Authors:
Alexander Bachmann
and
Irina Lulcheva
Affiliation:
University of Karlsruhe (TH), Germany
Keyword(s):
Stereo vision, Motion segmentation, Markov Random fields, Object classification, Global image context.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Detecting 3D Objects Using Patterns of Motion and Appearance
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Methodologies and Methods
;
Motion, Tracking and Stereo Vision
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Segment Cluster Tracking
;
Sensor Networks
;
Soft Computing
Abstract:
In this paper we address the problem of detecting objects form a moving camera by jointly considering lowlevel image features and high-level object information. The proposed method partitions an image sequence into independently moving regions with similar 3-dimensional (3D) motion and distance to the observer. In the recognition stage category-specific information is integrated into the partitioning process. An object category is represented by a set of descriptors expressing the local appearance of salient object parts. To account for the geometric relationships among object parts a structural prior over part configurations is designed. This prior structure expresses the spatial dependencies of object parts observed in a training data set. To achieve global consistency in the recognition process, information about the scene is extracted from the entire image based on a set of global image features. These features are used to predict the scene context of the image from which charact
eristic spatial distributions and properties of an object category are derived. The scene context helps to resolve local ambiguities and achieves locally and globally consistent image segmentation. Our expectations on spatial continuity of objects are expressed in a Markov Random Field (MRF) model. Segmentation results are presented based on real image sequences.
(More)