Geographic Element Extraction for Supporting Kota Lengkap Using Deep Learning

Abstract

Abstract An indicator of accelerating the ease of investment in land registration as legal certainty and protection of property assets. Pendaftaran Tanah Sistematis Lengkap (PTSL) is an effort to quickly and accurately develop data on all land parcels, both physical and legal. The use of deep learning to speed up mapping is a concrete example of how we are entering a new era of industrial revolution. The advantage of deep learning is to speed up the process of creating a Kota Lengkap map as a manifestation of a complete Pendaftaran Tanah Sistematis Lengkap (PTSL). The limitation in the number of human resources is a significant problem in measuring the road network to realise Kota Lengkap. This can be overcome by using automation to extract the road network. An orthophoto can more accurately show the location of all visible phenomena, thus enabling precise and accurate measurements of area, distance and direction. Deep learning methods can be applied to orthophotos and LIDAR to detect topographic features such as roads or rivers. Using the deep learning method and a split ratio of 80:20, it takes a total of 11 hours 45 minutes to automatically extract road features, while for river features it takes a total of 2 hours 38 minutes, resulting in an overall accuracy of 96.15%. The automated extraction of road and river networks from orthophotos cannot yet be applied directly to planar maps, as it requires post-processing to obtain gapless polygons.