A local feature description method based on three-dimensional point cloud

Abstract

The invention relates to a local feature description method based on three-dimensional point cloud. The method comprises the following steps: extracting a plurality of feature points from a scene point cloud, taking each feature point as a center, and establishing a three-dimensional local coordinate system according to points in a spherical neighborhood thereof; transforming the points in the spherical neighborhood of the feature points into the corresponding local coordinate system, and partitioning the spatial region of the spherical neighborhood along the radial direction. For each partitioned spatial region, the cosine values alpha and beta of the included angle between each point and the x-axis and z-axis of the coordinate system are calculated and mapped to two independent one-dimensional histograms, respectively. The one-dimensional histograms of all regions are connected in series and then divided by the total number of points in the spherical neighborhood of the feature points to normalize and obtain the final three-dimensional local feature description. The three-dimensional local feature descriptor provided by the invention has the characteristics of good discrimination, strong robustness and high computational efficiency, and improves the correct matching rate of similar parts between scene point clouds.

Description

Technical field [0001] The invention belongs to the field of computer vision, and specifically relates to a local feature description method based on a three-dimensional point cloud. Background technique [0002] Finding similarities in two different point cloud scenes is the basis of many applications, such as 3D scene reconstruction, 3D target recognition, and 3D target retrieval. The process of finding similarities is called feature matching. The feature description of the three-dimensional scene is the premise of feature matching. Due to the limitation of the accuracy of the sensor itself and the different acquisition angles of view, the point cloud data of the acquired scene may have uneven resolution, entrained noise, and even holes in some areas and the situation where the target of interest is blocked. These factors will increase Difficulty of large feature description. How to design a three-dimensional local feature with good distinguishability and strong robustness i...

AI Technical Summary

Problems solved by technology

However, the normal vector of each point needs to be estimated, and the estimation of the normal vector is easily affected by noise and uneven resolution, so the final feature descriptor will also be sensitive to these factors.

Images