Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method
Knowledge of the number and distribution of oil palm trees during the crop cycle is vital for sustainable management and predicting yields. The accuracy of the conventional image processing method is limited for the hand-crafted feature extraction method and the overfitting problem occurs due to the...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/12/4479 |
_version_ | 1797487706537721856 |
---|---|
author | Xinni Liu Kamarul H. Ghazali Akeel A. Shah |
author_facet | Xinni Liu Kamarul H. Ghazali Akeel A. Shah |
author_sort | Xinni Liu |
collection | DOAJ |
description | Knowledge of the number and distribution of oil palm trees during the crop cycle is vital for sustainable management and predicting yields. The accuracy of the conventional image processing method is limited for the hand-crafted feature extraction method and the overfitting problem occurs due to the insufficient dataset. We propose a modification of the Faster Region-based Convolutional Neural Network (FRCNN) for palm tree detection to reduce the overfitting problem and improve the detection accuracy. The enhanced FRCNN (EFRCNN) leads to improved performance for detecting objects (in the same image) when they are of multiple sizes by using a feature concatenation method. Transfer learning based on a ResNet50 model is used to extract the features of the input image. High-resolution images of oil palm trees from a drone are used to form the data set, containing mature, young, and mixed oil palm tree regions. We train and test the EFRCNN, the FRCNN, a CNN used recently for oil palm image detection, and two standard methods, namely, the support vector machine (SVM) and template matching (TM). The results reveal an overall accuracy of ≥96.8% for the EFRCNN on the three test sets. The accuracy is higher than the CNN and FRCNN and substantially higher than SVM and TM. For large-scale plantations, the accuracy improvement is significant. This research provides a method for automatically counting the oil palm trees in large-scale plantations. |
first_indexed | 2024-03-09T23:51:34Z |
format | Article |
id | doaj.art-631bff7ff2504ed6a24c357ab74ec5e0 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-09T23:51:34Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-631bff7ff2504ed6a24c357ab74ec5e02023-11-23T16:31:50ZengMDPI AGEnergies1996-10732022-06-011512447910.3390/en15124479Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning MethodXinni Liu0Kamarul H. Ghazali1Akeel A. Shah2School of Information, Xi’an University of Finance and Economics, Xi’an 710100, ChinaFaculty of Electrical and Electronic Engineering Technology, Universiti Malaysia Pahang, Pekan 26600, MalaysiaKey Laboratory of Low-Grade Energy Utilization Technologies and Systems, MOE, Chongqing University, Chongqing 400030, ChinaKnowledge of the number and distribution of oil palm trees during the crop cycle is vital for sustainable management and predicting yields. The accuracy of the conventional image processing method is limited for the hand-crafted feature extraction method and the overfitting problem occurs due to the insufficient dataset. We propose a modification of the Faster Region-based Convolutional Neural Network (FRCNN) for palm tree detection to reduce the overfitting problem and improve the detection accuracy. The enhanced FRCNN (EFRCNN) leads to improved performance for detecting objects (in the same image) when they are of multiple sizes by using a feature concatenation method. Transfer learning based on a ResNet50 model is used to extract the features of the input image. High-resolution images of oil palm trees from a drone are used to form the data set, containing mature, young, and mixed oil palm tree regions. We train and test the EFRCNN, the FRCNN, a CNN used recently for oil palm image detection, and two standard methods, namely, the support vector machine (SVM) and template matching (TM). The results reveal an overall accuracy of ≥96.8% for the EFRCNN on the three test sets. The accuracy is higher than the CNN and FRCNN and substantially higher than SVM and TM. For large-scale plantations, the accuracy improvement is significant. This research provides a method for automatically counting the oil palm trees in large-scale plantations.https://www.mdpi.com/1996-1073/15/12/4479sustainableoil palm treeresource assessmentdeep learningFaster Region-Based Convolutional Neural Networkfeature map concatenation |
spellingShingle | Xinni Liu Kamarul H. Ghazali Akeel A. Shah Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method Energies sustainable oil palm tree resource assessment deep learning Faster Region-Based Convolutional Neural Network feature map concatenation |
title | Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method |
title_full | Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method |
title_fullStr | Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method |
title_full_unstemmed | Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method |
title_short | Sustainable Oil Palm Resource Assessment Based on an Enhanced Deep Learning Method |
title_sort | sustainable oil palm resource assessment based on an enhanced deep learning method |
topic | sustainable oil palm tree resource assessment deep learning Faster Region-Based Convolutional Neural Network feature map concatenation |
url | https://www.mdpi.com/1996-1073/15/12/4479 |
work_keys_str_mv | AT xinniliu sustainableoilpalmresourceassessmentbasedonanenhanceddeeplearningmethod AT kamarulhghazali sustainableoilpalmresourceassessmentbasedonanenhanceddeeplearningmethod AT akeelashah sustainableoilpalmresourceassessmentbasedonanenhanceddeeplearningmethod |