Recognition of Sago Palm Trees Based on Transfer Learning
Sago palm tree, known as <i>Metroxylon Sagu Rottb</i>, is one of the priority commodities in Indonesia. Based on our previous research, the potential habitat of the plant has been decreasing. On the other hand, while the use of remote sensing is now widely developed, it is rarely applied...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/19/4932 |
_version_ | 1797477136146104320 |
---|---|
author | Sri Murniani Angelina Letsoin Ratna Chrismiari Purwestri Fajar Rahmawan David Herak |
author_facet | Sri Murniani Angelina Letsoin Ratna Chrismiari Purwestri Fajar Rahmawan David Herak |
author_sort | Sri Murniani Angelina Letsoin |
collection | DOAJ |
description | Sago palm tree, known as <i>Metroxylon Sagu Rottb</i>, is one of the priority commodities in Indonesia. Based on our previous research, the potential habitat of the plant has been decreasing. On the other hand, while the use of remote sensing is now widely developed, it is rarely applied for detection and classification purposes, specifically in Indonesia. Considering the potential use of the plant, local farmers identify the harvest time by using human inspection, i.e., by identifying the bloom of the flower. Therefore, this study aims to detect sago palms based on their physical morphology from Unmanned Aerial Vehicle (UAV) RGB imagery. Specifically, this paper endeavors to apply the transfer learning approach using three deep pre-trained networks in sago palm tree detection, namely, SqueezeNet, AlexNet, and ResNet-50. The dataset was collected from nine different groups of plants based on the dominant physical features, i.e., leaves, flowers, fruits, and trunks by using a UAV. Typical classes of plants are randomly selected, like coconut and oil palm trees. As a result, the experiment shows that the ResNet-50 model becomes a preferred base model for sago palm classifiers, with a precision of 75%, 78%, and 83% for sago flowers (SF), sago leaves (SL), and sago trunk (ST), respectively. Generally, all of the models perform well for coconut trees, but they still tend to perform less effectively for sago palm and oil palm detection, which is explained by the similarity of the physical appearance of these two palms. Therefore, based our findings, we recommend improving the optimized parameters, thereby providing more varied sago datasets with the same substituted layers designed in this study. |
first_indexed | 2024-03-09T21:13:20Z |
format | Article |
id | doaj.art-c57f6ac84777448f8440a84049ef53b7 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T21:13:20Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-c57f6ac84777448f8440a84049ef53b72023-11-23T21:41:06ZengMDPI AGRemote Sensing2072-42922022-10-011419493210.3390/rs14194932Recognition of Sago Palm Trees Based on Transfer LearningSri Murniani Angelina Letsoin0Ratna Chrismiari Purwestri1Fajar Rahmawan2David Herak3Department of Mechanical Engineering, Faculty of Engineering, Czech University of Life Sciences Prague, Kamýcká 129, Suchdol, 16500 Praha, Czech RepublicDepartment of Excellent Research EVA 4.0, Faculty of Forestry and Wood Sciences, Czech University of Life Sciences Prague, Kamýcká 129, Suchdol, 16500 Praha, Czech RepublicINTSIA Foundation of Papua Province, Furia 3 Number 116 Abepura, Jayapura City 99225, IndonesiaDepartment of Mechanical Engineering, Faculty of Engineering, Czech University of Life Sciences Prague, Kamýcká 129, Suchdol, 16500 Praha, Czech RepublicSago palm tree, known as <i>Metroxylon Sagu Rottb</i>, is one of the priority commodities in Indonesia. Based on our previous research, the potential habitat of the plant has been decreasing. On the other hand, while the use of remote sensing is now widely developed, it is rarely applied for detection and classification purposes, specifically in Indonesia. Considering the potential use of the plant, local farmers identify the harvest time by using human inspection, i.e., by identifying the bloom of the flower. Therefore, this study aims to detect sago palms based on their physical morphology from Unmanned Aerial Vehicle (UAV) RGB imagery. Specifically, this paper endeavors to apply the transfer learning approach using three deep pre-trained networks in sago palm tree detection, namely, SqueezeNet, AlexNet, and ResNet-50. The dataset was collected from nine different groups of plants based on the dominant physical features, i.e., leaves, flowers, fruits, and trunks by using a UAV. Typical classes of plants are randomly selected, like coconut and oil palm trees. As a result, the experiment shows that the ResNet-50 model becomes a preferred base model for sago palm classifiers, with a precision of 75%, 78%, and 83% for sago flowers (SF), sago leaves (SL), and sago trunk (ST), respectively. Generally, all of the models perform well for coconut trees, but they still tend to perform less effectively for sago palm and oil palm detection, which is explained by the similarity of the physical appearance of these two palms. Therefore, based our findings, we recommend improving the optimized parameters, thereby providing more varied sago datasets with the same substituted layers designed in this study.https://www.mdpi.com/2072-4292/14/19/4932classificationdeep learningmodelssago |
spellingShingle | Sri Murniani Angelina Letsoin Ratna Chrismiari Purwestri Fajar Rahmawan David Herak Recognition of Sago Palm Trees Based on Transfer Learning Remote Sensing classification deep learning models sago |
title | Recognition of Sago Palm Trees Based on Transfer Learning |
title_full | Recognition of Sago Palm Trees Based on Transfer Learning |
title_fullStr | Recognition of Sago Palm Trees Based on Transfer Learning |
title_full_unstemmed | Recognition of Sago Palm Trees Based on Transfer Learning |
title_short | Recognition of Sago Palm Trees Based on Transfer Learning |
title_sort | recognition of sago palm trees based on transfer learning |
topic | classification deep learning models sago |
url | https://www.mdpi.com/2072-4292/14/19/4932 |
work_keys_str_mv | AT srimurnianiangelinaletsoin recognitionofsagopalmtreesbasedontransferlearning AT ratnachrismiaripurwestri recognitionofsagopalmtreesbasedontransferlearning AT fajarrahmawan recognitionofsagopalmtreesbasedontransferlearning AT davidherak recognitionofsagopalmtreesbasedontransferlearning |