Visual identification and positioning method based on RGB-D camera

Abstract

The invention provides a visual identification and positioning method based on an RGB-D camera. The method comprises the following steps of 1) using a Microsoft Kinect camera sensor to carry out collection of a color image and a depth image and then converting into three-dimensional point cloud, and extracting a plane in a scene; 2) after the plane in the step 1) is extracted, carrying out object extraction and segmentation on the remaining point cloud; 3) carrying out identification and matching on a point cloud set of an object acquired from the step 2) respectively; and 4) though calculating the object point cloud acquired from the step 2), realizing object positioning. In the method, based on a three-dimensional point cloud image collected by a Microsoft RGB-D sensor Kinect II, object identification and positioning are performed, and method does not relate to complex operations of matching of a plurality of images during object positioning and the like. Calculating efficiency is greatly increased, and simultaneously the method possesses advantages that real-time performance is high and the method is suitable for a complex environment of a daily life.

Description

technical field [0001] The invention relates to the field of machine vision recognition and positioning, in particular to a visual recognition and positioning method based on an RGB-D camera. Background technique [0002] At present, most of the existing object recognition and positioning systems based on multi-eye color image cameras obtain the position of each pixel in space by stereo matching the images collected by different sensors, which are costly and slow. , system complexity and other issues. [0003] Object edge segmentation is mostly realized by the method of convex hull extraction based on the image of the color camera. This processing method needs to consider the appearance color of the object, and it is easy to cause misjudgment when the background color is similar to the object, and the method of convex hull extraction is also difficult. There are problems with the wrong convex hull outline of the object and the inclusion of the background part. [0004] Com...

AI Technical Summary

Problems solved by technology

[0002] At present, most of the existing object recognition and positioning systems based on multi-eye color image cameras obtain the position of each pixel in space by stereo matching the images collected by different sensors, which are costly and slow. , system complexity and other issues

[0003] Object edge segmentation is mostly realized by the method of convex hull extraction based on the image of the color camera. This processing method needs to consider the appearance color of the object, and it is easy to cause misjudgment when the background color is similar to the object, and the method of convex hull extraction is also difficult. There is an error in the contour of the convex hull of the object and the problem of including the background part

Images