AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Abstract

Point cloud local feature extraction places an important part of point cloud deep learning neural networks. Accurate extraction of point cloud features is still a challenge for deep learning networks. Oversampling and feature loss of point cloud model are important problems in the accuracy of image point cloud deep learning network. In this paper, we propose an adaptive clustering method for point cloud feature extraction—adaptive optimal means clustering (AOMC)—and apply it to point cloud deep learning network tasks. This method solves the problem of determining the number of clustering centers in the process of point cloud feature extraction so that the feature points contain the whole point cloud model and avoid the problem of losing detail features. Specifically, according to the loss characteristics of point cloud clustering, AOMC selects a different number of clustering centers for various models. Moreover, in light of the density distribution of the point cloud, the radius of the clustering subset is determined. This method effectively improves the accuracy of the point cloud deep learning network on object classification and parts segmentation. Our method reaches demand on Modelnet10 and shapenetcore_partanno_segmentation_benchmark datasets. In terms of deep learning network optimization, it has good performance. Additionally, our method has high accuracy and low algorithm complexity.

Features extraction of point clouds based on Otsu’s algorithm

“…Finally, a minimum spanning tree of the feature points is established to construct the set of feature points. Zhang and Jin [28] proposed an adaptive optimal mean clustering (AOMC) method for point cloud feature extraction. (4) Deep learning algorithms.…”

Enhancing Web Text Clustering Accuracy and Efficiency With a Maximum Entropy Function Model: Overcoming High-Dimensional and Directional Challenges

“…The ever-expanding volume of data presents an immense challenge in the modern era, calling for effective management of this abundance of information. In the realm of exploratory data analysis [1], [2], clustering emerges as a valuable tool across various domains, encompassing pattern recognition [3], feature extraction [4], vector quantization (VQ) [5], image segmentation [6], function approximation [7]. Data mining [8], [9].…”

An improved feature point selection algorithm for point cloud data

“…However, in the traditional fitting method, due to the huge amount of data, an approximation fitting algorithm is often used, or the designed fitting algorithm can only achieve a fitting effect on the data of a certain unique curve characteristic [3] .To solve this problem, we can think from two aspects. One is to adjust the fitted spline curve, that is, to connect data points with different "soft rulers" [4] . The other is to process the data points, and fit a complete curve with as few connection segments as possible under the premise of satisfying the fitting accuracy.…”