Delineating farm boundaries: why is it important?
The analysis of high spatial resolution RS data permits the delineation of farm boundaries. Accurate delineation of farm boundaries is important to undertake many planning and decision-making actions.
First, it enables a better estimation of cropland area, which is important information for both the farmer and agricultural managers (e.g., ministries, private sector players). Farmers in SHA systems often use traditional measurement approaches to estimate the area of their farms, which sometimes leads to high under- or over-estimation. Accurate knowledge of farm boundary (and therefore cropland area) will lead to efficient use of farm inputs such as seeds, fertilizers and pesticides, and may also help to optimize harvest logistics.
Second, accurate information on farm boundaries can facilitate land registration and subsequent acquisition of land use rights for smallholder farmers (through a land tenure information system). Farmers, communities and the private sector are mostly deterred from investing in land resources due to unclear land use rights in rural areas. Development of an accurate parcel database through high spatial resolution remote sensing data is an important first step towards the development of a land tenure information system and potentially, a land taxation scheme. Such a system will reduce land-related conflicts and encourage increased investment in agriculture. It can also improve farmer access to inputs and credits.
Within the West African part of the STARS project, parcel use certificates are being developed from a database of field boundaries generated from high resolution images. This database has been coupled with a business model. Initial results, though promising, indicate a too low frequency of land transactions to sustain an organization in maintaining the land cadaster.
Third, delineation of farm field boundaries can improve crop type classification using object-based image analysis (OBIA) procedures (Duro et al., 2012; Peña-Barragán et al., 2011). In traditional classification approaches, each a satellite image pixel is analyzed to reveal the land cover it belongs to (i.e., following a per-pixel approach). In OBIA, however, all pixels in an area (a delineated farm field in this case) are treated to belong to one land cover class (Blaschke, 2010). This approach has been found to produce more accurate and visually appealing results than the traditional pixel-based approaches (Blaschke, 2010; Peña-Barragán et al., 2011). Its implementation is, however, dependent on the availability of field boundaries, which can be obtained through image segmentation techniques. SHA farm fields often display vague boundaries, due to natural vegetation and weeds with the crops, which presents formidable challenges to segmentation approaches.