Method of recognition and pose estimation of multiple occurrences of multiple objects in visual images

Deepak Khosla; David J. Huber

doi:10.1117/12.883584

Translator Disclaimer

19 May 2011 Method of recognition and pose estimation of multiple occurrences of multiple objects in visual images

Deepak Khosla, David J. Huber

Author Affiliations +

Proceedings Volume 8049, Automatic Target Recognition XXI; 804903 (2011) https://doi.org/10.1117/12.883584
Event: SPIE Defense, Security, and Sensing, 2011, Orlando, Florida, United States

Abstract

This paper describes a system for multiple-object recognition and segmentation that (1) correctly identifies objects in a natural scene and provides a boundary for each object, (2) can identify multiple occurrences of the same object (e.g., two identical objects, side-by-side) in the scene from different training views. The algorithm is novel in that it employs statistical modeling to efficiently prune features from an identified object from the scene without disturbing similar features elsewhere in the scene. The originality of the approach allows one to analyze complex scenes that occur in nature contain multiple instances of the same object.

Citation Download Citation

Deepak Khosla and David J. Huber "Method of recognition and pose estimation of multiple occurrences of multiple objects in visual images", Proc. SPIE 8049, Automatic Target Recognition XXI, 804903 (19 May 2011); https://doi.org/10.1117/12.883584

ACCESS THE FULL ARTICLE