scholarly journals KVGCN: A KNN Searching and VLAD Combined Graph Convolutional Network for Point Cloud Segmentation

2021 ◽  
Vol 13 (5) ◽  
pp. 1003
Author(s):  
Nan Luo ◽  
Hongquan Yu ◽  
Zhenfeng Huo ◽  
Jinhui Liu ◽  
Quan Wang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Semantic Segmentation ◽  
K Nearest Neighbor ◽  
Topological Graph ◽  
Convolutional Network ◽  
Cloud Data ◽  
Nearest Neighbor Searching ◽  
Point Cloud Segmentation ◽  
Local Feature Extraction

Semantic segmentation of the sensed point cloud data plays a significant role in scene understanding and reconstruction, robot navigation, etc. This work presents a Graph Convolutional Network integrating K-Nearest Neighbor searching (KNN) and Vector of Locally Aggregated Descriptors (VLAD). KNN searching is utilized to construct the topological graph of each point and its neighbors. Then, we perform convolution on the edges of constructed graph to extract representative local features by multiple Multilayer Perceptions (MLPs). Afterwards, a trainable VLAD layer, NetVLAD, is embedded in the feature encoder to aggregate the local and global contextual features. The designed feature encoder is repeated for multiple times, and the extracted features are concatenated in a jump-connection style to strengthen the distinctiveness of features and thereby improve the segmentation. Experimental results on two datasets show that the proposed work settles the shortcoming of insufficient local feature extraction and promotes the accuracy (mIoU 60.9% and oAcc 87.4% for S3DIS) of semantic segmentation comparing to existing models.

scholarly journals NormNet: Point-wise normal estimation network for three-dimensional point cloud data

2019 ◽  
Vol 16 (4) ◽  
pp. 172988141985753 ◽  
Author(s):  
Janghun Hyeon ◽  
Weonsuk Lee ◽  
Joo Hyung Kim ◽  
Nakju Doh
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Three Dimensional ◽  
Local Feature ◽  
Data Sets ◽  
Point Cloud Data ◽  
K Nearest Neighbor ◽  
Cloud Data ◽  
Normal Estimation ◽  
Local Feature Extraction

In this article, a point-wise normal estimation network for three-dimensional point cloud data called NormNet is proposed. We propose the multiscale K-nearest neighbor convolution module for strengthened local feature extraction. With the multiscale K-nearest neighbor convolution module and PointNet-like architecture, we achieved a hybrid of three features: a global feature, a semantic feature from the segmentation network, and a local feature from the multiscale K-nearest neighbor convolution module. Those features, by mutually supporting each other, not only increase the normal estimation performance but also enable the estimation to be robust under severe noise perturbations or point deficiencies. The performance was validated in three different data sets: Synthetic CAD data (ModelNet), RGB-D sensor-based real 3D PCD (S3DIS), and LiDAR sensor-based real 3D PCD that we built and shared.

scholarly journals A GROSS ERROR ELIMINATION METHOD FOR POINT CLOUD DATA BASED ON KD-TREE

2018 ◽  
Vol XLII-3 ◽  
pp. 719-722 ◽  
Author(s):  
Q. Kang ◽  
G. Huang ◽  
S. Yang
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Target Point ◽  
Point Cloud Data ◽  
K Nearest Neighbor ◽  
Cloud Data ◽  
Gross Error ◽  
Error Elimination ◽  
K Nearest Neighbor Algorithm ◽  
Key Steps

Point cloud data has been one type of widely used data sources in the field of remote sensing. Key steps of point cloud data’s pro-processing focus on gross error elimination and quality control. Owing to the volume feature of point could data, existed gross error elimination methods need spend massive memory both in space and time. This paper employed a new method which based on Kd-tree algorithm to construct, k-nearest neighbor algorithm to search, settled appropriate threshold to determine with result turns out a judgement that whether target point is or not an outlier. Experimental results show that, our proposed algorithm will help to delete gross error in point cloud data and facilitate to decrease memory consumption, improve efficiency.

