Local image describing method based on RGB-D sensor

Abstract

The invention provides a local image describing method based on an RGB-D sensor. The local image describing method comprises the following steps: calibrating parameters of the RGB-D sensor, and carrying out image pretreatment and local characteristic extraction on acquired RGB images and depth images; expressing the central point of the extracted local characteristics through three variables of space partitioning, grayness sequence marking and normal vector sequence marking; calculating out the scale value and the principal direction of characteristic points according to the data of the depth images in the central point of the local characteristics; building a three-dimensional histogram, unfolding the three-dimensional histogram and normalizing the three-dimensional histogram to be a one-dimensional vector which is a descriptor for the local characteristics. Compared with two-dimensional, three-dimensional and fusion descriptors, the method has the advantages of obvious lighting robustness and the scene changeable robustness. Based on depth scale invariance and rotating invariance, in the method provided by the invention, point cloud depth data is used for replacing estimation to the scale space of a Gauss pyramid, so that the speed is accelerated greatly.

Description

technical field [0001] The invention relates to a method for matching data such as an image of an RGB-D sensor and a point cloud, in particular to a method for realizing RGB-D image matching by fusing RGB image texture information and a depth image. Background technique [0002] The local image description method based on RGB-D sensor is inspired by the local feature neighborhood description of 2D images and depth images. Two-dimensional images have rich textures and high information entropy. Therefore, the two-dimensional descriptors that exist at this stage start with spatial partitioning, grayscale, gradient, etc., and have good results, but the two-dimensional descriptors are not ideal for scenes with less lighting or texture changes. In a scene based entirely on a depth image, the depth image will not be affected by missing textures or dramatic lighting changes. Building various descriptors on this basis has a good matching effect, but the matching results of such desc...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a local image description method based on RGB-D sensors, which mainly solves the image matching problem of data obtained from RGB-D sensors

Images