Continental-scale computer vision models reveal generalizable patterns and pitfalls for urban tree inventories with street-view images
Thomas A. Lake, Brittany B. Laginhas, Brennen T Farrell, Ross K. Meentemeyer, Chris M. Jones
The paper develops computer vision models to detect and classify urban trees using street-view images, finding 67.1% accuracy with performance varying by city and genus.
ISPRS Open Journal of Photogrammetry and Remote Sensing · Jan 1, 2026Peer-reviewedEcology