Improved Diamond Search Algorithm
In order to improve the accuracy and speed of template matching, the paper presented a new fast search algorithm and called it the improved diamond search (IDS) algorithm. Through analyzing and carrying out several main search algorithms, the center-biased of motion field was taken into consideration in whole process. In addition, IDS algorithm added rough location and enhanced halfway-stop procedures to speed up convergence. Lots of vehicle tracking experiments show that the search performance of IDS algorithm is moderate. Moreover, contrastive experiments prove that IDS algorithm achieves faster search speed, supplying more effective technical support for template matching.
KeywordsImproved diamond search algorithm Motion vector Rough location
This work was supported by the National Nature Science Foundation of China (61072148).
- 1.Liu W, Sun X, Yuan H (2011) Moving target tracking based on the improved diamond search algorithm and Gaussian scale-space. IHMSC 1:65–70Google Scholar
- 2.Hu W-C (2008) Adaptive template block-based block matching for object tracking. ISDA 1(3):61–64Google Scholar
- 3.Ni W, Guo B, Ding G (2005) A Hexagon-based motion estimation algorithm using motion vector field adaptive search technique. Comput Eng 31(13):Google Scholar