Feature matching method and device and unmanned vehicle

Abstract

The invention provides a feature matching method and device and an unmanned vehicle, and relates to the technical field of computer vision, in particular to the field of unmanned driving. The feature matching method comprises the following steps: by taking each feature point in a first feature point set of a target as a reference point, constructing a reference deviation compensation vector according to a position deviation between the reference point and a candidate matching point in a second feature point set of the target; performing deviation compensation on other feature points in the first feature point set according to the reference deviation compensation vector; determining candidate matching points of the feature points after deviation compensation in the second feature point set to obtain a plurality of candidate matching point sets; and determining an optimal feature matching result of the first feature point set and the second feature point set according to the first feature point set and the plurality of candidate matching point sets. Through the steps, the matching effect of sparse feature points can be improved.

Description

technical field [0001] The present disclosure relates to the technical field of computer vision, in particular to the field of unmanned driving, and in particular to a feature matching method, device and unmanned vehicle. Background technique [0002] In the field of autonomous driving, the task of feature matching is a fundamental task. For example, when detecting and locating traffic lights, it is necessary to perform feature matching between the image data of the traffic lights collected by the camera and the point cloud data of the traffic lights extracted from the map. [0003] At present, feature matching algorithms are dominated by dense point cloud matching algorithms, such as Grid Motion Statistics (GMS) or Vector Field Consistency (VFC). This type of matching algorithm relies on the relatively complete feature distribution of dense point clouds and can achieve better feature matching results. If this type of matching algorithm is applied to sparse point cloud mat...

AI Technical Summary

Problems solved by technology

Using the limited distance combined with the KM algorithm can exclude matching points that are relatively far away, but it still cannot solve the problem of wrong matching caused by factors such as the interference point being close to the point to be matched, the abnormality of the feature point set, and the matching deviation.

Images