Improving motion-based object detection by incorporating object-specific knowledge. (15th May 2008)

• Record Type: Journal Article
• Authors: Bachmann, Alexander; Dang, Thao
• Is Part Of: International journal of intelligent information and database systems. Volume 2:Number 2(2008)
• Page Start: 258
• Page End: 276
• Publication Date: 2008-05-15
• Subjects: stereo vision -- image segmentation -- Markov random field -- MRF -- object classi&amp -- #64257 -- cation -- object appearance -- motion estimation -- object detection -- moving objects -- object recognition -- driver assistance systems; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

In this contribution, we describe an object detection method that jointly considers low-level features and higher-level object knowledge. The method partitions a stereo image sequence into its most prominent moving groups with similar 3-dimensional (3D) motion and of consistent object-specific appearance. Image segmentation is performed by a Bayesian Maximum a Posteriori estimator assigning the most probable motion profile to each image point. The motion profiles of the elaborated motion models are iteratively refined by an object tracking procedure. Additionally, the probability of salient points to belong to an object category is considered in the probabilistic framework. Our expectation on spatial continuity of objects is expressed in a Markov Random Field (MRF) model.