Agricultural Field Boundary Delineation with Satellite Image Segmentation for High-Resolution Crop Mapping: A Case Study of Rice Paddy
Open Access
- 28 September 2022
- Vol. 12 (10) , 2342
Abstract
Parcel-level cropland maps are an essential data source for crop yield estimation, precision agriculture, and many other agronomy applications. Here, we proposed a rice field mapping approach that combines agricultural field boundary extraction with fine-resolution satellite images and pixel-wise cropland classification with Sentinel-1 time series SAR (Synthetic Aperture Radar) imagery. The agricultural field boundaries were delineated by image segmentation using U-net-based fully convolutional network (FCN) models. Meanwhile, a simple decision-tree classifier was developed based on rice phenology traits to extract rice pixels with time series SAR imagery. Agricultural fields were then classified as rice or non-rice by majority voting from pixel-wise classification results. The evaluation indicated that SeresNet34, as the backbone of the U-net model, had the best performance in agricultural field extraction with an IoU (Intersection over Union) of 0.801 compared to the simple U-net and ResNet-based U-net. The combination of agricultural field maps with the rice pixel detection model showed promising improvement in the accuracy and resolution of rice mapping. The produced rice field map had an IoU score of 0.953, while the User‘s Accuracy and Producer‘s Accuracy of pixel-wise rice field mapping were 0.824 and 0.816, respectively. The proposed model combination scheme merely requires a simple pixel-wise cropland classification model that incorporates the agricultural field mapping results to produce high-accuracy and high-resolution cropland maps.Keywords
Funding Information
- Central Public-Interest Scientific Institution Basal Research Fund of China (Y2022PT07, JBYW-AII-2022-33, CAAS-ASTIP-2016-AII)
- Basal Research Fund of AII CAAS (Y2022PT07, JBYW-AII-2022-33, CAAS-ASTIP-2016-AII)
- Science and Technology Innovation Project of CAAS (Y2022PT07, JBYW-AII-2022-33, CAAS-ASTIP-2016-AII)
This publication has 45 references indexed in Scilit:
- Mapping rice extent and cropping scheme in the Mekong Delta using Sentinel-1A dataRemote Sensing Letters, 2016
- Paddy-Rice Phenology Classification Based on Machine-Learning Methods Using Multitemporal Co-Polar X-Band SAR ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Object-Based Crop Classification with Landsat-MODIS Enhanced Time-Series DataRemote Sensing, 2015
- Automated annual cropland mapping using knowledge-based temporal featuresISPRS Journal of Photogrammetry and Remote Sensing, 2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Object-Based Crop Species Classification Based on the Combination of Airborne Hyperspectral Images and LiDAR DataRemote Sensing, 2015
- Object-Based Image Classification of Summer Crops with Machine Learning MethodsRemote Sensing, 2014
- Object-based crop identification using multiple vegetation indices, textural features and crop phenologyRemote Sensing of Environment, 2011
- An Edge Embedded Marker-Based Watershed Algorithm for High Spatial Resolution Remote Sensing Image SegmentationIEEE Transactions on Image Processing, 2010
- A neural network integrated approach for rice crop monitoringInternational Journal of Remote Sensing, 2006