Semantic segmentation model training generation method and device and vehicle appearance detection method and device

Abstract

The invention relates to a semantic segmentation model training generation method, a vehicle appearance detection method and device, computer equipment and a storage medium. The training generation method of the semantic segmentation model comprises the following steps: acquiring a plurality of image samples; labeling the category in each image sample to generate a training set; obtaining a weightcorresponding to each category; training a semantic segmentation model to be trained by adopting a loss function, and performing weighted summation according to the weight and the category probability corresponding to each category to obtain a loss value; adjusting model parameters of the semantic segmentation model to be trained according to the loss value, and generating the semantic segmentation model. According to the method, the loss function with the weight is adopted to train the model; the importance of each category in the model training task is adjusted by configuring the weight corresponding to the category, so the precision of model recognition can be improved, and the accuracy of vehicle appearance detection can be improved by adopting the semantic segmentation model obtainedby the method in the vehicle appearance detection process.

Description

technical field [0001] The present application relates to the technical field of vehicle detection, in particular to a training and generation method, device, computer equipment and storage medium for a semantic segmentation model, and a vehicle appearance detection method, device, computer equipment and storage medium. Background technique [0002] With the continuous development of social economy and the continuous improvement of people's living standards, the number of motor vehicles has increased rapidly, so that the workload of annual inspection of motor vehicles has also increased rapidly. [0003] Vehicle appearance recognition is an important part of vehicle annual inspection. In traditional technology, manual judgment is mainly used for vehicle appearance judgment and recognition. In the requirements for the annual inspection of large vehicles, the requirements for determining the eligibility of each component of the large vehicle, such as length, width, thickness,...

AI Technical Summary

Problems solved by technology

However, using this intelligent detection method can only obtain the approximate position information of each component, and there is a problem that the vehicle appearance detection is not accurate enough

Images