Loading...
A RUBBER TREE ORCHARD MAPPING METHOD VIA IMAGE PROCESSING
Author(s)
Kunghun, Worawut
Date Issued
August 1, 2022
Type
Article
Abstract
This research was carried out in order to evaluate the performance of a computer visual mapping method using permanent targets mounted on the tree trucks as the distinctive marks to the environment. Two targets per tree trunk were used to create sufficient target perception from a distance. The computer vision uses the known distance between these two targets to determine the location of the camera using pin-hole camera principle. The system was designed based on configurations of the rubber tree orchard which is one of the main industrial crops in South East Asia. A set of experiment was carried out on both laboratory and real plantation site. With different parameters and setup, the mapping system was able to achieve the RMS maximum error 43.06 mm in laboratory control environment and 114.57 mm in actual site. This magnitude of error was considered acceptable in low accuracy autonomous operation in automatic agricultural tasks such as watering, fertilization and harvest. Several aspects regarding parameters in the mapping method setup and the outcome were discussed and compared.
Citation
International Journal of Innovative Computing Information and Control, 18(4), 1181-1201, 2022