Computer artificial intelligence recognition system relying on firefly optimization algorithm

Abstract

Human behavior recognition is a hot issue in the field of computer artificial intelligence recognition. However, most of the algorithms currently use only RGB or deep video sequences, and they are rarely combined for behavioral artificial intelligence recognition. Therefore, the algorithm relies on the firefly optimization algorithm. The two algorithms of robust depth map and RGB image are effectively combined. The SVM classifiers with multiple different kernel functions are used to evaluate them on the DHA dataset. The experimental results show that the performance of the proposed behavior description algorithm is better than some The performance of representative algorithms is better. At the same time, the performance of the algorithm is further improved after the fusion of depth data and RGB images, and it has better distinguishability and robustness.