Aims at the requirement of real-time processing in Real-Time Automatic Target Recognition(RTATR) system, this paper presents a hardware acceleration based two-scan connected-component labeling algorithm. Conventional pixel and run based algorithm’s merits are combined, in the first scan, the pixel is processed scan unit while line as label unit, label equivalences are recorded while scanning the image by pixel. Lines with provisional label are outputted as the connected component labeling result. Then the union-find algorithm is used for resolving label equivalences and finds the representative label for each provisional label after the first scan. The labels are replaced in the second scan to complete the connected-component labeling. Experiments on RTATR platform demonstrate that the hardware acceleration implementation of algorithm reaches a higher performance and efficiency and consumes few resources. The implementation of proposed algorithm can meet the demand of real-time processing, and possesses a better practicability.

王洪涛

Papers

New Algorithm for Binary Connected-Component Labeling Based on Run-Length Encoding and Union-Find Sets