Abstract:

As a primary technology of group targets tracking, the result of group segmentation is the key to the outcome of the entire data processing progress. Based on the stateofart researches, a fast algorithm of group segmentation based on coordinates transformations and distance differentiations is proposed. Firstly, the twodimension information of acquired sets is decomposed into two onedimensional information of coordinate distance. Then, the sets are sorted and segmented, which make time complexity reduced. Finally, the final segmentation group is obtained by extracting the intersection of two underprocessed groups. Compared to three traditional methods in theory analysis of time complexity, the proposed method is more effective especially under the condition of large field of vision with sparse radar echoes. The simulation results of multiscences show that, the proposed algorithm is much more efficient than the traditional methods, and has excellent robustness to dynamic scenes.