Human posture recognition technology has great research value and wide application prospect.The study proposes a human pose recognition algorithm based on deep learning and an improved Openpose algorithm based on energy sequence,extracts the key points of human skeleton,captures the spatial and temporal characteristics of human skeleton data through combining with convolutional neural network(CNN)and long short-term memory network(LSTM),obtains the final classification and recognition results,and verifies them in the data set.The experimental results show that proposed algorithm has gained good performance on human posture recognition.
维普
万方数据