ASSET-2:
Real-Time Motion Segmentation and Object Tracking
Technical Report TR95SMS2b

(Shorter versions of this have now been published in PAMI [30] and ICCV95 [28])

S.M. Smith

Oxford Centre for Functional Magnetic Resonance Imaging of the Brain (FMRIB),
Department of Clinical Neurology, Oxford University, Oxford, UK
(Previously in Computer Vision and Image Processing Group, DRA Chertsey, DERA, UK)
steve@fmrib.ox.ac.uk
www.fmrib.ox.ac.uk/~ steve

Abstract This paper describes how image sequences taken by a moving video camera may be processed to detect and track moving objects against a moving background in real-time. The motion segmentation and shape tracking system is known as ASSET-2 -- A Scene Segmenter Establishing Tracking, Version 2. Motion is found by tracking image features, and segmentation is based on first-order (i.e., six parameter) flow fields. Shape tracking is performed using two dimensional radial map representations. The system runs in real-time, and is accurate and reliable. It requires no camera calibration and no knowledge of the camera's motion.

Category: Active and real-time vision, motion analysis

© British Crown Copyright 1995, Defence Research Agency, Farnborough, Hampshire GU14 6TD, UK

• Introduction
• Review of Past Research
• ASSET-2 -- Overview
• Feature-Based Optic Flow Estimation
• Flow Segmentation
• Cluster Tracking and Filtering
• Boundary Enhancement Using Edges
• Real-Time Implementation of ASSET-2
• Results
• Conclusions and Future Work
• References