Real-time 3D space positioning method based on 3D point cloud fpfh feature
A positioning method and three-dimensional space technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of inaccurate positioning results, errors, and low space-time complexity, and achieve the effect of reducing space-time complexity
Active Publication Date: 2019-01-08
HANGZHOU HUICUI INTELLIGENT TECH CO LTD
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In order to overcome the inaccurate acquisition of color information of the robot under poor lighting or complete darkness conditions, which leads to large errors in registration results and inaccurate positioning results, the present invention provides a robot that is not affected by lighting conditions and has high accuracy. The real-time three-dimensional space positioning method based on the 3D point cloud FPFH feature, which is relatively high and has low computational time and space complexity, uses the three-dimensional point cloud and three-dimensional local features to register the front and rear consecutive frames, and directly obtains the three-dimensional position of the mobile robot. The 3D space positioning information of the mobile robot can be obtained in real time. This method can be used for but not limited to the 3D space positioning of the mobile robot based on vision
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0018] The present invention will be further explained below.
[0019] A real-time three-dimensional space positioning method based on 3D point cloud FPFH features, including the following steps:
[0020] 1) Obtain 3D point cloud data from the depth camera;
[0021] 2) Point cloud key frame selection. In the first frame, the first frame is regarded as a key frame, and the remaining key frame selection method is to filter the number of corresponding points matched by the threshold after the point cloud is accurately matched;
[0022] 3) Point cloud preprocessing: first segment the point cloud, after segmentation, all possible planes in the point cloud can be accurately given in real time; then the plane is downsampled and filtered by the grid downsampling method; finally, area filtering is performed. Eliminate areas with fewer key points;
[0023] 4) Feature description: Use the ISS algorithm to get the key points of the point cloud, and get the FPFH features of the key points;
[0024]...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention relates to a 3D point cloud FPFH characteristic-based real-time three dimensional space positioning method. The method comprises a step 1) of obtaining the 3D point cloud data from a depth camera; a step 2) of selecting the point cloud key frames; 3) a point cloud pre-processing step; 4) a characteristic description step of using an ISS algorithm to obtain the point cloud key points and obtaining the FPFH characteristics of the key points; 5) a point cloud registration step of firstly utilizing a sampling consistency initial registration algorithm to carry out the FPFH characteristic-based initial registration on two point clouds, and then using an ICP algorithm to carry out the secondary registration on an initial registration result; 6) a coordinate transformation step of obtaining a change matrix of the three dimensional space coordinates of a mobile robot, and transforming the coordinate of the current point cloud into an initial position via a transformation matrix; a step 7) of repeating the steps 1) to 6), and calculating the coordinate of the robot relative to the initial position along with the movement of the robot. The method of the present invention has a better accuracy for the real-time positioning of the mobile robot on a bad illumination or completely dark condition.
Description
Technical field [0001] The present invention relates to the field of mobile robot positioning, which can compensate for the inability to realize the positioning function due to the unstable feature extraction caused by unstable illumination or insufficient light, and the positioning result is more real-time and accurate. Background technique [0002] Positioning is the process of determining the position of the robot in its operating environment. More specifically, it uses input information such as a priori environment map, current robot pose estimation, and sensor observations, and undergoes certain processing and transformation. , To produce a more accurate estimate of the current position of the robot. Using the information sensed by sensors to obtain reliable positioning is the most basic and important function of autonomous mobile robots, and it is also an important and challenging research topic that has attracted much attention in mobile robot research. [0003] Kosaka et a...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/33
CPCG06T2207/10028
Inventor 张剑华邱叶强杨焕清刘盛陈胜勇
Owner HANGZHOU HUICUI INTELLIGENT TECH CO LTD