Human Action Recognition Based on AdaBoost Algorithm for Feature Extraction
Xiaofei Ji, Lu Zhou, Yibo Li · 2014
A novel action recognition method based on AdaBoost algorithm is proposed in this paper. The method can select the most discriminative sample subset from a large amount of raw features of training data, so it can reduce the recognition computational complexity with high accuracy. The histogram of oriented gradient feature (HOG) descriptor is utilized to represent raw feature data. In order to select the most discriminative samples, Gadabouts algorithm is used to extract the raw feature data. The nearest neighbor classifier algorithm is utilized to test the proposed method on the UCF Sports database. Experiment results show that the method not only achieve the better recognition rate but also greatly improve the speed of recognition.