Cataloging Public Objects Using Aerial and Street-Level Images — Urban Trees
Citations Over TimeTop 1% of 2016 papers
Abstract
Each corner of the inhabited world is imaged from multiple viewpoints with increasing frequency. Online map services like Google Maps or Here Maps provide direct access to huge amounts of densely sampled, georeferenced images from street view and aerial perspective. There is an opportunity to design computer vision systems that will help us search, catalog and monitor public infrastructure, buildings and artifacts. We explore the architecture and feasibility of such a system. The main technical challenge is combining test time information from multiple views of each geographic location (e.g., aerial and street views). We implement two modules: det2geo, which detects the set of locations of objects belonging to a given category, and geo2cat, which computes the fine-grained category of the object at a given location. We introduce a solution that adapts state-of the-art CNN-based object detectors and classifiers. We test our method on "Pasadena Urban Trees", a new dataset of 80,000 trees with geographic and species annotations, and show that combining multiple views significantly improves both tree detection and tree species classification, rivaling human performance.
Related Papers
- → VAID: An Aerial Image Dataset for Vehicle Detection and Classification(2020)66 cited
- → Evaluation of synthetic aerial imagery using unconditional generative adversarial networks(2022)22 cited
- → Opportunities to Enhance Discovery, Explorability, and Access for Digital Aerial Imagery Collections(2019)4 cited
- → Research on Data Annotation Based on Multi-Resolution Unmanned Aerial Vehicle (UAV) Aerial Imagery(2023)
- Locating Orphaned Wells Using Georeferenced Historical Aerial Imagery(2023)