Optimal color space selection method for plant/soil segmentation in agriculture

摘要: Display Omitted A new training algorithm is proposed for agricultural color classification problems.The method selects the optimal space and channels each scenario.Applied to estimate accurately efficiently percentage of green cover (PGC).Developed an application called ACPS (Automatic Classification Plants Soil). Color analysis techniques in agriculture should be able deal with non-trivial capture conditions such as shadows, noise, pixel saturation, low lighting, different varieties crops intrinsic parameters cameras. Previous studies have shown importance selecting optimum domain. This paper presents a probabilistic approach processing capable not only create models plant/soil segmentation, but also select most adequate problem. The system evaluates all possible alternatives, producing channels. Thereby, dependences on kind crop, camera are avoided, since adapted conditions. basis proposal use non-parametric probability density functions colors. has been implemented validated software tool, Soil), thus proving its practical feasibility. final purpose this vegetal ground cover, order obtain PGC (percentage cover) parameter. developed used by professionals, researchers, technicians anyone working area. Furthermore, created can exported defined file format which applications cloud, mobile devices compact controllers that currently being developed.