Accession Number : ADA448477


Title :   SOFTCBIR: Object Searching in Videos Combining Keypoint Matching and Graduated Assignment


Corporate Author : MARYLAND UNIV COLLEGE PARK INST FOR ADVANCED COMPUTER STUDIES


Personal Author(s) : Luo, Ming ; DeMenthon, Daniel ; Yu, Xiaodong ; Doermann, David


Full Text : http://www.dtic.mil/get-tr-doc/pdf?AD=ADA448477


Report Date : MAY 2006


Pagination or Media Count : 26


Abstract : This paper proposes a new approach to object searching in video databases, SoftCBIR, which combines a keypoint matching algorithm and a graduated assignment algorithm based on 'softassign'. Compared with previous approaches, SoftCBIR is an innovative combination of two powerful techniques: (1) An energy minimization algorithm is applied to match two groups of keypoints while accounting for both their similarity in descriptor space and the consistency of their geometric configuration. The algorithm computes correspondence and pose transformation between two groups of keypoints iteratively and alternately toward an optimal result. The objective energy function combines normalized distance errors in descriptor space and in the spatial domain. (2) Initial individual keypoint matching relies on Approximate K-Nearest Neighbor (ANN) search. ANN achieves much more accurate initial keypoint matching results in the descriptor space than K-means labeling. Experiments prove the effectiveness of our approach, and demonstrate the performance improvements rising from the combination of the two proposed techniques in the SoftCBIR algorithm.


Descriptors :   *DATA BASES , *ALGORITHMS , *VIDEO FRAMES , *VIDEO INTEGRATION


Subject Categories : NUMERICAL MATHEMATICS
      CYBERNETICS
      COMPUTER SYSTEMS


Distribution Statement : APPROVED FOR PUBLIC RELEASE