Wheel grounding point detection method and device and storage medium

Abstract

The embodiment of the invention provides a wheel grounding point detection method and device and a computer readable storage medium. The wheel grounding point detection method comprises the following steps: identifying an outer surrounding contour of at least one obstacle vehicle from a to-be-detected image; and inputting the image in the outer surrounding contour of the obstacle vehicle into a neural network model, and determining the position of the wheel grounding point of the obstacle vehicle in the to-be-detected image by using the output information of the neural network model. The position of the wheel grounding point of the obstacle vehicle in the to-be-detected image determined by the embodiment of the invention can reflect the spatial position of the target vehicle more accurately and truly, and the requirement on the image of the target vehicle is lower, and only one wheel needs to be contained in the image. In addition, the embodiment of the invention is suitable for all vehicles and most scene conditions, including vehicle truncation, overlong vehicles and the like, and has good robustness.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a method, device and computer-readable storage medium for detecting a wheel ground contact point. Background technique [0002] In an autonomous driving scenario, the vehicle needs to judge its positional relationship with other vehicles when driving 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 short distance in front of the lane or vehicles at a short distance on both sides cut into the lane, the vehicle needs to perform deceleration operation in time. To obtain the accurate distance and position information of other vehicles relative to the 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 vehicl...

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