A kind of Rapid Robust Human Detection Algorithm for the Interested Area

Abstract

A kind of rapid two-level human detection algorithm based on the interested area was proposed in the paper, the coarse-level classifier was obtained via using the cascade training of multi-scale direction feature and Adaboost to extract the possibly human interested area, the decomposition and dimension reduction were realized via nonnegative matrix, and the précised classifier was obtained via the cascade training of dimension reduction feature and intersection kernel support vector machine to detect the human precisely. The experiment on INRIA public test set showed that the algorithm proposed in the paper improved the detection accuracy and greatly reduced the detection time when compared with the currently representative algorithm.