Intelligent Bear Prevention System Based on Computer Vision: An Approach to Reduce Human-Bear Conflicts in the Tibetan Plateau Area, China

2025-03-29

AI Summary

Frequent human–bear conflicts on the Qinghai–Tibet Plateau, coupled with severe constraints in power supply and network connectivity in remote areas, hinder effective real-time wildlife conflict mitigation. Method: This study proposes a low-power edge-intelligent early-warning and deterrence system tailored for extreme environments. It features a lightweight YOLO model co-optimized with the K210 edge AI chip, an adaptive audio-visual deterrence module, and an integrated IoT sensing network enabling long-term, off-grid, unattended operation. Contribution/Results: Field evaluations in representative regions (e.g., Yushu) achieved a mean Average Precision (mAP) of 91.4%, significantly improving detection latency and reliability. To our knowledge, this is the first end-to-end, on-device visual recognition–decision–response closed loop deployed in high-altitude settings. The system reduces both human safety risks and unintended bear casualties, establishing a scalable technical paradigm for wildlife conflict management in high-elevation ecosystems.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Learning on the Edge & Model Compression
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Conflicts between humans and bears on the Tibetan Plateau present substantial threats to local communities and hinder wildlife preservation initiatives. This research introduces a novel strategy that incorporates computer vision alongside Internet of Things (IoT) technologies to alleviate these issues. Tailored specifically for the harsh environment of the Tibetan Plateau, the approach utilizes the K210 development board paired with the YOLO object detection framework along with a tailored bear-deterrent mechanism, offering minimal energy usage and real-time efficiency in bear identification and deterrence. The model's performance was evaluated experimentally, achieving a mean Average Precision (mAP) of 91.4%, demonstrating excellent precision and dependability. By integrating energy-efficient components, the proposed system effectively surpasses the challenges of remote and off-grid environments, ensuring uninterrupted operation in secluded locations. This study provides a viable, eco-friendly, and expandable solution to mitigate human-bear conflicts, thereby improving human safety and promoting bear conservation in isolated areas like Yushu, China.

Problem

• Reducing human-bear conflicts using computer vision and IoT
• Detecting and deterring bears in harsh Tibetan Plateau environments
• Providing eco-friendly solution for wildlife conservation and human safety

Innovation

• Computer vision and IoT for bear detection
• K210 board with YOLO for real-time efficiency
• Energy-efficient components for remote operation