Block-based adaptive correlation target localization method

• Main Authors: HAO LULU, SHAO XIAOPENG, LIU FEI, JU QING, LI XIANTONG, ZHAO XIAOMING
• Format: Patent
• Language: Chinese; English
• Published: 04.01.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a block-based self-adaptive correlation target positioning method, which comprises the following steps: S1, acquiring an initial frame target template and initializing a plurality of template blocks in the initial frame target template; S2, downsampling the initial frame target template to obtain a sampling template; S3, coarse positioning the target of the current image according to the sampling template to obtain the coarse positioning position of the target; S4, obtaining a current frame small block of the current image according to the coarse positioning position; S5, processing the current frame block according to the clustering voting algorithm to obtain the exact center of the target. The self-adaptive correlation target locating method based on the partitionof the invention performs single-connection hierarchical condensation clustering based on the partition of the partition, can accurately locate the center of the target to be tracked, and has small calculation amount and fas