Drones (UAS) are increasingly used for monitoring animals, offering multiple advantages, including time or cost savings, increased safety over occupied aircraft, and more accurate counts than traditional ground-based methods. Combining complementary information from both visible and thermal images acquired from drones provides a powerful approach for automating detection and classification of multiple animal species. We compared eight image fusion methods using thermal and visible drone images combined with two supervised deep learning models, to evaluate the detection and classification of white-tailed deer, domestic cow, and domestic horse. Results suggest that image fusion is ideal for surveying animals inconspicuous from their backgrounds, and our approach uses few image pairs to train compared to typical machine-learning methods.
Previous ArticleTransforming Enterprise Cybersecurity: Trend Micro Unleashes Trend Vision One™ Platform With Next-gen Xdr And Ai Capabilities
Next Article Chatgpt Glossary