The boundary extraction of an object from remote sensing imagery has been an important issue in the field of research. The automation of farmland boundary extraction is particularly in demand for rapid updates of the digital farm maps in Korea. This study aimed to develop a boundary extraction algorithm by systematically reconstructing a series of computational and mathematical methods, including the Suzuki85 algorithm, Canny edge detection, and Hough transform. Since most irregular farmlands in Korea have been consolidated into large rectangular arrangements for agricultural productivity, the boundary between two adjacent land parcels was assumed to be a straight line. The developed algorithm was applied over six different study sites to evaluate its performance at the boundary level and sectional area level. The correctness, completeness, and quality of the extracted boundaries were approximately 80.7%, 79.7%, and 67.0%, at the boundary level, and 89.7%, 90.0%, and 81.6%, at the area-based level, respectively. These performances are comparable with the results of previous studies on similar subjects; thus, this algorithm can be used for land parcel boundary extraction. The developed algorithm tended to subdivide land parcels for distinctive features, such as greenhouse structures or isolated irregular land parcels within the land blocks. The developed algorithm is currently applicable only to regularly arranged land parcels, and further study coupled with a decision tree or artificial intelligence may allow for boundary extraction from irregularly shaped land parcels.

No abstract

Prompt updates of land cover maps are important, as spatial information of land cover is widely used in many areas. However, current manual digitizing methods are time consuming and labor intensive, hindering rapid updates of land cover maps. The objective of this study was to develop an artificial intelligence (AI) based land cover classification model that allows for rapid land cover classification from high-resolution remote sensing (HRRS) images. The model comprises of three modules: pre-processing, land cover classification, and post-processing modules. The pre-processing module separates the HRRS image into multiple aspects by overlapping 75% using the sliding window algorithm. The land cover classification module was developed using the convolutional neural network (CNN) concept, based the FusionNet network and used to assign a land cover type to the separated HRRS images. Post-processing module determines ultimate land cover types by summing up the separated land cover result from the land cover classification module. Model training and validation were conducted to evaluate the performance of the developed model. The land cover maps and orthographic images of 547.29 km2 in area from the Jeonnam province in Korea were used to train the model. For model validation, two spatial and temporal different sites, one from Subuk-myeon of Jeonnam province in 2018 and the other from Daseo-myeon of Chungbuk province in 2016, were randomly chosen. The model performed reasonably well, demonstrating overall accuracies of 0.81 and 0.71, and kappa coefficients of 0.75 and 0.64, for the respective validation sites. The model performance was better when only considering the agricultural area by showing overall accuracy of 0.83 and kappa coefficients of 0.73. It was concluded that the developed model may assist rapid land cover update especially for agricultural areas and incorporation field boundary lineation is suggested as future study to further improve the model accuracy.