scholarly journals A Hybrid Spatial Indexing Structure of Massive Point Cloud Based on Octree and 3D R*-Tree

2021 ◽  
Vol 11 (20) ◽  
pp. 9581
Author(s):  
Wei Wang ◽  
Yi Zhang ◽  
Genyu Ge ◽  
Qin Jiang ◽  
Yang Wang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Nearest Neighbor Search ◽  
Index Structure ◽  
Spatial Indexing ◽  
Cloud Data ◽  
Neighbor Search ◽  
Nearest Neighbor Searching ◽  
Indexing Structure ◽  
Balanced Tree

The spatial index structure is one of the most important research topics for organizing and managing massive 3D Point Cloud. As a point in Point Cloud consists of Cartesian coordinates (x,y,z), the common method to explore geometric information and features is nearest neighbor searching. An efficient spatial indexing structure directly affects the speed of the nearest neighbor search. Octree and kd-tree are the most used for Point Cloud data. However, Octree or KD-tree do not perform best in nearest neighbor searching. A highly balanced tree, 3D R*-tree is considered the most effective method so far. So, a hybrid spatial indexing structure is proposed based on Octree and 3D R*-tree. In this paper, we discussed how thresholds influence the performance of nearest neighbor searching and constructing the tree. Finally, an adaptive way method adopted to set thresholds. Furthermore, we obtained a better performance in tree construction and nearest neighbor searching than Octree and 3D R*-tree.

scholarly journals PCA-Based Denoising Algorithm for Outdoor Lidar Point Cloud Data

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3703
Author(s):  
Dongyang Cheng ◽  
Dangjun Zhao ◽  
Junchao Zhang ◽  
Caisheng Wei ◽  
Di Tian
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Noise Removal ◽  
Normal Vector ◽  
Point Cloud Data ◽  
Optimization Strategy ◽  
K Nearest Neighbor ◽  
Cloud Data ◽  
Run Speed

Due to the complexity of surrounding environments, lidar point cloud data (PCD) are often degraded by plane noise. In order to eliminate noise, this paper proposes a filtering scheme based on the grid principal component analysis (PCA) technique and the ground splicing method. The 3D PCD is first projected onto a desired 2D plane, within which the ground and wall data are well separated from the PCD via a prescribed index based on the statistics of points in all 2D mesh grids. Then, a KD-tree is constructed for the ground data, and rough segmentation in an unsupervised method is conducted to obtain the true ground data by using the normal vector as a distinctive feature. To improve the performance of noise removal, we propose an elaborate K nearest neighbor (KNN)-based segmentation method via an optimization strategy. Finally, the denoised data of the wall and ground are spliced for further 3D reconstruction. The experimental results show that the proposed method is efficient at noise removal and is superior to several traditional methods in terms of both denoising performance and run speed.

scholarly journals Panicle-3D: Efficient Phenotyping Tool for Precise Semantic Segmentation of Rice Panicle Point Cloud

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Liang Gong ◽  
Xiaofeng Du ◽  
Kai Zhu ◽  
Ke Lin ◽  
Qiaojun Lou ◽  
...  
Keyword(s):  
Point Cloud ◽  
Network Models ◽  
Semantic Segmentation ◽  
Spatial Location ◽  
Point Clouds ◽  
Utilization Efficiency ◽  
Data Set ◽  
Cloud Data ◽  
Point Cloud Segmentation ◽  
Segmentation Accuracy

