Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning
Accurate and up-to-date road network information is very important for the Geographic Information System (GIS) database, traffic management and planning, automatic vehicle navigation, emergency response and urban pollution sources investigation. In this paper, we use vector field learning to extract...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/9/3152 |
| _version_ | 1797535417301467136 |
|---|---|
| author | Peng Liang Wenzhong Shi Yixing Ding Zhiqiang Liu Haolv Shang |
| author_facet | Peng Liang Wenzhong Shi Yixing Ding Zhiqiang Liu Haolv Shang |
| author_sort | Peng Liang |
| collection | DOAJ |
| description | Accurate and up-to-date road network information is very important for the Geographic Information System (GIS) database, traffic management and planning, automatic vehicle navigation, emergency response and urban pollution sources investigation. In this paper, we use vector field learning to extract roads from high resolution remote sensing imaging. This method is usually used for skeleton extraction in nature image, but seldom used in road extraction. In order to improve the accuracy of road extraction, three vector fields are constructed and combined respectively with the normal road mask learning by a two-task network. The results show that all the vector fields are able to significantly improve the accuracy of road extraction, no matter the field is constructed in the road area or completely outside the road. The highest F1 score is 0.7618, increased by 0.053 compared with using only mask learning. |
| first_indexed | 2024-03-10T11:45:08Z |
| format | Article |
| id | doaj.art-4dfe7dbfa0834ed289324ee08a478b35 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T11:45:08Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4dfe7dbfa0834ed289324ee08a478b352023-11-21T18:09:34ZengMDPI AGSensors1424-82202021-05-01219315210.3390/s21093152Road Extraction from High Resolution Remote Sensing Images Based on Vector Field LearningPeng Liang0Wenzhong Shi1Yixing Ding2Zhiqiang Liu3Haolv Shang4School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430072, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaPiesat Information Technology Co., Ltd., Beijing 100195, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAccurate and up-to-date road network information is very important for the Geographic Information System (GIS) database, traffic management and planning, automatic vehicle navigation, emergency response and urban pollution sources investigation. In this paper, we use vector field learning to extract roads from high resolution remote sensing imaging. This method is usually used for skeleton extraction in nature image, but seldom used in road extraction. In order to improve the accuracy of road extraction, three vector fields are constructed and combined respectively with the normal road mask learning by a two-task network. The results show that all the vector fields are able to significantly improve the accuracy of road extraction, no matter the field is constructed in the road area or completely outside the road. The highest F1 score is 0.7618, increased by 0.053 compared with using only mask learning.https://www.mdpi.com/1424-8220/21/9/3152road extractionvector field learninghigh resolution remote sensing imageencoder-decoderDCNN |
| spellingShingle | Peng Liang Wenzhong Shi Yixing Ding Zhiqiang Liu Haolv Shang Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning Sensors road extraction vector field learning high resolution remote sensing image encoder-decoder DCNN |
| title | Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning |
| title_full | Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning |
| title_fullStr | Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning |
| title_full_unstemmed | Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning |
| title_short | Road Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning |
| title_sort | road extraction from high resolution remote sensing images based on vector field learning |
| topic | road extraction vector field learning high resolution remote sensing image encoder-decoder DCNN |
| url | https://www.mdpi.com/1424-8220/21/9/3152 |
| work_keys_str_mv | AT pengliang roadextractionfromhighresolutionremotesensingimagesbasedonvectorfieldlearning AT wenzhongshi roadextractionfromhighresolutionremotesensingimagesbasedonvectorfieldlearning AT yixingding roadextractionfromhighresolutionremotesensingimagesbasedonvectorfieldlearning AT zhiqiangliu roadextractionfromhighresolutionremotesensingimagesbasedonvectorfieldlearning AT haolvshang roadextractionfromhighresolutionremotesensingimagesbasedonvectorfieldlearning |