A Survey of Farmland Boundary Extraction Technology Based on Remote Sensing Images

Farmland boundary information plays a key role in agricultural remote sensing, and it is of importance to modern agriculture. We collected the relevant research this field at home abroad review, we systematically assessed farmland extraction process, detection algorithms, influencing factors. In paper, first discuss five parts assessment: (1) image acquisition; (2) preprocessing; (3) algorithms; (4) postprocessing; (5) evaluation process. Second, recognition algorithms. Third, various The algorithms can be divided into four types: low-level feature which only consider features; high-level other simultaneously; visual hierarchy simulate biological vision systems; object recognize ideas. subdivide each type algorithm several subclasses. Fourth, technical factors natural that affect extraction. Finally, summarize development history field, analyze problems exist, such as lack adapted higher-resolution images, with good practical ability, unified effective index system.