A Fast Point Cloud Recognition Algorithm Based on Keypoint Pair Feature

Abstract

At present, PPF-based point cloud recognition algorithms can perform better matching than competitors and be verified in the case of severe occlusion and stacking. However, including certain superfluous feature point pairs in the global model description would significantly lower the algorithm’s efficiency. As a result, this paper delves into the Point Pair Feature (PPF) algorithm and proposes a 6D pose estimation method based on Keypoint Pair Feature (K-PPF) voting. The K-PPF algorithm is based on the PPF algorithm and proposes an improved algorithm for the sampling point part. The sample points are retrieved using a combination of curvature-adaptive and grid ISS, and the angle-adaptive judgment is performed on the sampling points to extract the keypoints, therefore improving the point pair feature difference and matching accuracy. To verify the effectiveness of the method, we analyze the experimental results in scenes with different occlusion and complexity levels under the evaluation metrics of ADD-S, Recall, Precision, and Overlap rate. The results show that the algorithm in this paper reduces redundant point pairs and improves recognition efficiency and robustness compared with PPF. Compared with FPFH, CSHOT, SHOT and SI algorithms, this paper improves the recall rate by more than 12.5%.

Research on point cloud matching algorithm based on point pair feature and improved ICP

“…This paper will verify the results in different complex scenarios according to the given models. Firstly, the occlusion degree of different scenes is determined, and the overlap rate between point clouds [1] is obtained to verify whether the algorithm has a good target recognition rate. The recognition objects of point clouds are shown in the following figure (a1), (b1) is the result of the algorithm recognized by the normal information of this paper, the model point clouds identified in the scene point clouds are depicted with red enclosing boxes, and the recognition effect is shown in red, (c1) is the result of the algorithm recognized by the color information of this paper, the model point clouds identified in the scene point clouds are depicted with red enclosing boxes, and the recognition effect is shown in green .…”

“…At present, in the virtual-real fusion based on augmented reality, the recognition of 3D objects obtained by different sensors has been widely studied [1]. It is summarized into 3 categories: 1.…”

A Robust Sphere Detection in a Realsense Point Cloud by USING Z-Score and RANSAC

“…Sphere detection is used in camera calibration [31], many approaches convert 3D data to 2D images as in [32], then use circle and ellipse detection to find circumferences in the 2D data and later translate coordinates from 2D to 3D to locate the sphere object in the 3D data. Furthermore, there are classical options as Hough Voting still being used [35,36], and deep learning approaches as in [37,38] to locate objects with a circular shape, novel approaches using deep learning allow to locate objects in complex scenes. Some previous methods use RANSAC to find and fit the sphere, nevertheless unlike the method proposed in [32] a background subtraction is required to limit the search space.…”

LiDAR Point Cloud Object Recognition Method via Intensity Image Compensation

“…The RoPS method has been shown to be highly descriptive [10]. Ge et al proposed a key point pair feature (K-PPF) algorithm [11]. They used the method to combine the curvature adaptive and grid ISS to extract the sample points and carried out angle adaptive judgment on the sampling points to extract the key points to improve the point pair feature difference and matching accuracy.…”