Point cloud registration method based on convolution restricted Boltzmann machine

Abstract

The invention discloses a point cloud registration method based on a convolution restricted Boltzmann machine. The multi-angle point cloud image of the object can be recognized, and the pose of the object is obtained. The method comprises the following steps: firstly, obtaining each basic angle of a to-be-identified object for scanning to obtain point cloud image data of the to-be-identified object, and preprocessing the point cloud image data; then, carrying out convolution calculation on the model by using a convolutional neural network to obtain a relatively robust node; constructing a restricted Boltzmann machine training model, determining each parameter of the model, inputting a result obtained by the convolutional network into the model for training, and obtaining optimized bias vectors a and b of the restricted Boltzmann machine and a weight matrix W; and carrying out reverse calculation according to the parameters to obtain a visible layer, wherein the feature vector with thehighest score is the feature vector of the object most possibly corresponding to the point cloud image, so that the object is identified.

Description

technical field [0001] The invention belongs to the field of three-dimensional image recognition, and relates to a point cloud registration method based on a convolution limited Boltzmann machine. Background technique [0002] In some harsh or complex environments, recognizing objects in the scene is a very important research aspect of computer vision. Since the emergence of computer vision, the recognition of two-dimensional images has developed rapidly, and has been applied in many fields and achieved remarkable results. However, compared with two-dimensional plane image recognition, three-dimensional stereo image recognition can realize object recognition and positioning more comprehensively and accurately, and even make a judgment on the posture of the object. 3D point cloud is an important representation of 3D stereoscopic images. The stereoscopic image recognition technology of 3D point cloud has developed rapidly in recent years. Development provides important techn...

AI Technical Summary

Problems solved by technology

However, these traditional methods are carried out by converting the angle of the point cloud image and extracting the local features of the point cloud image. It is difficult to achieve good robustness, so the accuracy and speed of registration are lacking.

Images