Wheel grounding point detection method, device and storage medium

Abstract

Embodiments of the present invention provide a wheel grounding point detection method, device, and computer-readable storage medium. The method for detecting wheel grounding points includes: identifying the outer contour of at least one obstacle vehicle from the image to be detected; inputting the image within the outer contour of the obstacle vehicle into a neural network model, and using the neural network model The output information determines the position of the wheel contact point of the obstacle vehicle in the image to be detected. The position of the wheel grounding point of the obstacle vehicle determined in the embodiment of the present invention in the image to be detected can more accurately and truly reflect the spatial position of the target vehicle, and has lower requirements on the image of the target vehicle, only the image only needs to contain at least one Just the wheels. In addition, the embodiments of the present invention are applicable to all vehicles and most scenarios, including vehicle truncation, vehicles with too long length, etc., and have good robustness.

Description

technical field [0001] The present invention relates to the field of information technology, and in particular, to a wheel grounding point detection method, device and computer-readable storage medium. Background technique [0002] In an autonomous driving scenario, the vehicle needs to determine the positional relationship with other vehicles when traveling in the current lane, and make appropriate control decisions accordingly to prevent collisions. For example, when it is detected that there is a vehicle at a close distance in front of the lane or a vehicle at a close distance on both sides cuts into the lane, the vehicle needs to decelerate in time. To obtain the accurate distance and position information of other vehicles relative to the own vehicle, it is first necessary to detect the accurate position information of other vehicles in the obtained image to be detected, and then estimate the distance between vehicles on this basis. [0003] For the problem of vehicle p...

AI Technical Summary

Problems solved by technology

(c) When the tail of the vehicle is not inside the image, the position of the vehicle cannot be calculated using the tail box

[0008] (2) The defects of radar distance detection mainly include: (a) Due to the influence of the performance of the radar equipment itself, the material of obstacles, and the reflection angle, the distance information contained in the feedback radar point has a large error

(b) A radar point falls on different positions of the same vehicle, such as the side and the back, and the distance information fed back by it is different, which cannot reflect the unified distance information

(c) The radar point has a certain probability of penetrating the target vehicle and falling on other objects. At this time, the distance information of the radar point cannot truly reflect the distance and position of the target vehicle

(d) Two radar points falling on different vehicles may be misjudged as belonging to the same vehicle, which will also affect the calculation results of vehicle distance and position

Images