An adaptive locally-coded point cloud classification and segmentation network coupled with genetic algorithm

2021 ◽  
pp. 1-16
Author(s):  
Ma Qihang ◽  
Zh Jian ◽  
Zhang Jiahao
Keyword(s):  
Genetic Algorithm ◽  
Point Cloud ◽  
Cloud Data ◽  
Fine Grained ◽  
Network Training ◽  
Cloud Classification ◽  
3D Data ◽  
Average Accuracy ◽  
Mutation Strategy ◽  
Point Cloud Classification

Local information coding helps capture the fine-grained features of the point cloud. The point cloud coding mechanism should be applicable to the point cloud data in different formats. However, the local features of the point cloud are directly affected by the attributes, size and scale of the object. This paper proposes an Adaptive Locally-Coded point cloud classification and segmentation Network coupled with Genetic Algorithm(ALCN-GA), which can automatically adjust the size of search cube to complete network training. ALCN-GA can adapt to the features of 3D data at different points, whose adjustment mechanism is realized by designing a robust crossover and mutation strategy. The proposed method is tested on the ModelNet40 dataset and S3DIS dataset. Respectively, the overall accuracy and average accuracy is 89.5% and 86.5% in classification, and overall accuracy and mIoU of segmentation is 80.34% and 51.05%. Compared with PointNet, average accuracy in classification and mIoU of segmentation is improved about 10% and 11% severally.

scholarly journals A Hierarchical Machine Learning Approach for Multi-Level and Multi-Resolution 3D Point Cloud Classification

2020 ◽  
Vol 12 (16) ◽  
pp. 2598
Author(s):  
Simone Teruggi ◽  
Eleonora Grilli ◽  
Michele Russo ◽  
Francesco Fassi ◽  
Fabio Remondino
Keyword(s):  
Machine Learning ◽  
Point Cloud ◽  
Large Scale ◽  
3D Point Cloud ◽  
Cloud Data ◽  
Cloud Classification ◽  
3D Data ◽  
Structured Information ◽  
Multi Level ◽  
Point Cloud Classification

The recent years saw an extensive use of 3D point cloud data for heritage documentation, valorisation and visualisation. Although rich in metric quality, these 3D data lack structured information such as semantics and hierarchy between parts. In this context, the introduction of point cloud classification methods can play an essential role for better data usage, model definition, analysis and conservation. The paper aims to extend a machine learning (ML) classification method with a multi-level and multi-resolution (MLMR) approach. The proposed MLMR approach improves the learning process and optimises 3D classification results through a hierarchical concept. The MLMR procedure is tested and evaluated on two large-scale and complex datasets: the Pomposa Abbey (Italy) and the Milan Cathedral (Italy). Classification results show the reliability and replicability of the developed method, allowing the identification of the necessary architectural classes at each geometric resolution.

scholarly journals Point Cloud Classification Algorithm Based on the Fusion of the Local Binary Pattern Features and Structural Features of Voxels

2021 ◽  
Vol 13 (16) ◽  
pp. 3156
Author(s):  
Yong Li ◽  
Yinzheng Luo ◽  
Xia Gu ◽  
Dong Chen ◽  
Fang Gao ◽  
...  
Keyword(s):  
Point Cloud ◽  
Local Binary Pattern ◽  
Random Forest Classifier ◽  
Normal Vector ◽  
Point Cloud Data ◽  
Color Information ◽  
Cloud Data ◽  
Cloud Classification ◽  
Local Difference ◽  
Point Cloud Classification

Point cloud classification is a key technology for point cloud applications and point cloud feature extraction is a key step towards achieving point cloud classification. Although there are many point cloud feature extraction and classification methods, and the acquisition of colored point cloud data has become easier in recent years, most point cloud processing algorithms do not consider the color information associated with the point cloud or do not make full use of the color information. Therefore, we propose a voxel-based local feature descriptor according to the voxel-based local binary pattern (VLBP) and fuses point cloud RGB information and geometric structure features using a random forest classifier to build a color point cloud classification algorithm. The proposed algorithm voxelizes the point cloud; divides the neighborhood of the center point into cubes (i.e., multiple adjacent sub-voxels); compares the gray information of the voxel center and adjacent sub-voxels; performs voxel global thresholding to convert it into a binary code; and uses a local difference sign–magnitude transform (LDSMT) to decompose the local difference of an entire voxel into two complementary components of sign and magnitude. Then, the VLBP feature of each point is extracted. To obtain more structural information about the point cloud, the proposed method extracts the normal vector of each point and the corresponding fast point feature histogram (FPFH) based on the normal vector. Finally, the geometric mechanism features (normal vector and FPFH) and color features (RGB and VLBP features) of the point cloud are fused, and a random forest classifier is used to classify the color laser point cloud. The experimental results show that the proposed algorithm can achieve effective point cloud classification for point cloud data from different indoor and outdoor scenes, and the proposed VLBP features can improve the accuracy of point cloud classification.

