Year: 2024
Type: article
Abstract: This paper proposes a potential solution for monitoring the durian plantations which apply intercropping by using drones equipped with RGB and spectral cameras. Currently, farmers mainly rely on their naked eyes to estimate whether a density of papayas around a durian tree is suitable. This eye estimation is time consuming and often not accurate enough, especially when trees reach the heights above the human head. To help the farmers, the proposed method used drones to create the ortho-mosaic map of the monitoring areas then YOLO V5 model is used to detect and locate durian and papaya trees. These results were used to evaluate the durian growth conditions. The trained model result showed a high accuracy at over 95% in detecting and locating trees which is reliable enough to apply to the practice. Furthermore, in the validating process, durian growth conditions also correctly evaluated and detected regions where density of papaya trees must be adjusted.
Source: Science & Technology Asia
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDGs: Zero hunger, Life on land
Open Access status: hybrid
OpenAlex ID: W7220134816