Abnormal driving monitoring model establishment method, device and storage medium

Abstract

The invention discloses a method for establishing an abnormal driving monitoring model. The method includes: acquiring a plurality of samples, each sample including the first modal data and the target of the first modal data in the same driving time period collected by multiple collectors Result: input the first modal data of the sample into the first abnormal driving monitoring model for training, and output the first fused data that fuses the single first modal data and the second fused data that fuses all the first modal data of the sample; according to The first fusion data, the second fusion data and the target result calculate the global loss function of the first abnormal driving monitoring model; use the back propagation mechanism and the Adam algorithm to update the weight of the first abnormal driving monitoring model according to the global loss function. The invention also discloses an abnormal driving monitoring model establishment device and a storage medium. The invention can perform multi-level and accurate fusion of multi-modal data, so that the abnormal driving monitoring model can accurately monitor various abnormal driving states.

Description

technical field [0001] The invention relates to the technical field of traffic analysis, in particular to a method, device and storage medium for establishing an abnormal driving monitoring model. Background technique [0002] In recent years, due to the impact of life pressure and physical and mental tension, traffic accidents caused by abnormal driving conditions such as fatigue driving, distraction, emotional driving, and sudden illness have gradually increased. Due to changes in age, physical or mental health, emotions, etc., even a good driver may not be able to maintain his original good driving state for a long time, but it is difficult for the driver himself to realize this gradual attenuation or subside. Therefore, monitoring the driver's driving behavior and giving an alert to abnormal driving behavior can improve the driver's driving ability and reduce his driving load, coordinate the relationship between the driver, the vehicle and the traffic environment, and e...

AI Technical Summary

Problems solved by technology

[0004] Existing abnormal driving monitoring methods currently have a single data source: they basically use a single modal modeling monitoring, such as driver monitoring video or mobile phone built-in motion sensors to identify driving status

Even if multi-modal monitoring is used, the fusion level of multi-modal data is simple and the effect is poor. Existing sensor data fusion methods often only use early fusion or decision-making fusion, and it is impossible to obtain the optimal fusion strategy integratedly.

Moreover, the abnormal state monitoring target is single. The existing abnormal driving states are generally divided into distraction, fatigue, etc., and the existing methods can only identify a single abnormal state, and cannot obtain multiple abnormal driving monitoring results.

Images