Mapping sidewalks and street furniture with AI and computer vision
summary
An AI pipeline converts 360° sidewalk images and GPS into geolocated point and line GIS layers — benches, garbage bins, bike racks, sidewalks and crosswalks — using semantic segmentation + monocular depth to estimate object distance and position, producing 3D point clouds. Data comes from 10 cities (Sydney, Bangkok, Manila, London, San Diego, San Francisco, etc.), includes crowdsourced collection (a student walked ~30 km), and uploads directly into JOSM/OSM for validation.
AI-written summary · about
chapters (6)
- 0:00Introduction to Fori
- 1:28Data collection workflow
- 3:31AI-driven mapping
- 5:30Practical urban applications
- 6:40OpenStreetMap integration
- 8:26Team background and conclusion
related talks
22mUrban Artificial Intelligence in Amsterdam
19mHow we leverage AI to build great maps at massive scale
22mIsland Mapping: Measuring Urban Footprints with Mapillary & Open Source Tools
26mFrom Panoramic Vision to Lightweight 3D Worlds for Semantic Visual Tracking
02mWe painted the whole town
17mGeoAI: a feature extraction tool set using Tensor Flow and Keras...
18mRecognition and Localization of Parking Signs using Deep Learning
11mUsing AI to Accelerate the Smart Green Transition