The GIS industry relies heavily on manual efforts to build and maintain digital maps. This approach is timeconsumingand requires a sizable workforce not only for map-making but also for quality-checks that are required toresolve the potential errors resulting from manual digitization.With recent advancements in computer vision, several organizations are using machine-learning algorithms togenerate map data from images. In the current machine learning based geometry creation process three limitationsprevails. Firstly, the output of the algorithms is never served on-demand to a map editing tool. Secondly, after beingfurther fine-tuned manually by annotators/validators, the results are never fed back to the algorithms to identify the errorsincurred and improve accuracy. Finally, a lot of manual effort is required to create training data for new terrains andregions. We propose an end-to-end machine learning system integrated with current map-making tools to address theselimitations and reduce the manual effort in creating and updating geometry.
展开▼
