Semantic Segmentation for Urban Planning Maps based on U-Net
This addresses the inefficient manual digitization of maps for urban planning, though it is incremental as it applies an existing method to a new domain.
The study tackled the problem of automating semantic segmentation for urban planning maps, achieving a Jaccard similarity coefficient of 93.63% and overall accuracy of 99.36% with processing times under three minutes for the Shibuya district.
The automatic digitizing of paper maps is a significant and challenging task for both academia and industry. As an important procedure of map digitizing, the semantic segmentation section mainly relies on manual visual interpretation with low efficiency. In this study, we select urban planning maps as a representative sample and investigate the feasibility of utilizing U-shape fully convolutional based architecture to perform end-to-end map semantic segmentation. The experimental results obtained from the test area in Shibuya district, Tokyo, demonstrate that our proposed method could achieve a very high Jaccard similarity coefficient of 93.63% and an overall accuracy of 99.36%. For implementation on GPGPU and cuDNN, the required processing time for the whole Shibuya district can be less than three minutes. The results indicate the proposed method can serve as a viable tool for urban planning map semantic segmentation task with high accuracy and efficiency.