The automated measurement of crop phenotypic parameters is of great significance to the quantitative study of crop growth. The segmentation and classification of crop point cloud help to realize the automation of crop phenotypic parameter measurement. At present, crop spike-shaped point cloud segmentation has problems such as fewer samples, uneven distribution of point clouds, occlusion of stem and spike, disorderly arrangement of point clouds, and lack of targeted network models. The traditional clustering method can realize the segmentation of the plant organ point cloud with relatively independent spatial location, but the accuracy is not acceptable. This paper first builds a desktop-level point cloud scanning apparatus based on a structured-light projection module to facilitate the point cloud acquisition process. Then, the rice ear point cloud was collected, and the rice ear point cloud data set was made. In addition, data argumentation is used to improve sample utilization efficiency and training accuracy. Finally, a 3D point cloud convolutional neural network model called Panicle-3D was designed to achieve better segmentation accuracy. Specifically, the design of Panicle-3D is aimed at the multiscale characteristics of plant organs, combined with the structure of PointConv and long and short jumps, which accelerates the convergence speed of the network and reduces the loss of features in the process of point cloud downsampling. After comparison experiments, the segmentation accuracy of Panicle-3D reaches 93.4%, which is higher than PointNet. Panicle-3D is suitable for other similar crop point cloud segmentation tasks.

scholarly journals WEAKLY SUPERVISED PSEUDO-LABEL ASSISTED LEARNING FOR ALS POINT CLOUD SEMANTIC SEGMENTATION

2021 ◽  
Vol V-2-2021 ◽  
pp. 43-50
Author(s):  
P. Wang ◽  
W. Yao
Keyword(s):  
Point Cloud ◽  
Three Dimensional ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Training Data ◽  
Data Annotation ◽  
Cloud Data ◽  
Point Cloud Segmentation ◽  
Prediction Probability ◽  
Weakly Supervised

Abstract. Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus, obtaining accurate results with limited ground truth as training data is considerably important. As a simple and effective method, pseudo labels can use information from unlabeled data for training neural networks. In this study, we propose a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class. An adaptive thresholding strategy was proposed to generate a pseudo-label based on the prediction probability. Pseudo-label learning is an iterative process, and pseudo labels were updated solely on ground-truth weak labels as the model converged to improve the training efficiency. Experiments using the ISPRS 3D sematic labeling benchmark dataset indicated that our proposed method achieved an equally competitive result compared to that using a full supervision scheme with only up to 2‰ of labeled points from the original training set, with an overall accuracy of 83.7% and an average F1 score of 70.2%.

Substation Equipment 3D Identification Based on KNN Classification of Subspace Feature Vector

2017 ◽  
Vol 28 (5) ◽  
pp. 807-819 ◽  
Author(s):  
Weiying Guo ◽  
Yong Ji ◽  
Yong Luo ◽  
Yan Zhou
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Feature Vector ◽  
Identification Accuracy ◽  
K Nearest Neighbor ◽  
Positive Direction ◽  
Cloud Data ◽  
Knn Classification ◽  
Substation Equipment

Abstract Aiming to realize rapid and efficient three-dimensional (3D) identification of substation equipment, this article proposes a new method in which the 3D identification of substation equipment is based on K-nearest neighbor (KNN) classification of subspace feature vector. First of all, the article uses octree encoding to reduce and denoise the point cloud data obtained by a 3D laser scanner. Secondly, position calibration and size standardization are used for the point cloud after pretreatment. Then, the normalized point cloud is divided into a number of cubes with same size. The cosine of the angle between the positive direction of z axis and a vector from the global centroid of the point cloud to the centroid of each subspace is regarded as the feature of the subspace. All cosines of subspaces constitute the feature of the point cloud. Finally, we classify the subspace feature vector by using the KNN algorithm and improve classification accuracy by using the particle swarm optimization algorithm. The simulation results show that the identification accuracy of the proposed method for unknown substation equipment is about 90% and the proposed method is applicable to low-degree losses. Apparently, this method can accurately identify 3D substation equipment. At the same time, increasing the number of subspaces will improve the accuracy; however, it will increase the recognition time.

scholarly journals HOLE-FILLING ALGORITHM FOR AIRBORNE LIDAR POINT CLOUD DATA

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 739-745
Author(s):  
P. Liang ◽  
G. Q. Zhou ◽  
Y. L. Lu ◽  
X. Zhou ◽  
B. Song
Keyword(s):  
Boundary Point ◽  
Point Cloud ◽  
Nearest Neighbor ◽  
Nearest Neighbor Search ◽  
Airborne Lidar ◽  
Least Square ◽  
Point Cloud Data ◽  
K Nearest Neighbor ◽  
Cloud Data ◽  
Moving Least Square

