Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing
Roadway area calculation is a novel problem in remote sensing and urban planning. This paper models this problem as a two-step problem, roadway extraction, and area calculation. Roadway extraction from satellite images is a problem that has been tackled many times before. This paper proposes a metho...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/8/5/124 |
| _version_ | 1797498838410330112 |
|---|---|
| author | Varun Yerram Hiroyuki Takeshita Yuji Iwahori Yoshitsugu Hayashi M. K. Bhuyan Shinji Fukui Boonserm Kijsirikul Aili Wang |
| author_facet | Varun Yerram Hiroyuki Takeshita Yuji Iwahori Yoshitsugu Hayashi M. K. Bhuyan Shinji Fukui Boonserm Kijsirikul Aili Wang |
| author_sort | Varun Yerram |
| collection | DOAJ |
| description | Roadway area calculation is a novel problem in remote sensing and urban planning. This paper models this problem as a two-step problem, roadway extraction, and area calculation. Roadway extraction from satellite images is a problem that has been tackled many times before. This paper proposes a method using pixel resolution to calculate the area of the roads covered in satellite images. The proposed approach uses novel U-net and Resnet architectures called U-net++ and ResNeXt. The state-of-the-art model is combined with the proposed efficient post-processing approach to improve the overlap with ground truth labels. The performance of the proposed road extraction algorithm is evaluated on the Massachusetts dataset and it is shown that the proposed approach outperforms the existing solutions which use models from the U-net family. |
| first_indexed | 2024-03-10T03:39:05Z |
| format | Article |
| id | doaj.art-d9c7762269ec490ba23aabc0bfdb040c |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T03:39:05Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-d9c7762269ec490ba23aabc0bfdb040c2023-11-23T11:37:59ZengMDPI AGJournal of Imaging2313-433X2022-04-018512410.3390/jimaging8050124Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-ProcessingVarun Yerram0Hiroyuki Takeshita1Yuji Iwahori2Yoshitsugu Hayashi3M. K. Bhuyan4Shinji Fukui5Boonserm Kijsirikul6Aili Wang7Department of Electronics & Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, IndiaGraduate School of Engineering, Chubu University, Kasugai 487-8501, JapanGraduate School of Engineering, Chubu University, Kasugai 487-8501, JapanGraduate School of Engineering, Chubu University, Kasugai 487-8501, JapanDepartment of Electronics & Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati 781039, IndiaDepartment of Information Education, Aichi University of Education, Kariya 448-8542, JapanDepartment of Computer Engineering, Chulalongkorn University, Bangkok 10330, ThailandHigher Educational Key Laboratory for Measuring and Control Technology and Instrumentations of Heilongjiang, Harbin University of Science and Technology, Harbin 150080, ChinaRoadway area calculation is a novel problem in remote sensing and urban planning. This paper models this problem as a two-step problem, roadway extraction, and area calculation. Roadway extraction from satellite images is a problem that has been tackled many times before. This paper proposes a method using pixel resolution to calculate the area of the roads covered in satellite images. The proposed approach uses novel U-net and Resnet architectures called U-net++ and ResNeXt. The state-of-the-art model is combined with the proposed efficient post-processing approach to improve the overlap with ground truth labels. The performance of the proposed road extraction algorithm is evaluated on the Massachusetts dataset and it is shown that the proposed approach outperforms the existing solutions which use models from the U-net family.https://www.mdpi.com/2313-433X/8/5/124roadway extractionarea calculationsatellite imagesU-net++ResNeXtPix2Pix |
| spellingShingle | Varun Yerram Hiroyuki Takeshita Yuji Iwahori Yoshitsugu Hayashi M. K. Bhuyan Shinji Fukui Boonserm Kijsirikul Aili Wang Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing Journal of Imaging roadway extraction area calculation satellite images U-net++ ResNeXt Pix2Pix |
| title | Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing |
| title_full | Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing |
| title_fullStr | Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing |
| title_full_unstemmed | Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing |
| title_short | Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing |
| title_sort | extraction and calculation of roadway area from satellite images using improved deep learning model and post processing |
| topic | roadway extraction area calculation satellite images U-net++ ResNeXt Pix2Pix |
| url | https://www.mdpi.com/2313-433X/8/5/124 |
| work_keys_str_mv | AT varunyerram extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT hiroyukitakeshita extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT yujiiwahori extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT yoshitsuguhayashi extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT mkbhuyan extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT shinjifukui extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT boonsermkijsirikul extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing AT ailiwang extractionandcalculationofroadwayareafromsatelliteimagesusingimproveddeeplearningmodelandpostprocessing |