Furthering Automatic Feature Extraction for Fit-for-Purpose Cadastral Updating: Cases from Peri-Urban Addis Ababa, Ethiopia

Fit-for-purpose land administration (FFPLA) seeks to simplify cadastral mapping via lowering the costs and time associated with conventional surveying methods. This approach can be applied both initial establishment on-going maintenance of system. In Ethiopia, remains an challenge, especially in rapidly urbanizing peri-urban areas, where farmers’ rights tenure security are often jeopardized. Automatic Feature Extraction (AFE) is emerging FFPLA approach, proposed as alternative for updating boundaries. study explores role AFE boundaries vibrant areas Addis Ababa. Open-source software solutions were utilized assess (semi-) automatic extraction from orthophotos (segmentation), designation “boundary” “non-boundary” outlines (classification), delimitation (interactive delineation). Both qualitative quantitative assessments achieved results (validation) undertaken. A high-resolution orthophoto area a reference boundary shape file used, respectively, extracting parcel validating interactive delineation results. Qualitative (visual) assessment verified completed newly constructed area, although non-boundary such footpaths artifacts also retrieved. For buffer overlay analysis, interactively delineated lines cadastre buffered within spatial accuracy limits urban rural cadastres. As result, delivered 52% correctness 32% completeness width 0.4 m 0.6 m, The publicly available outlined workflow automatically extract aerial/satellite images. It further demonstrated potentially significant could play delivering fast, affordable, reliable mapping. Further investigation, based on user input expertise evaluation, help improve apply it real-world setting.