Driver driving abnormity detection device and method based on computer vision

Abstract

The invention discloses a driver driving abnormity detection device and method based on computer vision. The detection device comprises a vehicle-mounted camera and video recording, storing and returning equipment. The vehicle-mounted camera is connected with the video recording, storing and returning equipment. The device is characterized by further comprising a detection server and a data storage server which are arranged in a detection center, the detection server is connected with the data storage server through a network, and the detection server is connected with the video recording, storing and returning equipment through the network. Central video image processing and target detection equipment is further arranged in the detection center, the central video image processing and target detection equipment is connected with a detection server, and the detection server is connected with video recording, storing and returning equipment through a network. According to the invention,the problems of large workload and slow response of manual analysis of the existing monitoring means are solved, real-time automatic detection and monitoring of the driving conditions of drivers, passengers and vehicles are realized, a large amount of manpower is saved, accuracy and effectiveness are realized, and the purpose of detection is achieved.

Description

technical field [0001] The invention relates to a computer vision-based driver abnormality detection device and a detection method, relates to the fields of computer vision and machine learning, and is a computer vision-based detection method for a driver's driving situation. Background technique [0002] The driver's driving situation is directly related to the occurrence of vehicle traffic accidents. Good driving behavior can reduce the occurrence of traffic accidents and casualties during vehicle driving; while bad driving behaviors such as fatigue driving, drunk driving, answering phone calls and replying text messages during driving Or surfing the Internet, taking your hands off the steering wheel, etc. will lead to distraction of the driver and even abnormal driving of the vehicle, which will more easily cause traffic accidents. [0003] For transport vehicles, the driver's dangerous driving behavior not only easily leads to road traffic accidents, but also causes acci...

AI Technical Summary

Problems solved by technology

[0004] The current driving behavior of the driver is usually to detect the driving status of the vehicle through external sensors. It is necessary to install corresponding sensors on the outside of the vehicle or on the transmission system, which is costly and requires more additional acquisition and processing equipment; In the case of abnormal driving, the analysis of video surveillance data is mostly manual monitoring and spot checks, with a large analysis workload, small coverage, and poor results, and manual review cannot monitor the scene in real time, making it difficult to monitor all abnormal driving situations and make decisions. Reminders and Quick Responses

Images