Research On Risky Action Recognition Method Of Constructors Based On Improved Two-Stream CNN

Construction activities are typical high-risk production activities.Due to the weak safety awareness and irregular operation of construction workers,most construction safety accidents are caused by the unsafe action of construction workers.Two-stream CNN and model lightweight methods have been applied to the intelligent recognition analysis of unsafe action of construction workers,but there are problems such as large model size,low recognition speed and low recognition accuracy.Therefore,it is significant to improve the recognition speed and accuracy of the model of unsafe action of construction workers.On the basis of attention mechanism based feature vector extraction method and the deep learning model-based lightweight method,this paper designs an unsafe action recognition model of construction workers based on improved two-stream CNN.The model first extracts dense optical flow images based on TV-L1 method,selects video key frames using the inter-frame difference method,and reduplicates the extracted key frames to further reduce the similarity of adjacent key frames and improve the model processing efficiency.Based on the two-stream CNN framework,the model secondly adopts the efficient neural network structure ShuffleNetV2 and the CBAM to achieve spatial-temporal flow feature extraction from video data,introduces the Bi-LSTM structure for the long-time sequence characteristics of the video to integrate the spatial-temporal flow features,and uses the attention mechanism to adaptively optimize the results of action recognition.The results show that the recognition accuracy of the trained unsafe action recognition model designed in this paper is 94.3%and 94.8%on the public datasets and self-built datasets,and the model size is 41M.Compared with the traditional two-stream CNN action recognition model,the recognition accuracy of the model is improved,and the model size and computational complexity are greatly reduced.Finally,the minimum hardware circuit system of edge recognition device for unsafe action of construction workers based on RK3399Pro core board is designed,which mainly includes power supply circuit,reset circuit and clock circuit,as well as peripheral function interface circuit such as USB circuit,video display circuit and UART circuit.For realizing the in-situ processing of the video by the model at edge,it is necessary to execute model transformation and model quantification on the lightweight unsafe action recognition model of construction workers.The results show that the model size after 16-bit integer conversion is 20.9M,the model recognition accuracy is 91.1%.The experimental results show that although the accuracy of the lightweight unsafe action recognition model designed in this paper decreases slightly on edge devices with limited performance,it reaches more than 90%of the general requirement,indicating that the model proposed in this paper has certain reference value.