Urban tree health diagnosis approach based on thermal image and deep learning model

Monitoring the health of urban trees is essential for maintaining a sustainable and resilient urban ecosystem. Traditional methods of manual inspection are labour-intensive and prone to errors. In this research paper, we propose a novel approach for diagnosing tree health based on thermal imaging and deep learning models. Our approach leverages the advantages of thermal imaging in detecting temperature variations associated with various tree health conditions, and the power of deep learning in automating the diagnosis process. We demonstrate the efficacy of our approach through extensive experiments and validation on a tree image dataset collected from the Ao Ba Om historical place in Tra Vinh province, Vietnam, showcasing its potential for large-scale urban tree health monitoring and management. By combining the power of thermal imaging and deep learning, our proposed methodology offers a more efficient, objective, and scalable solution for early detection and diagnosis of tree health issues, enabling timely interventions and supporting the long-term sustainability of urban forests.