A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes
With the quick development of mobile light detection and ranging (LiDAR) systems, point clouds are frequently applied for various large-scale outdoor scenes. It is fundamental to quickly and accurately classify objects of mobile laser scanning (MLS) point clouds in such urban scene applications. How...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10325490/ |
| _version_ | 1797401002275504128 |
|---|---|
| author | Mingxue Zheng Xiangcheng Shen Zhiqing Luo Pingting Chen Bo Guan Jicheng Yi Hairong Ma |
| author_facet | Mingxue Zheng Xiangcheng Shen Zhiqing Luo Pingting Chen Bo Guan Jicheng Yi Hairong Ma |
| author_sort | Mingxue Zheng |
| collection | DOAJ |
| description | With the quick development of mobile light detection and ranging (LiDAR) systems, point clouds are frequently applied for various large-scale outdoor scenes. It is fundamental to quickly and accurately classify objects of mobile laser scanning (MLS) point clouds in such urban scene applications. However, an important problem is the need for massive training samples in object classification. High computational cost is also a common challenge. To overcome them, a knowledge-based multi-scale adaptive classification approach (KMAC) is proposed in the paper. The method consisting of four layers derives from a normal neural network framework, the operation in part layers differ. As the scale difference of various objects in natural environment, 3D multi-scale spatial local relation of objects is explored with inspiration by the idea of convolution. Two types of distinguishable features of actual objects are explored to describe 3D point clouds by a 2D vector representation. Then, human knowledge is used to directly build an end-to-end match between these feature descriptions in 2D and 3D point clouds of actual objects. Point clouds which are adjacent with the same feature representation would be intentionally integrated into multiple adaptive regions. The adaptive integration solves scale difference of various objects. The direct match by knowledge exactly plays the role of training samples. Qualitative and quantitative experimental results on three data-sets finally show the proposed approach is promising to efficiently classify unlabeled objects in urban scenes. |
| first_indexed | 2024-03-09T02:03:36Z |
| format | Article |
| id | doaj.art-3cb0ed5eb66f4f20a069806644a13a28 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-09T02:03:36Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3cb0ed5eb66f4f20a069806644a13a282023-12-08T00:06:05ZengIEEEIEEE Access2169-35362023-01-011113453113454610.1109/ACCESS.2023.333560710325490A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban ScenesMingxue Zheng0https://orcid.org/0000-0001-9791-5634Xiangcheng Shen1Zhiqing Luo2Pingting Chen3Bo Guan4Jicheng Yi5Hairong Ma6https://orcid.org/0000-0002-6335-3087Institute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaInstitute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaInstitute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaInstitute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaInstitute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaInstitute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaInstitute of Agricultural Economy and Technology, Hubei Academy of Agricultural Sciences, Wuhan, ChinaWith the quick development of mobile light detection and ranging (LiDAR) systems, point clouds are frequently applied for various large-scale outdoor scenes. It is fundamental to quickly and accurately classify objects of mobile laser scanning (MLS) point clouds in such urban scene applications. However, an important problem is the need for massive training samples in object classification. High computational cost is also a common challenge. To overcome them, a knowledge-based multi-scale adaptive classification approach (KMAC) is proposed in the paper. The method consisting of four layers derives from a normal neural network framework, the operation in part layers differ. As the scale difference of various objects in natural environment, 3D multi-scale spatial local relation of objects is explored with inspiration by the idea of convolution. Two types of distinguishable features of actual objects are explored to describe 3D point clouds by a 2D vector representation. Then, human knowledge is used to directly build an end-to-end match between these feature descriptions in 2D and 3D point clouds of actual objects. Point clouds which are adjacent with the same feature representation would be intentionally integrated into multiple adaptive regions. The adaptive integration solves scale difference of various objects. The direct match by knowledge exactly plays the role of training samples. Qualitative and quantitative experimental results on three data-sets finally show the proposed approach is promising to efficiently classify unlabeled objects in urban scenes.https://ieeexplore.ieee.org/document/10325490/Geometrical Eigen-featuresadaptivemulti-scaleknowledgeclassificationMLS point cloud |
| spellingShingle | Mingxue Zheng Xiangcheng Shen Zhiqing Luo Pingting Chen Bo Guan Jicheng Yi Hairong Ma A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes IEEE Access Geometrical Eigen-features adaptive multi-scale knowledge classification MLS point cloud |
| title | A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes |
| title_full | A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes |
| title_fullStr | A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes |
| title_full_unstemmed | A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes |
| title_short | A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes |
| title_sort | knowledge based multi scale adaptive classification approach for mobile laser scanning point clouds in urban scenes |
| topic | Geometrical Eigen-features adaptive multi-scale knowledge classification MLS point cloud |
| url | https://ieeexplore.ieee.org/document/10325490/ |
| work_keys_str_mv | AT mingxuezheng aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT xiangchengshen aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT zhiqingluo aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT pingtingchen aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT boguan aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT jichengyi aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT hairongma aknowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT mingxuezheng knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT xiangchengshen knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT zhiqingluo knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT pingtingchen knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT boguan knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT jichengyi knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes AT hairongma knowledgebasedmultiscaleadaptiveclassificationapproachformobilelaserscanningpointcloudsinurbanscenes |