Image-based vehicle loss assessment method, device, and system, and electronic device

Abstract

The embodiment of the application discloses an image-based vehicle loss assessment method, device, and system, and an electronic device. The method includes steps of: acquiring an image to be processed and recognizing a first vehicle part in the image to be processed; matching a local image having a unrecognized vehicle part in the image to be processed with a part image having a recognized vehicle part in order to determine a second vehicle part to which the local image belongs; detecting the image to be processed and recognizing a damaged position and a damage type in the image to be processed; based on the recognized first vehicle part, the second vehicle part, the damaged position and the damage type, determining a damaged part in the image to be processed and the damaged position and the damage type corresponding to the damaged part. The embodiments of the present application can detect the specific information about the damaged position and degree of the vehicle part quickly, accurately and reliably so that a loss assessment result is accurate and user service experience is improved.

Description

technical field [0001] The present application belongs to the technical field of computer image data processing, and in particular relates to an image-based vehicle damage assessment method, device and electronic equipment. Background technique [0002] After a traffic accident, it is often necessary to wait for the claims adjuster of the insurance company to go to the scene to deal with it, and obtain the basis for the claim by taking pictures. With the increase in the number of motor vehicles in recent years, the number of traffic accidents per year has been at a high level. However, the processing of vehicle claims and loss determination business often needs to rely on the human on-site processing of professional insurance staff, which has high cost, long waiting period and low processing efficiency. [0003] At present, there are some processing methods in the industry that use the images of the traffic accident scene to automatically analyze and obtain the classificati...

AI Technical Summary

Problems solved by technology

In addition, its algorithm only uses CNN's general object recognition algorithm, and the final result of vehicle damage assessment still relies on manual assessment, which requires a large amount of manpower and time, and different insurance companies have inconsistent assessment standards for vehicle damage, coupled with the influence of human subjective factors. The difference in the loss assessment results is large and the reliability is low

Images