Automobile airbag defect detection algorithm based on improved Faster RCNN

Abstract

The traditional image processing method has a low detection rate for various kinds of automobile airbag surface defects in the production process, which is difficult to meet the actual demand of industrial production. In order to improve the detection rate of automobile airbag surface defects and meet the real-time requirements of industrial detection, this paper proposes an improved Faster RCNN deep learning algorithm. Firstly, the method adopts the E-FPN to enhance the feature extraction ability of the network for multi-scale targets. Then, ROI Align algorithm is introduced instead of ROI Pooling algorithm to improve the detection ability of small targets. Finally, the designed Light Head is used to improve the running speed of the network. The experimental results show that the average precision of the improved Faster RCNN algorithm for automobile airbag defect detection reaches 97.2%, and the detection time is 23.73 milliseconds, which is obviously superior to the original algorithm and has higher detection accuracy and practicability.