Synthetic Thermal Image Generation for Real-Time Animal Detection Under Low-Visibility Conditions

2026-09-26

AI Summary

This study addresses the limited robustness of detection models under low-visibility conditions caused by the scarcity of infrared animal data. To mitigate this issue, we propose a synthetic thermal image generation and real-data augmentation method based on CycleGAN-Turbo. By constructing a synthetic-real mixed training strategy, the approach significantly reduces reliance on scarce annotated infrared datasets. Experiments conducted using YOLOv8 through YOLOv10 and RT-DETR architectures demonstrate that RT-DETR achieves a mAP of 0.9613 on synthetic data, while YOLOv10s attains a mAP@0.5:0.95 of 0.9571 on augmented data, effectively balancing high precision with real-time inference capabilities. This research presents an efficient data augmentation paradigm for mitigating wildlife-vehicle collision risks.

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.

Problem

• wildlife-vehicle collisions
• thermal imaging
• animal detection
• low-visibility conditions
• dataset scarcity

Innovation

• Synthetic Thermal Image Generation
• CycleGAN-Turbo
• Real-Time Animal Detection
• Data Augmentation
• Object Detection