Automobile collision detection method and system based on deep learning

Abstract

The invention relates to an automobile collision detection method and system based on deep learning. The automobile collision detection system is mainly composed of a video recording device and an image detection system deployed at a server, and is characterized in that the video recording device acquires images around an automobile, positioning and category classification are performed on automobiles emerging in the images by the image detection system deployed on the server, and according to a classification result and the minimum distance between automobile bounding boxes, a warning is given or recording is performed when the minimum distance between the automobile bounding boxes is less than a safety spacing. According to the invention, feature extraction, positioning and classification are performed based on a deep neural network, and the accuracy and the recall rate of image detection are greatly improved compared with those of a traditional computer vision method, so that the automobile collision detection system can perform effective evaluation on driving behaviors of a driver and especially on a scene in which a vehicle driven by the driver has dangerous driving or collision. The automobile collision detection system records relevant images when the distance between vehicle is less than the safety spacing, and has high efficiency, accuracy and practicability.

Description

technical field [0001] The invention relates to the technical field of automobile safety, in particular to an automobile collision detection technology based on deep learning. Background technique [0002] With the rapid development of society, the popularity of automobiles is also increasing. The rate of car ownership, the percentage of people with a driver's license, and the demand for cars are also increasing. At present, the sharing economy model is becoming more and more popular, and more and more companies are developing car rental business. In addition, in the insurance industry, differentiated insurance products that are priced according to the driving conditions of different drivers have also begun to appear for automobile-related insurance. Whether it is car rental or differentiated insurance products, an important basis for product providers to evaluate drivers is to analyze the data of drivers' driving behavior and safety conditions. Therefore, there is an urg...

AI Technical Summary

Problems solved by technology

However, due to the large amount of information in the image itself and the difficulty of obtaining characteristic information related to the driving state directly through simple calculations, it is often difficult for existing image detection technologies to effectively analyze images collected by vehicle-mounted cameras.

[0005] Existing technology is difficult to automatically analyze and evaluate the driver's driving behavior

Images