Synthetic thermal images improve real-time animal detection at night
Synthetic Thermal Image Generation for Real-Time Animal Detection Under Low-Visibility Conditions
Computer Vision and Pattern Recognition
Summary
Collisions between vehicles and animals on roads are a big problem, especially at night when regular cameras don’t work well. The authors show that by creating fake thermal images from regular photos, computers can learn to spot animals even in low light. They tested different detection models and found that synthetic thermal data helps train effective animal detectors. Using these images could lead to better systems that keep animals and drivers safer on the road at night.
What this means in practice
- •For automotive safety engineers: Integrate synthetic thermal datasets to improve vehicle-mounted animal detection systems for safer nighttime driving.
- •For wildlife monitoring teams: Use synthetic thermal image generation to enhance infrared animal detection in remote or low-light environments where collecting real data is hard.
Authors
James Momoh, Khandaker Mamun Ahmed
Abstract
Wildlife-vehicle collisions remain a significant road safety concern, particularly during nighttime and low-visibility conditions when RGB-based perception systems are often unreliable. Thermal imaging offers a promising alternative for detecting animals under poor illumination. However, the limited availability of annotated infrared animal datasets restricts the development of robust deep learning-based detection models. This paper investigates synthetic thermal image generation as a scalable approach for real-time animal detection under low-visibility conditions. A subset of 514 annotated visible-spectrum animal images from the NTLNP dataset is translated into synthetic thermal representations using CycleGAN-Turbo, while a limited real thermal dataset of 60 images is expanded through thermal-focused augmentation. Multiple object detection architectures, including YOLOv8, YOLOv9, YOLOv10, and RT-DETR, are trained independently on synthetic and real thermal datasets and evaluated using precision, recall, mAP@0.5, mAP@0.5:0.95, model size, and inference latency. Experimental results show that synthetic thermal images provide competitive detection performance, with RT-DETR achieving the highest synthetic-data mAP@0.5 of 0.9613. Models trained on augmented real thermal data achieve the strongest overall performance, with YOLOv10s obtaining 0.9879 mAP@0.5 and 0.9571 mAP@0.5:0.95. Computational analysis further indicates that lightweight YOLO variants provide favorable inference latency, supporting their potential for real-time deployment. These findings demonstrate that synthetic thermal imagery can reduce dependence on scarce infrared datasets and support the development of efficient animal detection systems for future vehicle-mounted wildlife collision mitigation applications.