Traffic sign detection and identification method based on pruning and knowledge distillation

Abstract

The invention relates to a traffic sign detection and identification method based on pruning and knowledge distillation. The method comprises the following steps: preparing a data set and carrying outdata enhancement; establishing a network and training the network: establishing a YOLOV3-SPP network, loading parameters of a pre-training model trained in the data set ImageNet, and inputting the cut training set images subjected to data enhancement into the network in batches for forward propagation to obtain a model which is an original YOLOV3-SPP network; sparse training: using a scaling coefficient of a BN layer as a parameter for measuring channel importance, adding an L1 regularization item on the basis of an original target function, after adding the L1 regularization item, performingtraining again until loss convergence, and naming the process as sparse training; pruning according to the threshold value; and obtaining a final model by knowledge distillation.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving, and relates to a method for lightweighting traffic sign detection and recognition algorithms by using pruning and knowledge distillation. Background technique [0002] The detection and recognition of traffic signs is a very important content in assisted driving or automatic driving. may have adverse consequences. Because traffic signs transmit guidance, restrictions, warnings or instructions, they play a very important role in predicting road conditions and reducing traffic accidents. Therefore, real-time and accurate recognition of traffic signs is one of the important goals of intelligent driving technology. Deep convolutional neural networks have been successfully applied in the field of traffic sign detection and recognition. However, the huge amount of parameters and calculations of deep convolutional neural networks have seriously affected the real-time performance of traffic ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem of slow speed of existing traffic sign detection and recognition algorithms, the present invention provides a traffic sign detection and recognition method based on pruning and knowledge distillation

Images