Unsupervised spatial-awareness attention-based and multi-scale domain adaption network for point cloud classification

2021 ◽  
pp. 2150007
Author(s):  
Rui Guo ◽  
Yong Zhou ◽  
Jiaqi Zhao ◽  
Rui Yao ◽  
Bing Liu ◽  
...  
Keyword(s):  
Point Cloud ◽  
Domain Adaptation ◽  
Spatial Awareness ◽  
Target Domain ◽  
Multi Scale ◽  
Cloud Classification ◽  
Domain Adaption ◽  
3D Data ◽  
3D Data Processing ◽  
Point Cloud Classification

Domain adaption is a special transfer learning method, whose source domain and target domain generally have different data distribution, but need to complete the same task. There have been many significant types of research on domain adaptation in 2D images, but in 3D data processing, domain adaptation is still in its infancy. Therefore, we design a novel domain adaptive network to complete the unsupervised point cloud classification task. Specifically, we propose a multi-scale transform module to improve the feature extractor. Besides, a spatial-awareness attention module combined with channel attention to assign weights to each node is designed to represent hierarchically scaled features. We have validated the proposed method on the PointDA-10 dataset for domain adaption classification tasks. Empirically, it shows strong performance on par or even better than state-of-the-art.

A study on the classification of vegetation point cloud based on the straw checkerbo-ard barriers area of random forest

2021 ◽  
pp. 1-13
Author(s):  
Tiebo Sun ◽  
Jinhao Liu ◽  
Jiangming Kan ◽  
Tingting Sui
Keyword(s):  
Random Forest ◽  
Decision Tree ◽  
Classification Accuracy ◽  
Point Cloud ◽  
Point Cloud Data ◽  
Random Forest Algorithm ◽  
Cloud Data ◽  
Cloud Classification ◽  
Point Cloud Classification

Aiming at the problem of automatic classification of point cloud in the investigation of vegetation resources in the straw checkerboard barriers region, an improved random forest point cloud classification algorithm was proposed. According to the problems of decision tree redundancy and absolute majority voting in the existing random forest algorithm, first the similarity of the decision tree was calculated based on the tree edit distance, further clustered reduction based on the maximum and minimum distance algorithm, and then introduced classification accuracy of decision tree to construct weight matrix to implement weighted voting at the voting stage. Before random forest classification, based on the characteristics of point cloud data, a total of 20 point cloud single-point features and multi-point statistical features were selected to participate in point cloud classification, based on the point cloud data spatial distribution characteristics, three different scales for selecting point cloud neighborhoods were set based on the point cloud density, point cloud classification feature sets at different scales were constructed, optimizing important features of point cloud to participate in point cloud classification calculation after variable importance scored. The experimental results showed that the point cloud classification based on the optimized random forest algorithm in this paper achieved a total classification accuracy of 94.15% in dataset 1 acquired by lidar, the overall accuracy of classification on dataset 2 obtained by dense matching reaches 92.03%, both were higher than the unoptimized random forest algorithm and MRF, SVM point cloud classification method, and dimensionality reduction through feature optimization can greatly improve the efficiency of the algorithm.

scholarly journals PEMCNet: An Efficient Multi-Scale Point Feature Fusion Network for 3D LiDAR Point Cloud Classification

2021 ◽  
Vol 13 (21) ◽  
pp. 4312
Author(s):  
Genping Zhao ◽  
Weiguang Zhang ◽  
Yeping Peng ◽  
Heng Wu ◽  
Zhuowei Wang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Feature Learning ◽  
Point Cloud Data ◽  
Cloud Data ◽  
Multi Scale ◽  
Cloud Classification ◽  
Public Datasets ◽  
Point Cloud Classification ◽  
3D Lidar ◽  
Point Feature

