Extracting Agricultural Parcel Boundaries From High Spatial Resolution Remote Sensing Images Based on a Multi-Task Deep Learning Network With Boundary Enhancement Mechanism

Abstract

Extracting agricultural parcel boundaries from remote sensing images based on deep learning methods is currently the most promising method. Due to the diversity of agricultural types and limitations of deep learning networks, parcel boundaries extracted by edge detection deep learning networks lack target specificity, and parcel boundaries extracted by semantic segmentation deep learning networks generally causes a loss of precise boundary information. Based on the principles of multi-task deep learning networks Psi-Net, BsiNet, and ResUNet-a, we constructed a parallel multi-task deep learning network M_ResUnet. The M_ResUnet is capable of performing edge detection and semantic segmentation simultaneously, and it is designed for extracting agricultural parcel boundaries from high-resolution remote sensing images. To improve the effectiveness of parcel boundary recognition, the edge enhancement concept from the context-aware tracing strategy (CATS) is introduced into the M_ResUnet, which enhanced the continuity and effectiveness of parcel boundary recognition and accelerated network training convergence. Finally, we conducted experiments on three different study areas with different remote sensing data sources and agricultural parcel types. The experimental results demonstrate that the method we proposed achieved better continuity in identifying parcel boundaries, and it also improved the recognition of boundaries between neighboring parcels with strong similarities remote sensing features such as texture and spectral characteristics.

Keywords

• Remote sensing
• agricultural parcels
• deep learning
• semantic segmentation
• edge detection
• multi-tasking