Human Action Recognition based on Convolutional Neural Networks with a Convolutional Auto-Encoder
Chi Geng, Jianxin Song · Advances in computer science research · 2016
Human action recognition (HAR) research is hot in computer vision, but high precision recognition of human action in the complex background is still an open question.Most current methods build classifiers based on complex handcrafted features computed from the raw inputs, which are driven by tasks and uncertain.In this paper, type of deep model convolutional neural network (CNN) is proposed for HAR that can act directly on the raw inputs.In addition, an efficient pre-training strategy has been introduced to reduce the high computational cost of kernel training to enable improved real-world applications.The proposed approach has been tested on the KTH database and the achieved results compares favorably against state-of-the-art algorithms using hand-designed features.