United StatesPublic sector2019 – ongoingWorld Wildlife Fund US
Wildlife Insights AI classification of camera-trap images
WWF partnered on Wildlife Insights, whose image-classification AI was trained on over 600 species
Problem
Camera traps generated more images than conservation researchers could readily process. Files stored on separate hard drives also made collaboration difficult.
Approach
WWF operated Wildlife Insights with conservation partners and Google. Google's AI identified animals in uploaded photographs, while shared cloud storage supported collaborative analysis. The platform combined image processing with access to a common wildlife database.
Results
Takeaway
Automatic identification addressed image-processing backlogs, while shared storage addressed a separate barrier to collaboration. WWF did not report measured staff-hour savings.
Categories
- Industry
- Public sector
- Business function
- Production and qualityIT and R&D
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
WWF described the jointly operated Wildlife Insights platform and Google's automatic image identification. It reported training coverage exceeding 600 species and explained the obstacles created by unprocessed, separately stored photographs.
Full details are in the original sources.