Hyperspectral target tracking method based on four-feature fusion and weight coefficients

• Main Authors: QIAN KUN, WANG JIUSHAN, SHEN JIANLU, CHEN PENG
• Format: Patent
• Language: Chinese; English
• Published: 02.04.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a hyperspectral target tracking method based on four-feature fusion and weight coefficients, and belongs to the technical field of image processing. According to the method, ahyperspectral image sequence of a selected channel after spectral dimension reduction and a hyperspectral image sequence of a fused channel after spectral dimension reduction are adopted, so that thedefects of large calculated amount and poor real-time performance caused by simultaneous processing of hyperspectral videos of all wave bands in the prior art are overcome; therefore, the target tracking speed in the hyperspectral image sequence under the complex background is improved. Furthermore, by adopting a response graph fusion mode, a weight coefficient updating method and a base sample updating method, the interference of clutter backgrounds in complex backgrounds is effectively overcome, and the defects that in the prior art, the influence of target shielding and deformation is likely to occur, errors occur i