University of Twente Student Theses


Segmentation and Motion Estimation of Multiple Independently Moving Objects in Stereo Video Streams

Willemink, G.H. (2005) Segmentation and Motion Estimation of Multiple Independently Moving Objects in Stereo Video Streams.

[img] PDF
Abstract:A method for segmentation and estimation of object motion and structure from 3-d points in a dynamic scene, observed by a sequence of stereo images is proposed. The scope of the assignment is in a project named ‘Wearable Navigation Assistance - A Tool for the Blind’, with the goal of developing a local navigation system for blind people. The proposed method is mainly an extension to a previously described method by Qian [1], with several changes to the method with respect to the measurements, implemented state estimation and clustering. The proposed method is a recursive method where the estimation problem is solved by state estimation of a dynamic system. State estimation will be handled in our method by a Rao-Blackwellized particle filter, where the object motion part of the state is represented by a set of weighted samples and conditioned on the motion, the object structure is represented by Kalman filters. The segmentation problem, defined as the task of segmenting the scene into independently moving objects, is solved by keeping track of which motion samples are compatible with which part of the object structure. By clustering motion samples according to similar object structure compatibility, a segmentation will result where the set of motion samples is divided into subsets, each representing a distinct object motion. The feasibility and performance of the proposed method are investigated by running the method on synthetic scenes. Results from these experiments indicate that the method works well for the simulated scenes. The computational complexity of the method is quite high and as a consequence the method can not yet be implemented in a real-time scenario. Also further research needs to be performed to see how the method performs in real scenes.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:53 electrotechnology
Programme:Electrical Engineering MSc (60353)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page