New method estimates sidewalk width from street-view images

Researchers have developed UrbanVGGT, a new method for estimating sidewalk width using street-view images. This approach combines semantic segmentation, 3D reconstruction, and scale calibration to measure sidewalk dimensions. Tested on a Washington, D.C. dataset, UrbanVGGT achieved a mean absolute error of 0.252 meters, with over 95% of estimates within 0.50 meters of ground truth. The method was also applied to three cities to create a prototype sidewalk-width dataset, demonstrating its potential for large-scale urban planning data generation, though further validation is needed. AI

IMPACT This research could enable scalable generation of urban planning data, improving accessibility and network quality assessments.

RANK_REASON The cluster contains an academic paper detailing a new methodology and dataset. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• Kaizhen Tan
• OpenStreetMap
• SV-SideWidth
• UrbanVGGT
• Washington, D.C.

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →