Real-time Deer Detection and Warning in Connected Vehicles via Thermal Sensing and Deep Learning

2025-09-23

AI Summary

This study addresses the significant human casualties, economic losses, and ecological impacts caused by frequent deer–vehicle collisions in the United States. To mitigate this, we propose a real-time cooperative perception system integrating thermal imaging, a lightweight deep learning model, and cellular vehicle-to-everything (C-V2X) communication. A high-quality, self-collected thermal deer dataset is used to train an end-to-end detection model, ensuring robust cross-weather performance. A declarative data-sharing mechanism is introduced to trigger low-latency inter-vehicle warnings (<100 ms) in high-risk scenarios. Experimental results demonstrate a mean average precision of 98.84%, with accuracy maintained at 88%–92% under adverse weather—substantially outperforming visible-light-based approaches. The core contributions include: (i) a thermal imaging–driven, low-latency cooperative perception architecture; and (ii) its rigorous validation and reliable deployment in real-world road environments.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deer-vehicle collisions represent a critical safety challenge in the United States, causing nearly 2.1 million incidents annually and resulting in approximately 440 fatalities, 59,000 injuries, and 10 billion USD in economic damages. These collisions also contribute significantly to declining deer populations. This paper presents a real-time detection and driver warning system that integrates thermal imaging, deep learning, and vehicle-to-everything communication to help mitigate deer-vehicle collisions. Our system was trained and validated on a custom dataset of over 12,000 thermal deer images collected in Mars Hill, North Carolina. Experimental evaluation demonstrates exceptional performance with 98.84 percent mean average precision, 95.44 percent precision, and 95.96 percent recall. The system was field tested during a follow-up visit to Mars Hill and readily sensed deer providing the driver with advanced warning. Field testing validates robust operation across diverse weather conditions, with thermal imaging maintaining between 88 and 92 percent detection accuracy in challenging scenarios where conventional visible light based cameras achieve less than 60 percent effectiveness. When a high probability threshold is reached sensor data sharing messages are broadcast to surrounding vehicles and roadside units via cellular vehicle to everything (CV2X) communication devices. Overall, our system achieves end to end latency consistently under 100 milliseconds from detection to driver alert. This research establishes a viable technological pathway for reducing deer-vehicle collisions through thermal imaging and connected vehicles.

Problem

• Developing real-time deer detection using thermal imaging and deep learning
• Mitigating deer-vehicle collisions through connected vehicle communication systems
• Creating robust wildlife detection that works across diverse weather conditions

Innovation

• Thermal imaging for robust deer detection
• Deep learning model trained on custom dataset
• CV2X communication for real-time warning sharing