Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data
Power lines classification is important for electric power management and geographical objects extraction using LiDAR (light detection and ranging) point cloud data. Many supervised classification approaches have been introduced for the extraction of features such as ground, trees, and buildings, an...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/10/8/1222 |
| _version_ | 1798031510268280832 |
|---|---|
| author | Yanjun Wang Qi Chen Lin Liu Xiong Li Arun Kumar Sangaiah Kai Li |
| author_facet | Yanjun Wang Qi Chen Lin Liu Xiong Li Arun Kumar Sangaiah Kai Li |
| author_sort | Yanjun Wang |
| collection | DOAJ |
| description | Power lines classification is important for electric power management and geographical objects extraction using LiDAR (light detection and ranging) point cloud data. Many supervised classification approaches have been introduced for the extraction of features such as ground, trees, and buildings, and several studies have been conducted to evaluate the framework and performance of such supervised classification methods in power lines applications. However, these studies did not systematically investigate all of the relevant factors affecting the classification results, including the segmentation scale, feature selection, classifier variety, and scene complexity. In this study, we examined these factors systematically using airborne laser scanning and mobile laser scanning point cloud data. Our results indicated that random forest and neural network were highly suitable for power lines classification in forest, suburban, and urban areas in terms of the precision, recall, and quality rates of the classification results. In contrast to some previous studies, random forest yielded the best results, while Naïve Bayes was the worst classifier in most cases. Random forest was the more robust classifier with or without feature selection for various LiDAR point cloud data. Furthermore, the classification accuracies were directly related to the selection of the local neighborhood, classifier, and feature set. Finally, it was suggested that random forest should be considered in most cases for power line classification. |
| first_indexed | 2024-04-11T19:58:39Z |
| format | Article |
| id | doaj.art-f55750661e364d43aea210af3d690d9e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T19:58:39Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f55750661e364d43aea210af3d690d9e2022-12-22T04:05:53ZengMDPI AGRemote Sensing2072-42922018-08-01108122210.3390/rs10081222rs10081222Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud DataYanjun Wang0Qi Chen1Lin Liu2Xiong Li3Arun Kumar Sangaiah4Kai Li5National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology, Hunan University of Science and Technology, No.1 Taoyuan Road, Xiangtan 411201, ChinaDepartment of Geography and Environment, University of Hawaii at Mānoa, 2424 Maile Way, Honolulu, HI 96822, USADepartment of Geography, University of Cincinnati, Braunstein Hall, 400E, Cincinnati, OH 45221, USASchool of Computer Science and Engineering, Hunan University of Science and Technology, No. 1 Taoyuan Road, Xiangtan 411201, ChinaSchool of Computing Science and Engineering, Vellore Institute of Technology (VIT), Vellore-632014, IndiaNational-Local Joint Engineering Laboratory of Geo-Spatial Information Technology, Hunan University of Science and Technology, No.1 Taoyuan Road, Xiangtan 411201, ChinaPower lines classification is important for electric power management and geographical objects extraction using LiDAR (light detection and ranging) point cloud data. Many supervised classification approaches have been introduced for the extraction of features such as ground, trees, and buildings, and several studies have been conducted to evaluate the framework and performance of such supervised classification methods in power lines applications. However, these studies did not systematically investigate all of the relevant factors affecting the classification results, including the segmentation scale, feature selection, classifier variety, and scene complexity. In this study, we examined these factors systematically using airborne laser scanning and mobile laser scanning point cloud data. Our results indicated that random forest and neural network were highly suitable for power lines classification in forest, suburban, and urban areas in terms of the precision, recall, and quality rates of the classification results. In contrast to some previous studies, random forest yielded the best results, while Naïve Bayes was the worst classifier in most cases. Random forest was the more robust classifier with or without feature selection for various LiDAR point cloud data. Furthermore, the classification accuracies were directly related to the selection of the local neighborhood, classifier, and feature set. Finally, it was suggested that random forest should be considered in most cases for power line classification.http://www.mdpi.com/2072-4292/10/8/1222laser scanning datapower line classificationrandom forestfeature selectionclassifier |
| spellingShingle | Yanjun Wang Qi Chen Lin Liu Xiong Li Arun Kumar Sangaiah Kai Li Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data Remote Sensing laser scanning data power line classification random forest feature selection classifier |
| title | Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data |
| title_full | Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data |
| title_fullStr | Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data |
| title_full_unstemmed | Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data |
| title_short | Systematic Comparison of Power Line Classification Methods from ALS and MLS Point Cloud Data |
| title_sort | systematic comparison of power line classification methods from als and mls point cloud data |
| topic | laser scanning data power line classification random forest feature selection classifier |
| url | http://www.mdpi.com/2072-4292/10/8/1222 |
| work_keys_str_mv | AT yanjunwang systematiccomparisonofpowerlineclassificationmethodsfromalsandmlspointclouddata AT qichen systematiccomparisonofpowerlineclassificationmethodsfromalsandmlspointclouddata AT linliu systematiccomparisonofpowerlineclassificationmethodsfromalsandmlspointclouddata AT xiongli systematiccomparisonofpowerlineclassificationmethodsfromalsandmlspointclouddata AT arunkumarsangaiah systematiccomparisonofpowerlineclassificationmethodsfromalsandmlspointclouddata AT kaili systematiccomparisonofpowerlineclassificationmethodsfromalsandmlspointclouddata |