In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest
Producing accurate crop maps during the current growing season is essential for effective agricultural monitoring. Substantial efforts have been made to study regional crop distribution from year to year, but less attention is paid to the dynamics of composition and spatial extent of crops within a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/9/11/1184 |
| _version_ | 1819107493752602624 |
|---|---|
| author | Qian Song Qiong Hu Qingbo Zhou Ciara Hovis Mingtao Xiang Huajun Tang Wenbin Wu |
| author_facet | Qian Song Qiong Hu Qingbo Zhou Ciara Hovis Mingtao Xiang Huajun Tang Wenbin Wu |
| author_sort | Qian Song |
| collection | DOAJ |
| description | Producing accurate crop maps during the current growing season is essential for effective agricultural monitoring. Substantial efforts have been made to study regional crop distribution from year to year, but less attention is paid to the dynamics of composition and spatial extent of crops within a season. Understanding how crops are distributed at the early developing stages allows for the timely adjustment of crop planting structure as well as agricultural decision making and management. To address this knowledge gap, this study presents an approach integrating object-based image analysis with random forest (RF) for mapping in-season crop types based on multi-temporal GaoFen satellite data with a spatial resolution of 16 meters. A multiresolution local variance strategy was used to create crop objects, and then object-based spectral/textural features and vegetation indices were extracted from those objects. The RF classifier was employed to identify different crop types at four crop growth seasons by integrating available features. The crop classification performance of different seasons was assessed by calculating F-score values. Results show that crop maps derived using seasonal features achieved an overall accuracy of more than 87%. Compared to the use of spectral features, a feature combination of in-season textures and multi-temporal spectral and vegetation indices performs best when classifying crop types. Spectral and temporal information is more important than texture features for crop mapping. However, texture can be essential information when there is insufficient spectral and temporal information (e.g., crop identification in the early spring). These results indicate that an object-based image analysis combined with random forest has considerable potential for in-season crop mapping using high spatial resolution imagery. |
| first_indexed | 2024-12-22T02:54:55Z |
| format | Article |
| id | doaj.art-fa01de6487024607b8b183320dc14b3b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-22T02:54:55Z |
| publishDate | 2017-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-fa01de6487024607b8b183320dc14b3b2022-12-21T18:41:18ZengMDPI AGRemote Sensing2072-42922017-11-01911118410.3390/rs9111184rs9111184In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random ForestQian Song0Qiong Hu1Qingbo Zhou2Ciara Hovis3Mingtao Xiang4Huajun Tang5Wenbin Wu6Key Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaKey Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaKey Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaCenter for System Integration and Sustainability, Michigan State University, East Lansing, MI 48824, USAKey Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaKey Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaKey Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaProducing accurate crop maps during the current growing season is essential for effective agricultural monitoring. Substantial efforts have been made to study regional crop distribution from year to year, but less attention is paid to the dynamics of composition and spatial extent of crops within a season. Understanding how crops are distributed at the early developing stages allows for the timely adjustment of crop planting structure as well as agricultural decision making and management. To address this knowledge gap, this study presents an approach integrating object-based image analysis with random forest (RF) for mapping in-season crop types based on multi-temporal GaoFen satellite data with a spatial resolution of 16 meters. A multiresolution local variance strategy was used to create crop objects, and then object-based spectral/textural features and vegetation indices were extracted from those objects. The RF classifier was employed to identify different crop types at four crop growth seasons by integrating available features. The crop classification performance of different seasons was assessed by calculating F-score values. Results show that crop maps derived using seasonal features achieved an overall accuracy of more than 87%. Compared to the use of spectral features, a feature combination of in-season textures and multi-temporal spectral and vegetation indices performs best when classifying crop types. Spectral and temporal information is more important than texture features for crop mapping. However, texture can be essential information when there is insufficient spectral and temporal information (e.g., crop identification in the early spring). These results indicate that an object-based image analysis combined with random forest has considerable potential for in-season crop mapping using high spatial resolution imagery.https://www.mdpi.com/2072-4292/9/11/1184crop mappingin-seasonobject-based classificationRandom Forest |
| spellingShingle | Qian Song Qiong Hu Qingbo Zhou Ciara Hovis Mingtao Xiang Huajun Tang Wenbin Wu In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest Remote Sensing crop mapping in-season object-based classification Random Forest |
| title | In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest |
| title_full | In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest |
| title_fullStr | In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest |
| title_full_unstemmed | In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest |
| title_short | In-Season Crop Mapping with GF-1/WFV Data by Combining Object-Based Image Analysis and Random Forest |
| title_sort | in season crop mapping with gf 1 wfv data by combining object based image analysis and random forest |
| topic | crop mapping in-season object-based classification Random Forest |
| url | https://www.mdpi.com/2072-4292/9/11/1184 |
| work_keys_str_mv | AT qiansong inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest AT qionghu inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest AT qingbozhou inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest AT ciarahovis inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest AT mingtaoxiang inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest AT huajuntang inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest AT wenbinwu inseasoncropmappingwithgf1wfvdatabycombiningobjectbasedimageanalysisandrandomforest |