Title :
A system for model-based recognition of articulated objects
Author :
Bhanu, Bir ; Ahn, Joon
Author_Institution :
Center for Res. in Intelligent Syst., California Univ., Riverside, CA, USA
Abstract :
This paper presents a model-based matching technique for recognition of articulated objects (with two parts) and the poses of these parts in synthetic aperture radar (SAR) images. Using articulation invariants as features, the recognition system first hypothesizes the pose of the larger part and then the pose of the smaller part. Geometric reasoning is carried out to correct identification errors. The thresholds for the quality of match are determined dynamically by minimizing the probability of a random match. Results are presented using SAR images of three articulated objects. The system performance is evaluated with respect to identification performance, accuracy of estimates for the poses of the object parts and noise
Keywords :
feature extraction; image matching; object recognition; radar target recognition; spatial reasoning; SAR images; articulated object recognition; feature extraction; geometric reasoning; image matching; model-based recognition; pose estimation; Error correction; Feature extraction; Image recognition; Image resolution; Intelligent systems; Pattern recognition; Scattering; System performance; System testing; Target recognition;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.712081