A Method for Cropland Layer Extraction in Complex Scenes Integrating Edge Features and Semantic Segmentation
Open Access
- 8 September 2024
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 14 (9) , 1553
Abstract
Cultivated land is crucial for food production and security. In complex environments like mountainous regions, the fragmented nature of the cultivated land complicates rapid and accurate information acquisition. Deep learning has become essential for extracting cultivated land but faces challenges such as edge detail loss and limited adaptability. This study introduces a novel approach that combines geographical zonal stratification with the temporal characteristics of medium-resolution remote sensing images for identifying cultivated land. The methodology involves geographically zoning and stratifying the study area, and then integrating semantic segmentation and edge detection to analyze remote sensing images and generate initial extraction results. These results are refined through post-processing with medium-resolution imagery classification to produce a detailed map of the cultivated land distribution. The method achieved an overall extraction accuracy of 95.07% in Tongnan District, with specific accuracies of 92.49% for flat cultivated land, 96.18% for terraced cultivated land, 93.80% for sloping cultivated land, and 78.83% for forest intercrop land. The results indicate that, compared to traditional methods, this approach is faster and more accurate, reducing both false positives and omissions. This paper presents a new methodological framework for large-scale cropland mapping in complex scenarios, offering valuable insights for subsequent cropland extraction in challenging environments.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFB3900501, 86-Y50G27-9001-22/23, 21C00346)
- Major Special Project of the High-Resolution Earth Observation System (2021YFB3900501, 86-Y50G27-9001-22/23, 21C00346)
- Chongqing Agricultural Industry Digital Map Project (2021YFB3900501, 86-Y50G27-9001-22/23, 21C00346)
This publication has 31 references indexed in Scilit:
- Cloudiness and water from cloud seeding in connection with plants distribution in the Republic of MoldovaApplied Water Science, 2022
- Pixel based classification for Landsat 8 OLI multispectral satellite images using deep learning neural networkRemote Sensing Applications: Society and Environment, 2021
- Examining earliest identifiable timing of crops using all available Sentinel 1/2 imagery and Google Earth EngineISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Mapping major land cover dynamics in Beijing using all Landsat images in Google Earth EngineRemote Sensing of Environment, 2017
- Spectral considerations for modeling yield of canolaRemote Sensing of Environment, 2016
- A scalable satellite-based crop yield mapperRemote Sensing of Environment, 2015
- Global land cover mapping at 30 m resolution: A POK-based operational approachISPRS Journal of Photogrammetry and Remote Sensing, 2015
- Comparing the suitability of classified land cover data and remote sensing variables for modeling distribution patterns of plantsEcological Modelling, 2014
- The spatial distribution of crop types from MODIS data: Temporal unmixing using Independent Component AnalysisRemote Sensing of Environment, 2010
- Red and photographic infrared linear combinations for monitoring vegetationRemote Sensing of Environment, 1979