Segmentation-based classification for 3D urban point clouds

Xiang, Binbin; Yao, Jian; Lu, Xin; Li, Li; Xie, Rong

doi:10.1109/icinfa.2016.7831817

Cited by 14 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Naive Bayes: Assumes an independent normal distribution across each feature. It is possible to calculate the probability of a feature vector belonging to a class using the variance across each feature [15,20,[38][39][40][41]. 3.…”

Section: Traditional Classification Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Extending Convolution to Semantic Segmentation with Graph Neural Networks

Armstrong,

Grobler

2023

Preprint

View full text Add to dashboard Cite

Scene understanding enables multiple applications such as robotic automation. To enable scene understanding, semantic segmentation is an essential component. Highly accurate per-voxel semantic labels can efficiently be obtained through the use of encoder-decoder Convolutional Neural Networks (CNNs). However, scene understanding requires instances of objects to be discovered in a scene. Per-voxel labelling is unable to distinguish between separate instances of a given object. A novel method is proposed that enables segment-level predictions to be formed from the voxel-level predictions provided by the CNN architecture. This method uses an existing 3D CNN architecture to provide rich and computationally inexpensive features. The scene is then segmented with a graph-based segmentation technique to identify objects in the scene. Finally, a graph-based neural network is used to capture hierarchical information improving overall accuracy. The approach is tested on the S3DIS and ScanNet datasets to provide a comparable baseline to more modern architectures.

show abstract

Section: Traditional Classification Approachesmentioning

confidence: 99%

“…Support Vector Machine: SVMs attempt to find the line that creates the largest separation between two classes. SVMs can be adapted to handle non-linear boundaries with the use of a radial basis function [15,25,26,28,39,[42][43][44][45][46][47][48][49][50][51][52][53]. 4.…”

Section: Traditional Classification Approachesmentioning

confidence: 99%

Extending Convolution to Semantic Segmentation with Graph Neural Networks

Armstrong,

Grobler

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Compared with the single point-based classification, point set-based method can better express the topological relationships among points and point sets, facilitating to improve classification accuracy. For example, Xiang et al [39] construct adjacency relationships of each point according to the normal information. Then large segmented blocks can be built, and support vector machine (SVM) is used to finalize point cloud classification of urban road scenes.…”

Section: B Semantic Segmentation Algorithmsmentioning

confidence: 99%

CSPC-Dataset: New LiDAR Point Cloud Dataset and Benchmark for Large-Scale Scene Semantic Segmentation

Tong

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Large-scale point clouds scanned by light detection and ranging (lidar) sensors provide detailed geometric characteristics of scenes due to the provision of 3D structural data. The semantic segmentation of large-scale point clouds is a crucial step for an in-depth understanding of complex scenes. Of late, although a large number of point cloud semantic segmentation algorithms have been proposed, semantic segmentation methods are still far from being satisfactory in terms of precision and accuracy of large-scale point clouds. For machine learning (ML) and deep learning (DL) methodologies, the semantic segmentation is largely influenced by the quality of training sets and methods themselves. Therefore, we construct a new point cloud dataset, namely CSPC-Dataset (Complex Scene Point Cloud Dataset) for large-scale scene semantic segmentation. CSPC-Dataset point clouds are acquired by a wearable laser mobile mapping robot. It covers five complex urban and rural scenes and mainly includes six types of objects, i.e., ground, car, building, vegetation, bridge, and pole. It provides large-scale outdoor scenes with color information, which has advantages such as the scene more complete, point density relatively uniform, diversity and complexity of objects and the high discrepancy between different scenes. Based on the CSPC-Dataset, we construct a new benchmark, which includes approximately 68 million points with explicit semantic labels. To extend the dataset into a wide range of applications, this paper provides the semantic segmentation results and comparative analysis of 7 baseline methods based on CSPC-Dataset. In the experiment part, three groups of experiments are conducted for benchmarking, which offers an effective way to make comparisons with different point-labeling algorithms. The labeling results have shown that the highest Intersection over Union (IoU) of pole, ground, building, car, vegetation, and bridge for all benchmarks is 36.0%, 97.8%,

show abstract

“…Recently, the application of light detection and ranging (LiDAR) has become more widespread in autonomous navigation systems [1][2][3][4][5][6][7] and three-dimensional (3D) environment reconstruction systems. [8][9][10][11][12] In both areas, clustering as a preprocessing step of 3D point clouds is very important because it directly affects the accuracy of object classification and dynamic object detection. In autonomous navigation systems, the vehicle must detect objects on the street, such as pedestrians, moving vehicles, and other obstacles, to avoid accidents.…”

Section: Introductionmentioning

confidence: 99%

“…[8][9][10][11][12] In both areas, clustering as a preprocessing step of 3D point clouds is very important because it directly affects the accuracy of object classification and dynamic object detection. In autonomous navigation systems, the vehicle must detect objects on the street, such as pedestrians, moving vehicles, and other obstacles, to avoid accidents.…”

Section: Introductionmentioning

confidence: 99%

Range image-based density-based spatial clustering of application with noise clustering method of three-dimensional point clouds

Wen

Cho

Chae

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Clustering plays an important role in processing light detection and ranging points in the autonomous perception tasks of robots. Clustering usually occurs near the start of processing three-dimensional point clouds obtained from light detection and ranging for detection and classification. Therefore, errors caused by clustering will directly affect the detection and classification accuracy. In this article, a clustering method is presented that combines density-based spatial clustering of application with noise and two-dimensional range image composed by scan lines of light detection and ranging based on the order of generation time. The results show that the proposed method achieves state-of-the-art performance in aspect of time efficiency and clustering accuracy. A ground extraction method based on scan line is also presented in this article, which has strong ability to separate ground points and non-ground points.

show abstract

Segmentation-based classification for 3D urban point clouds

Cited by 14 publications

References 15 publications

Extending Convolution to Semantic Segmentation with Graph Neural Networks

Extending Convolution to Semantic Segmentation with Graph Neural Networks

CSPC-Dataset: New LiDAR Point Cloud Dataset and Benchmark for Large-Scale Scene Semantic Segmentation

Range image-based density-based spatial clustering of application with noise clustering method of three-dimensional point clouds

Contact Info

Product

Resources

About