Method and device for generating vehicle appearance part identification sample, medium and server

Abstract

The embodiment of the invention relates to the field of intelligent insurance, and discloses a method and device for generating a vehicle appearance part recognition sample, a medium and a server. The method comprises the following steps: acquiring three-dimensional model information of a to-be-processed vehicle; obtaining an ID map of the vehicle part according to the three-dimensional model information; setting rendering data, wherein the rendering data comprises internal and external parameters, light source parameters and background images of the observation camera; rendering the vehicle three-dimensional model into a two-dimensional vehicle image according to the rendering data and the ID chartlet of the vehicle part, and obtaining a vehicle part mask on the vehicle image; and training a vehicle image style converter by using a CycleGAN network, and further migrating the rendered vehicle image into a real style vehicle image while keeping the position of the component mask. According to the implementation of the invention, the vehicle picture sample with the accurate mask-level part label is automatically generated, and the manual label cost of a vehicle part identification task can be remarkably saved.

Description

technical field [0001] The embodiments of the present invention relate to the field of smart insurance, and in particular to a method, device, medium and server for generating identification samples of vehicle exterior parts. Background technique [0002] Vehicle damage assessment based on image recognition has begun to be applied in the field of vehicle insurance. Usually, the deep neural network (DNN) model is used to segment the captured vehicle appearance damage images by parts, and to detect or segment various vehicle damage areas on the image. Then the part segmentation result and the damage detection or segmentation result are fused according to the image position, and finally the damage judgment result of each vehicle part in the image is output. [0003] In order to achieve the segmentation of vehicle parts, the training of existing common segmentation networks such as MaskRCNN requires a large number of image samples with pixel-level annotations. Compared with the...

AI Technical Summary

Problems solved by technology

In order to cover as many as 50 kinds of vehicle appearance parts, as well as various car models, the image samples required to train an available vehicle part segmentation model often reach the order of hundreds of thousands, and the cost of labeling is huge , it is difficult to achieve manually

Images