RESOLVE NGO: AI for Good
We worked with Resolve NGO to put their data science capabilities into high gear: deploying over 20 smart camera applications in 6 months across Asia and Africa. By creating AI using only synthetic data, we improved operational efficiency by 2000%, increased product battery life by 42x, and developed object detection algorithms for animals rarely photographed in the wild.
The Pain Points
RESOLVE is an international environmental NGO based in Washington DC that has created TrailguardAI, an intelligent camera system aimed at addressing global environmental concerns. The system is specifically designed to monitor endangered species and detect illegal activities, such as poaching and wildlife trafficking.
Wildlife trafficking is a major issue, with an annual value of $175 billion. However, traditional data collection methods are limited by the scarcity of photos and videos of endangered species, making it difficult to develop accurate detection models.
The current cameras also require frequent maintenance due to limitations in AI power and battery life. RESOLVE needed a solution that would enable their cameras to effectively track endangered species and detect illegal activities while preventing false positives and reducing maintenance burdens.
"Now typically we want cameras to last a year, even two years. You don't want to have to go change the battery every two months, but in fact, that's what we had to do. So the experiment we just did in South Africa, a typical rate of intruders (at a given trail) is maybe between one to ten transgressions a month. If we do the math, that should be the equivalent of 7 years of use in the field."
Eric Dinerstein
Director of Biodiversity, RESOLVE NGO
Our Solution
CVEDIA developed effective algorithms using synthetic data to train AI models for RESOLVE's TrailguardAI cameras. This innovative approach allowed us to create detection models for endangered species that are rarely photographed in the wild.
By using synthetic data, we were able to generate thousands of training images without the need for extensive field data collection. This dramatically reduced development time and costs while improving model accuracy.
The AI models were optimized for edge deployment, ensuring minimal power consumption and extending battery life by 42x, a critical improvement for remote wildlife monitoring applications.
Resolve NGO achieved a remarkable feat with CVEDIA technology, deploying their first intelligent camera within three weeks of conception. Within a month, they had deployed an intelligent camera running a CVEDIA algorithm in Asia, capturing photos of wild elephants for research purposes in collaboration with geologists, conservationists, and local communities.
The NGO plans to deploy their cameras in 200 parks within a year to combat illegal wildlife poaching effectively. This innovative use of technology has allowed them to expand their donor list and fundraise with an active, in-the-field solution.
Over 20 AI systems have since been built by CVEDIA for Resolve NGO, including those for endangered species such as snow leopards, rhinos, and tigers. The NGO aims to monitor every square mile of wildlife on the planet with their solutions, effectively eliminating environmental crime.
Key Results
2000%
Operational Efficiency Improvement
42x
Battery Life Increase
20+
AI Systems Deployed
Start Using CVEDIA-RT
Ready to transform your computer vision applications with synthetic data?
Get Started