Abstract. Due to the influence of the occlusion of objects or the complexity of the measured terrain in the scanning process of airborne lidar, the point cloud data inevitably appears holes after filtering and other processing. The incomplete data will inevitably have an impact on the quality of the reconstructed digital elevation model, so how to repair the incomplete point cloud data has become an urgent problem to be solved. To solve the problem of hole repair in point cloud data, a hole repair algorithm based on improved moving least square method is proposed in this paper by studying existing hole repair algorithms. Firstly, the algorithm extracts the boundary of the point cloud based on the triangular mesh model. Then we use k-nearest neighbor search to obtain the k-nearest neighbor points of the boundary point. Finally, according to the boundary point and its k-nearest neighbor point, the improved moving least squares method is used to fit the hole surface to realize the hole repair. Combined with C++ and MATLAB language, the feasibility of the algorithm is tested by specific application examples. The experimental results show that the algorithm can effectively repair the point cloud data holes, and the repairing precision is high. The filled hole area can be smoothly connected with the boundary.

scholarly journals Label3DMaize: toolkit for 3D point cloud data annotation of maize shoots

GigaScience ◽  
2021 ◽  
Vol 10 (5) ◽  
Author(s):  
Teng Miao ◽  
Weiliang Wen ◽  
Yinglun Li ◽  
Sheng Wu ◽  
Chao Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Training Dataset ◽  
Growth Stages ◽  
3D Point Cloud ◽  
Plant Structure ◽  
Data Annotation ◽  
Cloud Data ◽  
Point Cloud Segmentation ◽  
Different Growth Stages

Abstract Background The 3D point cloud is the most direct and effective data form for studying plant structure and morphology. In point cloud studies, the point cloud segmentation of individual plants to organs directly determines the accuracy of organ-level phenotype estimation and the reliability of the 3D plant reconstruction. However, highly accurate, automatic, and robust point cloud segmentation approaches for plants are unavailable. Thus, the high-throughput segmentation of many shoots is challenging. Although deep learning can feasibly solve this issue, software tools for 3D point cloud annotation to construct the training dataset are lacking. Results We propose a top-to-down point cloud segmentation algorithm using optimal transportation distance for maize shoots. We apply our point cloud annotation toolkit for maize shoots, Label3DMaize, to achieve semi-automatic point cloud segmentation and annotation of maize shoots at different growth stages, through a series of operations, including stem segmentation, coarse segmentation, fine segmentation, and sample-based segmentation. The toolkit takes ∼4–10 minutes to segment a maize shoot and consumes 10–20% of the total time if only coarse segmentation is required. Fine segmentation is more detailed than coarse segmentation, especially at the organ connection regions. The accuracy of coarse segmentation can reach 97.2% that of fine segmentation. Conclusion Label3DMaize integrates point cloud segmentation algorithms and manual interactive operations, realizing semi-automatic point cloud segmentation of maize shoots at different growth stages. The toolkit provides a practical data annotation tool for further online segmentation research based on deep learning and is expected to promote automatic point cloud processing of various plants.

scholarly journals PCT: Point cloud transformer

2021 ◽  
Vol 7 (2) ◽  
pp. 187-199
Author(s):  
Meng-Hao Guo ◽  
Jun-Xiong Cai ◽  
Zheng-Ning Liu ◽  
Tai-Jiang Mu ◽  
Ralph R. Martin ◽  
...  
Keyword(s):  
Language Processing ◽  
Point Cloud ◽  
Nearest Neighbor ◽  
Semantic Segmentation ◽  
Nearest Neighbor Search ◽  
Local Context ◽  
Irregular Domain ◽  
Cloud Processing ◽  
Neighbor Search ◽  
Farthest Point

AbstractThe irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer (PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing and displays great potential in image processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning. To better capture local context within the point cloud, we enhance input embedding with the support of farthest point sampling and nearest neighbor search. Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

Sign in / Sign up

Export Citation Format

Share Document