Point cloud classification plays a significant role in Light Detection and Ranging (LiDAR) applications. However, most available multi-scale feature learning networks for large-scale 3D LiDAR point cloud classification tasks are time-consuming. In this paper, an efficient deep neural architecture denoted as Point Expanded Multi-scale Convolutional Network (PEMCNet) is developed to accurately classify the 3D LiDAR point cloud. Different from traditional networks for point cloud processing, PEMCNet includes successive Point Expanded Grouping (PEG) units and Absolute and Relative Spatial Embedding (ARSE) units for representative point feature learning. The PEG unit enables us to progressively increase the receptive field for each observed point and aggregate the feature of a point cloud at different scales but without increasing computation. The ARSE unit following the PEG unit furthermore realizes representative encoding of points relationship, which effectively preserves the geometric details between points. We evaluate our method on both public datasets (the Urban Semantic 3D (US3D) dataset and Semantic3D benchmark dataset) and our new collected Unmanned Aerial Vehicle (UAV) based LiDAR point cloud data of the campus of Guangdong University of Technology. In comparison with four available state-of-the-art methods, our methods ranked first place regarding both efficiency and accuracy. It was observed on the public datasets that with a 2% increase in classification accuracy, over 26% improvement of efficiency was achieved at the same time compared to the second efficient method. Its potential value is also tested on the newly collected point cloud data with over 91% of classification accuracy and 154 ms of processing time.

scholarly journals Manual Point Cloud Classification and Extraction for Hunter-Gatherer Feature Investigation: A Test Case From Two Low Arctic Paleo-Inuit Sites

2016 ◽  
Vol 2 (1) ◽  
Author(s):  
David B. Landry ◽  
S. Brooke Milne ◽  
Robert W. Park ◽  
Ian J. Ferguson ◽  
Mostafa Fayek
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
Test Case ◽  
Cloud Data ◽  
Cloud Classification ◽  
Low Arctic ◽  
Point Cloud Classification ◽  
Effective Use

AbstractFor archaeologists, the task of processing large terrestrial laser scanning (TLS)-derived point cloud data can be difficult, particularly when focusing on acquiring analytical and interpretive outcomes from the data. Using our TLS lidar data collected in 2013 from two compositionally different, low Arctic multi-component hunter-gatherer sites (LdFa-1 and LeDx-42), we demonstrate how a manual point cloud classification approach with open source software can be used to extract natural and archaeological features from a site’s surface. Through a combination of spectral datasets typical to TLS (i.e., intensity and RGB values), archaeologists can enhance the visual and analytical representation of archaeological huntergatherer site surfaces. Our approach classifies low visibility Arctic site point clouds into independent segments, each representing a different surface material found on the site. With the segmented dataset, we extract only the surface boulders to create an alternate characterization of the site’s prominent features and their surroundings. Using surface point clouds from Paleo-Inuit sites allows us to demonstrate the value of this approach within hunter-gatherer research as our results illustrate an effective use of large TLS datasets for extracting and improving our analytical capabilities for low relief site features.

scholarly journals Comparison of Different Feature Sets for TLS Point Cloud Classification

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4206 ◽  
Author(s):  
Quan Li ◽  
Xiaojun Cheng
Keyword(s):  
Feature Selection ◽  
Point Cloud ◽  
Laser Scanning ◽  
Geometric Features ◽  
Real World Data ◽  
Cloud Data ◽  
Cloud Classification ◽  
Color Features ◽  
Point Cloud Classification ◽  
Corrected Intensity

Point cloud classification is an essential requirement for effectively utilizing point cloud data acquired by Terrestrial laser scanning (TLS). Neighborhood selection, feature selection and extraction, and classification of points based on the respective features constitute the commonly used workflow of point cloud classification. Feature selection and extraction has been the focus of many studies, and the choice of different features has had a great impact on classification results. In previous studies, geometric features were widely used for TLS point cloud classification, and only a few studies investigated the potential of both intensity and color on classification using TLS point cloud. In this paper, the geometric features, color features, and intensity features were extracted based on a supervoxel neighborhood. In addition, the original intensity was also corrected for range effect, which is why the corrected intensity features were also extracted. The different combinations of these features were tested on four real-world data sets. Experimental results demonstrate that both color and intensity features can complement the geometric features to help improve the classification results. Furthermore, the combination of geometric features, color features, and corrected intensity features together achieves the highest accuracy in our test.

scholarly journals A POINT CLOUD CLASSIFICATION APPROACH BASED ON VERTICAL STRUCTURES OF GROUND OBJECTS

2018 ◽  
Vol XLII-3 ◽  
pp. 2427-2434
Author(s):  
Y. Zhao ◽  
Q. Hu ◽  
W. Hu
Keyword(s):  
Point Cloud ◽  
Structural Characteristics ◽  
Three Dimensional ◽  
Point Cloud Data ◽  
Characteristic Curves ◽  
Layer Spacing ◽  
Cloud Data ◽  
Whole Process ◽  
Cloud Classification ◽  
Point Cloud Classification

