Title :
Stochastic models for recognition of articulated objects
Author :
Bhanu, Bir ; Tian, Bing
Author_Institution :
Coll. of Eng., California Univ., Riverside, CA, USA
Abstract :
We present a hidden Markov modeling (HMM) based approach for recognition of articulated objects in synthetic aperture radar (SAR) images. We develop multiple models for a given SAR image of an object and integrate these models synergistically using their probabilistic estimates for recognition and estimates of invariance of features as a result of articulation. The models are based on sequentialization of scattering centers extracted from SAR images. Experimental results are presented using 1440 training images and 2520 testing images for 4 classes
Keywords :
feature extraction; hidden Markov models; image sequences; maximum likelihood estimation; object recognition; probability; radar cross-sections; radar imaging; radar target recognition; stochastic processes; synthetic aperture radar; 1D sequences; HMM; SAR images; articulated objects recognition; experimental results; feature invariance estimation; hidden Markov modeling; maximum likelihood decision; multiple models; probabilistic estimates; scattering centers; stochastic models; synthetic aperture radar; testing images; training image; Azimuth; Geometry; Hidden Markov models; Image recognition; Object recognition; Radar scattering; Solid modeling; Speech recognition; Stochastic processes; Synthetic aperture radar; Testing;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.638629
