions of the above publications can be downloaded from my
publications page.**