This paper proposes a novel method for point cloud classification using vertical structural characteristics of ground objects. Since urbanization develops rapidly nowadays, urban ground objects also change frequently. Conventional photogrammetric methods cannot satisfy the requirements of updating the ground objects’ information efficiently, so LiDAR (Light Detection and Ranging) technology is employed to accomplish this task. LiDAR data, namely point cloud data, can obtain detailed three-dimensional coordinates of ground objects, but this kind of data is discrete and unorganized. To accomplish ground objects classification with point cloud, we first construct horizontal grids and vertical layers to organize point cloud data, and then calculate vertical characteristics, including density and measures of dispersion, and form characteristic curves for each grids. With the help of PCA processing and K-means algorithm, we analyze the similarities and differences of characteristic curves. Curves that have similar features will be classified into the same class and point cloud correspond to these curves will be classified as well. The whole process is simple but effective, and this approach does not need assistance of other data sources. In this study, point cloud data are classified into three classes, which are vegetation, buildings, and roads. When horizontal grid spacing and vertical layer spacing are 3 m and 1 m respectively, vertical characteristic is set as density, and the number of dimensions after PCA processing is 11, the overall precision of classification result is about 86.31 %. The result can help us quickly understand the distribution of various ground objects.

scholarly journals COMPARISON OF POINT AND SEGMENT BASED POINT CLOUD CLASSIFICATION METHOD IN URBAN SCENES

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 461-465
Author(s):  
E. Hasanpour ◽  
M. Saadatseresht ◽  
E. G. Parmehr
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Classification Method ◽  
Geometric Features ◽  
Classification Result ◽  
Urban Scenes ◽  
Cloud Data ◽  
Random Forest Classification ◽  
Cloud Classification ◽  
Point Cloud Classification

Abstract. Point cloud classification is an essential requirement for effectively utilizing point cloud data acquired by different kind of sources such as Terrestrial Laser Scanning (TLS), Aerial LiDAR (Light Detection and Ranging), and Photogrammetry. Classification of point cloud is a process that points are separated into different point groups that each group has similar features. Point cloud classification can be done in three levels (point-based, segment-based, and object-based) and the choice of different level has significant impact on classification result. In this research, random forest classification method is utilized in which the point-wise and segment-wise spectral and geometric features are selected as the input of the classification. In our experiments, the results of point- and segment-based classification were compared. In addition, point-wise classification result for two different features (geometric with/without spectral features) has been compared and the results are presented. The experiments illustrated that segment based classification with both color and geometric features has the best overall accuracy of 83% especially near the object boundaries.

scholarly journals Incorporating Handcrafted Features into Deep Learning for Point Cloud Classification

2020 ◽  
Vol 12 (22) ◽  
pp. 3713
Author(s):  
Pai-Hui Hsu ◽  
Zong-Yi Zhuang
Keyword(s):  
Deep Learning ◽  
Complex Network ◽  
Network Architecture ◽  
Point Cloud ◽  
Complex Model ◽  
Cloud Data ◽  
Cloud Classification ◽  
Deep Learning Network ◽  
Application Requirements ◽  
Point Cloud Classification

Point cloud classification is an important task in point cloud data analysis. Traditional point cloud classification is conducted primarily on the basis of specific handcrafted features with a specific classifier and is often capable of producing satisfactory results. However, the extraction of crucial handcrafted features hinges on sufficient knowledge of the field and substantial experience. In contrast, while powerful deep learning algorithms possess the ability to learn features automatically, it normally requires complex network architecture and a considerable amount of calculation time to attain better accuracy of classification. In order to combine the advantages of both the methods, in this study, we integrated the handcrafted features, whose benefits were confirmed by previous studies, into a deep learning network, in the hopes of solving the problem of insufficient extraction of specific features and enabling the network to recognise other effective features through automatic learning. This was done to achieve the performance of a complex model by using a simple model and fulfil the application requirements of the remote sensing domain. As indicated by the experimental results, the integration of handcrafted features into the simple and fast-calculating PointNet model could generate a classification result that bore comparison with that generated by a complex network model such as PointNet++ or KPConv.

Sign in / Sign up

Export Citation Format

Share Document