Three-dimensional target detection method, system and device based on RGB-D

Abstract

The invention belongs to the technical field of target detection, particularly relates to a three-dimensional target detection method, system and device based on RGB-D, and aims to solve the problem that efficiency and 3D target detection accuracy cannot be both considered in the prior art. The method comprises the steps of performing feature extraction on a 2D image set of a to-be-detected target, and reversely mapping the 2D image set to a 3D space; performing voxel division on the 3D point cloud data of the to-be-detected target, and performing feature coding through a 3D convolutional neural network in combination with the mapping voxel of the 2D image; aggregating 2D image texture features and 3D point cloud data geometrical features; obtaining a target feature cluster set through a Hough voting network; and obtaining a target bounding box as a three-dimensional target detection result through the target regression and classification network. According to the method, the 2D imagedata is reversely mapped to the 3D space, the 3D point cloud geometrical characteristics and the 2D image texture characteristics are fused, the 3D target detection accuracy is improved, the pre-selected area is generated through adoption of the Hough voting method, and the 3D target detection efficiency is guaranteed.

Description

technical field [0001] The invention belongs to the technical field of target detection, and in particular relates to an RGB-D-based three-dimensional target detection method, system and device. Background technique [0002] Environmental perception is not only an important issue in computer vision, but also affects the autonomous driving and intelligent robot industries. In the environmental perception problem, the perception technology for 2D image data and 3D point cloud data has achieved unprecedented development. Technologies such as the Faster-Rcnn neural network algorithm based on two-dimensional images and the PointRCNN based on three-dimensional point cloud data are widely used in the industrial field. [0003] There are many common methods in 3D object detection: the first is the projection method, which maps the 3D point cloud to the 2D image, and combines the feature extraction technology of the image. The typical method is the pyramid mapping method. When this...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the above-mentioned problems in the prior art, that is, the problem that the prior art cannot take into account the efficiency and the accuracy of 3D target detection, the present invention provides a RGB-D-based three-dimensional target detection method, the three-dimensional target detection method includes:

Images