Oil palm tree detection and counting in aerial images based on faster R-CNN

Oil palm tree detection and counting in aerial images based on faster R-CNN

Malaysian oil palm industry has been a great contributor to the country’s creation of job opportunity, foreign exchange earnings and GDP. Information about the amount and the distribution of oil palm trees in a plantation are important for sustainable management. In this paper, we propose an oil pal...

Full description

Bibliographic Details
Main Authors: Xinni, Liu, Kamarul Hawari, Ghazali, Fengrong, Han, Izzeldin, I. Mohd, Yue, Zhao, Yuanfa, Ji
Format: Conference or Workshop Item
Language:English
Published: Springer, Singapore 2020
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://umpir.ump.edu.my/id/eprint/30346/1/Oil%20palm%20tree%20detection%20and%20counting%20in%20aerial%20images%20%20.pdf
Description
Summary:Malaysian oil palm industry has been a great contributor to the country’s creation of job opportunity, foreign exchange earnings and GDP. Information about the amount and the distribution of oil palm trees in a plantation are important for sustainable management. In this paper, we propose an oil palm tree detection and counting method based on the Faster Regions with Convolutional Neural Network algorithm (Faster R-CNN). Experiment on the oil palm tree images collected by a drone shows that the proposed method can effectively detect the oil palm trees and counting its number when the age of the trees in a plantation is different from 2 years old to 8 years old. The proposed approach can be used to predict the scale of the plantation and meets the requirements of real-time detection.

Similar Items