Point Cloud Registration Algorithm Combined Gaussian Mixture Model and Point-to-Plane Metric

Abstract Depth data is an effective tool to locate the intelligent agent in space because it accurately records the 3D geometry information on the surface of the scanned object, and is not affected by factors like shadow and light. However, if there are many planes in the work scene, it is difficult to identify objects and process the resulting huge amount of data. In view of this problem and targeted at object calibration, this paper puts forward a depth data calibration method based on Gauss mixture model. The method converts the depth data to point cloud, filters the noise and collects samples, which effectively reduces the computational load in the following steps. Besides, the authors cluster the point cloud vector with the Gaussian mixture model, and obtain the target and background planes by using the random sampling consensus algorithm to fit the planes. The combination of target Region Of Intelligent agent (ROI) and point cloud significantly reduces the computational load and improves the computing speed. The effect and accuracy of the algorithm is verified by the test of the actual object.

Download Full-text

Point Cloud Registration Algorithm Based on Laplace Mixture Model

IEEE Access ◽

10.1109/access.2021.3119574 ◽

2021 ◽

pp. 1-1

Author(s):

Qin Shu ◽

Yu Fan ◽

Chang Wang ◽

Xiuli He ◽

Chunxiao Yu

Keyword(s):

Mixture Model ◽

Point Cloud ◽

Point Cloud Registration ◽

Registration Algorithm

Download Full-text

Cloud robotic grasping of Gaussian mixture model based on point cloud projection under occlusion

Assembly Automation ◽

10.1108/aa-11-2020-0170 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Shifeng Lin ◽

Ning Wang

Keyword(s):

Gaussian Mixture Model ◽

Mixture Model ◽

Point Cloud ◽

Gaussian Mixture ◽

Working Environment ◽

Vision Sensor ◽

Content Type ◽

Cloud Robotics ◽

Camera View ◽

Robot Grasping

Purpose In multi-robot cooperation, the cloud can share sensor data, which can help robots better perceive the environment. For cloud robotics, robot grasping is an important ability that must be mastered. Usually, the information source of grasping mainly comes from visual sensors. However, due to the uncertainty of the working environment, the information acquisition of the vision sensor may encounter the situation of being blocked by unknown objects. This paper aims to propose a solution to the problem in robot grasping when the vision sensor information is blocked by sharing the information of multi-vision sensors in the cloud. Design/methodology/approach First, the random sampling consensus algorithm and principal component analysis (PCA) algorithms are used to detect the desktop range. Then, the minimum bounding rectangle of the occlusion area is obtained by the PCA algorithm. The candidate camera view range is obtained by plane segmentation. Then the candidate camera view range is combined with the manipulator workspace to obtain the camera posture and drive the arm to take pictures of the desktop occlusion area. Finally, the Gaussian mixture model (GMM) is used to approximate the shape of the object projection and for every single Gaussian model, the grabbing rectangle is generated and evaluated to get the most suitable one. Findings In this paper, a variety of cloud robotic being blocked are tested. Experimental results show that the proposed algorithm can capture the image of the occluded desktop and grab the objects in the occluded area successfully. Originality/value In the existing work, there are few research studies on using active multi-sensor to solve the occlusion problem. This paper presents a new solution to the occlusion problem. The proposed method can be applied to the multi-cloud robotics working environment through cloud sharing, which helps the robot to perceive the environment better. In addition, this paper proposes a method to obtain the object-grabbing rectangle based on GMM shape approximation of point cloud projection. Experiments show that the proposed methods can work well.

Download Full-text

Point Cloud Filtering via Generalized Gaussian Mixture Model

Proceedings of The 7th International Conference on Intelligent Systems and Image Processing 2019 ◽

10.12792/icisip2019.018 ◽

2019 ◽

Author(s):

Chunzhi Gu ◽

Kota Ushiwaka ◽

Shogo Tokai ◽

Chao Zhang

Keyword(s):

Gaussian Mixture Model ◽

Mixture Model ◽

Point Cloud ◽

Gaussian Mixture

Download Full-text

A Method for Broccoli Seedling Recognition in Natural Environment Based on Binocular Stereo Vision and Gaussian Mixture Model

Sensors ◽

10.3390/s19051132 ◽

2019 ◽

Vol 19 (5) ◽

pp. 1132 ◽

Cited By ~ 6

Author(s):

Luzhen Ge ◽

Zhilun Yang ◽

Zhe Sun ◽

Gan Zhang ◽

Ming Zhang ◽

...

Keyword(s):

Gaussian Mixture Model ◽

Mixture Model ◽

Natural Environment ◽

Point Cloud ◽

Low Cost ◽

Operation Time ◽

Gaussian Mixture ◽

Disparity Map ◽

Binocular Stereo Vision ◽

Global Matching

Illumination in the natural environment is uncontrollable, and the field background is complex and changeable which all leads to the poor quality of broccoli seedling images. The colors of weeds and broccoli seedlings are close, especially under weedy conditions. The factors above have a large influence on the stability, velocity and accuracy of broccoli seedling recognition based on traditional 2D image processing technologies. The broccoli seedlings are higher than the soil background and weeds in height due to the growth advantage of transplanted crops. A method of broccoli seedling recognition in natural environments based on Binocular Stereo Vision and a Gaussian Mixture Model is proposed in this paper. Firstly, binocular images of broccoli seedlings were obtained by an integrated, portable and low-cost binocular camera. Then left and right images were rectified, and a disparity map of the rectified images was obtained by the Semi-Global Matching (SGM) algorithm. The original 3D dense point cloud was reconstructed using the disparity map and left camera internal parameters. To reduce the operation time, a non-uniform grid sample method was used for the sparse point cloud. After that, the Gaussian Mixture Model (GMM) cluster was exploited and the broccoli seedling points were recognized from the sparse point cloud. An outlier filtering algorithm based on k-nearest neighbors (KNN) was applied to remove the discrete points along with the recognized broccoli seedling points. Finally, an ideal point cloud of broccoli seedlings can be obtained, and the broccoli seedlings recognized. The experimental results show that the Semi-Global Matching (SGM) algorithm can meet the matching requirements of broccoli images in the natural environment, and the average operation time of SGM is 138 ms. The SGM algorithm is superior to the Sum of Absolute Differences (SAD) algorithm and Sum of Squared Differences (SSD) algorithms. The recognition results of Gaussian Mixture Model (GMM) outperforms K-means and Fuzzy c-means with the average running time of 51 ms. To process a pair of images with the resolution of 640×480, the total running time of the proposed method is 578 ms, and the correct recognition rate is 97.98% of 247 pairs of images. The average value of sensitivity is 85.91%. The average percentage of the theoretical envelope box volume to the measured envelope box volume is 95.66%. The method can provide a low-cost, real-time and high-accuracy solution for crop recognition in natural environment.

Download Full-text