-- AI is advancing at an extraordinary pace, with some experts suggesting it could help solve humanity's most pressing challenges. Yet, a significant gap remains: there aren't enough developers applying AI to solve the UN SDGs. To bridge this divide and support global sustainability efforts, ARM and NXP partnered with FruitPunch AI to sponsor the AI for Bears Challenge to identify and monitor wild bear populations with AI, and avoid conflicts.
FruitPunch AI consists of a community of over 4,500 engineers working in small teams on impactful challenges that address the world’s most urgent issues. These challenges span across healthcare, wildlife, climate change and technological impact such as greener data centers.
Human-bear conflicts and its impact
Human-bear conflicts can pose challenges to effective bear conservation and threats to people and property. Promoting coexistence and mitigating human-bear conflicts is key to the long-term conservation of brown bears, preserving the vital role they play in maintaining a balanced ecosystem.
By understanding and protecting them, we contribute to the overall health of the environment. However, monitoring bears is difficult due to their elusive and wide-ranging nature. The toolbox of methods available to study bears in non-invasive ways is limited, leading to a reduced understanding of their population status and trends.
To address this issue, FruitPunch AI launched a challenge through its community of AI engineers that contribute to reach the Sustainable Development Goals (SDGs). Up to 50 engineers were assigned to different teams working on specific technical challenges needed to build a solution that can be used in the wild.
Using AI for bear population analysis
But AI for Bears aimed to go beyond conflict resolution; it strives to enhance the efficiency of bear population analysis. By leveraging AI to expedite this process, we can empower informed decision-making for land use and protection strategies. This, in turn, contributes to the broader goal of creating a harmonious relationship between humans and bears, ensuring sustainable coexistence.
With machine learning (metric learning), over 90% accuracy was achieved to identify bears in the wild and monitor their movements. This model was implemented on-edge using ARM & NXP edge devices to trigger an alarm which scares the bear off, thus preventing it from wandering into a village.
The next step is to integrate these models as a reference use case for smart wildlife cameras so that the technology can be widely used.
Importance of AI for Good in wildlife conservation
Impact for wildlife conservation, especially bears, was a key goal. FruitPunch AI has contributed to this space before: "We are very excited this collaboration allowed us to use our community and experience in previous animal re-identification challenges to tackle this problem for bears as well and contribute to conservation efforts of these wonderful animals", said FruitPunch AI’s CEO Buster Franken.
It wasn’t only the development teams that gained by participating in the challenge. Brian de Bart, team lead for system innovations at NXP added: “The AI for Bears project was a great opportunity for NXP Semiconductors to contribute our microprocessor and AI technologies for a good cause.
“Our engineers got to work with an engaged team of AI enthusiasts and support them in building a solution for identifying bears in the wild. By deploying the developed AI models on the i.MX93 NPU, the team showed the effectiveness of the i.MX93 solution for achieving real-time classification and identification of bears on the edge.”
About AI for Good
AI for Good refers to the application of artificial intelligence technologies to address societal, environmental, and humanitarian challenges. It involves leveraging AI to create solutions that benefit humanity and the planet, aligning technological advancement with ethical, equitable, and sustainable goals.
However, achieving these goals is not without its challenges. Bias in AI systems can lead to inequitable outcomes, raising concerns about fairness in critical areas like healthcare, education, and criminal justice.
Additionally, accessibility remains a pressing issue, as the benefits of AI often fail to reach underserved and marginalized communities. Transparency and accountability in AI decision-making are essential to building trust, yet many systems remain opaque and difficult to scrutinize. Moreover, the significant energy consumption of AI technologies contributes to their environmental impact, conflicting with the sustainability goals they aim to support. Despite these challenges, AI for Good exemplifies the potential to align innovation with responsibility for a better future.
FruitPunch continues to deploy new AI for Good challenges for the world’s most urgent issues in wildlife and beyond to contribute to the SDGs.
Contact Info:
Name: Roeland Pater
Email: Send Email
Organization: FruitPunch AI
Address: Van Asch van Wijckskade 20, 3512 VS Utrecht, Netherland
Website: https://fruitpunch.ai
Release ID: 89152047
Google
RSS