Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information
Airborne laser scanning (ALS) can acquire both geometry and intensity information of geo-objects, which is important in mapping a large-scale three-dimensional (3D) urban environment. However, the intensity information recorded by ALS will be changed due to the flight height and atmospheric attenuat...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/20/4583 |
| _version_ | 1798039010862432256 |
|---|---|
| author | Xiaoqiang Liu Yanming Chen Shuyi Li Liang Cheng Manchun Li |
| author_facet | Xiaoqiang Liu Yanming Chen Shuyi Li Liang Cheng Manchun Li |
| author_sort | Xiaoqiang Liu |
| collection | DOAJ |
| description | Airborne laser scanning (ALS) can acquire both geometry and intensity information of geo-objects, which is important in mapping a large-scale three-dimensional (3D) urban environment. However, the intensity information recorded by ALS will be changed due to the flight height and atmospheric attenuation, which decreases the robustness of the trained supervised classifier. This paper proposes a hierarchical classification method by separately using geometry and intensity information of urban ALS data. The method uses supervised learning for stable geometry information and unsupervised learning for fluctuating intensity information. The experiment results show that the proposed method can utilize the intensity information effectively, based on three aspects, as below. (1) The proposed method improves the accuracy of classification result by using intensity. (2) When the ALS data to be classified are acquired under the same conditions as the training data, the performance of the proposed method is as good as the supervised learning method. (3) When the ALS data to be classified are acquired under different conditions from the training data, the performance of the proposed method is better than the supervised learning method. Therefore, the classification model derived from the proposed method can be transferred to other ALS data whose intensity is inconsistent with the training data. Furthermore, the proposed method can contribute to the hierarchical use of some other ALS information, such as multi-spectral information. |
| first_indexed | 2024-04-11T21:48:02Z |
| format | Article |
| id | doaj.art-c2861fc76e8f42079d6421a55dea73b8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:48:02Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c2861fc76e8f42079d6421a55dea73b82022-12-22T04:01:21ZengMDPI AGSensors1424-82202019-10-011920458310.3390/s19204583s19204583Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity InformationXiaoqiang Liu0Yanming Chen1Shuyi Li2Liang Cheng3Manchun Li4School of Geography and Ocean Science, Nanjing University, Nanjing 210093, ChinaSchool of Geography and Ocean Science, Nanjing University, Nanjing 210093, ChinaSchool of Geography and Ocean Science, Nanjing University, Nanjing 210093, ChinaSchool of Geography and Ocean Science, Nanjing University, Nanjing 210093, ChinaSchool of Geography and Ocean Science, Nanjing University, Nanjing 210093, ChinaAirborne laser scanning (ALS) can acquire both geometry and intensity information of geo-objects, which is important in mapping a large-scale three-dimensional (3D) urban environment. However, the intensity information recorded by ALS will be changed due to the flight height and atmospheric attenuation, which decreases the robustness of the trained supervised classifier. This paper proposes a hierarchical classification method by separately using geometry and intensity information of urban ALS data. The method uses supervised learning for stable geometry information and unsupervised learning for fluctuating intensity information. The experiment results show that the proposed method can utilize the intensity information effectively, based on three aspects, as below. (1) The proposed method improves the accuracy of classification result by using intensity. (2) When the ALS data to be classified are acquired under the same conditions as the training data, the performance of the proposed method is as good as the supervised learning method. (3) When the ALS data to be classified are acquired under different conditions from the training data, the performance of the proposed method is better than the supervised learning method. Therefore, the classification model derived from the proposed method can be transferred to other ALS data whose intensity is inconsistent with the training data. Furthermore, the proposed method can contribute to the hierarchical use of some other ALS information, such as multi-spectral information.https://www.mdpi.com/1424-8220/19/20/4583airborne laser scanninghierarchical classificationintensitygeometrysupervised learningunsupervised learning |
| spellingShingle | Xiaoqiang Liu Yanming Chen Shuyi Li Liang Cheng Manchun Li Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information Sensors airborne laser scanning hierarchical classification intensity geometry supervised learning unsupervised learning |
| title | Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information |
| title_full | Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information |
| title_fullStr | Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information |
| title_full_unstemmed | Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information |
| title_short | Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information |
| title_sort | hierarchical classification of urban als data by using geometry and intensity information |
| topic | airborne laser scanning hierarchical classification intensity geometry supervised learning unsupervised learning |
| url | https://www.mdpi.com/1424-8220/19/20/4583 |
| work_keys_str_mv | AT xiaoqiangliu hierarchicalclassificationofurbanalsdatabyusinggeometryandintensityinformation AT yanmingchen hierarchicalclassificationofurbanalsdatabyusinggeometryandintensityinformation AT shuyili hierarchicalclassificationofurbanalsdatabyusinggeometryandintensityinformation AT liangcheng hierarchicalclassificationofurbanalsdatabyusinggeometryandintensityinformation AT manchunli hierarchicalclassificationofurbanalsdatabyusinggeometryandintensityinformation |