Vehicle collision detection method and device, electronic equipment and storage medium

Abstract

The invention relates to a vehicle collision detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the driving data of a vehicle under the condition that the vehicle is abnormal, and determining a to-be-detected image sequence comprising at least two vehicle images based on the driving data of the vehicle; further, detecting the to-be-detected image sequence to confirm whether a collision event occurs in the vehicle, and confirming a vehicle collision scene under the condition that the collision event occurs in the vehicle is detected. According to the embodiment of the invention, when the vehicle sensor senses that the vehicle is abnormal, whether the vehicle is collided or not is automatically detected according to the driving condition, and collision misinformation caused by sensor sensitivity is avoided. Meanwhile, the vehicle collision scene is automatically identified after the vehicle collision is detected, so the efficiency of the subsequent vehicle rescue process is improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a vehicle collision detection method and device, electronic equipment, and a storage medium. Background technique [0002] The real-time detection of vehicle collision events can significantly improve the efficiency of traffic accident rescue, and help to more accurately identify accidents and settle vehicle maintenance claims. However, related technologies usually perform collision detection based on abnormal signals captured by on-board sensors such as gyroscopes. Due to the sensitivity of the on-board sensors, when the road environment is poor, the vehicle accelerates sharply, or makes a sharp turn, the non-collision state will be detected as a vehicle collision, resulting in a large number of false alarms. Moreover, the method for solving the above-mentioned false positives in related technologies is to perform secondary confirmation through manual identificat...

AI Technical Summary

Problems solved by technology

Due to the sensitivity of the on-board sensors, when the road environment is poor, the vehicle accelerates sharply, or makes a sharp turn, the non-collision state will be detected as a vehicle collision, resulting in a large number of false alarms

Moreover, the method of related technologies to solve the above-mentioned false positives is to perform secondary confirmation through manual identification. This confirmation method requires a huge amount of human and financial resources and is inefficient.

Images