Plant Doctor: A hybrid machine learning and image segmentation software to quantify plant damage in video footage
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913415909343232 |
|---|---|
| author | Marques, Marc Josep Montagut Mingxin, Liu Shiojiri, Kuri Thomas Hagiwara, Tomika Hirose, Kayo Shiojiri, Kaori Umezu, Shinjiro |
| author_facet | Marques, Marc Josep Montagut Mingxin, Liu Shiojiri, Kuri Thomas Hagiwara, Tomika Hirose, Kayo Shiojiri, Kaori Umezu, Shinjiro |
| contents | Artificial intelligence has significantly advanced the automation of diagnostic processes, benefiting various fields including agriculture. This study introduces an AI-based system for the automatic diagnosis of urban street plants using video footage obtained with accessible camera devices. The system aims to monitor plant health on a day-to-day basis, aiding in the control of disease spreading in urban areas. By combining two machine vision algorithms, YOLOv8 and DeepSORT, the system efficiently identifies and tracks individual leaves, extracting the optimal images for health analysis. YOLOv8, chosen for its speed and computational efficiency, locates leaves, while DeepSORT ensures robust tracking in complex environments. For detailed health assessment, DeepLabV3Plus, a convolutional neural network, is employed to segment and quantify leaf damage caused by bacteria, pests, and fungi. The hybrid system, named Plant Doctor, has been trained and validated using a diverse dataset including footage from Tokyo urban plants. The results demonstrate the robustness and accuracy of the system in diagnosing leaf damage, with potential applications in large scale urban flora illness monitoring. This approach provides a non-invasive, efficient, and scalable solution for urban tree health management, supporting sustainable urban ecosystems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02853 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Plant Doctor: A hybrid machine learning and image segmentation software to quantify plant damage in video footage Marques, Marc Josep Montagut Mingxin, Liu Shiojiri, Kuri Thomas Hagiwara, Tomika Hirose, Kayo Shiojiri, Kaori Umezu, Shinjiro Computer Vision and Pattern Recognition Artificial intelligence has significantly advanced the automation of diagnostic processes, benefiting various fields including agriculture. This study introduces an AI-based system for the automatic diagnosis of urban street plants using video footage obtained with accessible camera devices. The system aims to monitor plant health on a day-to-day basis, aiding in the control of disease spreading in urban areas. By combining two machine vision algorithms, YOLOv8 and DeepSORT, the system efficiently identifies and tracks individual leaves, extracting the optimal images for health analysis. YOLOv8, chosen for its speed and computational efficiency, locates leaves, while DeepSORT ensures robust tracking in complex environments. For detailed health assessment, DeepLabV3Plus, a convolutional neural network, is employed to segment and quantify leaf damage caused by bacteria, pests, and fungi. The hybrid system, named Plant Doctor, has been trained and validated using a diverse dataset including footage from Tokyo urban plants. The results demonstrate the robustness and accuracy of the system in diagnosing leaf damage, with potential applications in large scale urban flora illness monitoring. This approach provides a non-invasive, efficient, and scalable solution for urban tree health management, supporting sustainable urban ecosystems. |
| title | Plant Doctor: A hybrid machine learning and image segmentation software to quantify plant damage in video footage |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.02853 |