Weed Localization: Comparison of Different Transfer Learning Models with U-Net

Neha Shekhawat; Seema Verma; F. H. Juwono; Wong Kitt Wei; Catur Apriono; I. Gde Dharma Nugraha

doi:10.1007/978-981-97-2508-3_1

Weed Localization: Comparison of Different Transfer Learning Models with U-Net

Neha Shekhawat
, Seema Verma
, F. H. Juwono
, Wong Kitt Wei
, Catur Apriono
, I. Gde Dharma Nugraha

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Unwanted plants called weeds challenges the crops for nutrients, water, sunshine, and space in agricultural areas, which lowers crop quality and yield. Farmers have used a variety of techniques and tools to get rid of weeds for millennia. Herbicides are currently being used by farmers to manage weeds, but they are negatively affecting agricultural productivity. Farmers seek to use fewer herbicides to boost crop productivity. To overcome this, precision agriculture is used. To effectively identify weeds in rice fields, unmanned aerial vehicle (UAV) system-based imaging has been used. The usage of UAV and deep learning models has provided effective results in weed detection in the fields. Therefore, in this work, the performance of the UNet model and modified UNet using transfer learning models are analysed to detect weeds using UAV images collected from a rice crop field. U-Net, UNet-VGG16, UNet-VGG19, and UNet-ResNet50 have been compared with the different batch sizes i.e. 16, 32, and 64. Among this UNet-VGG19 95.51% with a batch size of 16 outperformed. Precision, Recall, and F1-score were also considered to analyze the results.

Original language	English
Title of host publication	Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023
Editors	K.C. Santosh, Sandeep Kumar Sood, Hari Mohan Pandey, Charu Virmani
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1-14
Number of pages	14
ISBN (Print)	9789819725076
DOIs	https://doi.org/10.1007/978-981-97-2508-3_1
Publication status	Published - 2024
Event	3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023 - Faridabad, India Duration: 14 Jul 2023 → 15 Jul 2023

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1191 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023
Country/Territory	India
City	Faridabad
Period	14/07/23 → 15/07/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 2 Zero Hunger

Keywords

U-Net, UNet-VGG16, UNet-VGG19 and UNet-ResNet50
Unmanned aerial vehicle (UAV)
Weed detection

Access to Document

10.1007/978-981-97-2508-3_1

Cite this

Shekhawat, N., Verma, S., Juwono, F. H., Wei, W. K., Apriono, C., & Gde Dharma Nugraha, I. (2024). Weed Localization: Comparison of Different Transfer Learning Models with U-Net. In K. C. Santosh, S. K. Sood, H. M. Pandey, & C. Virmani (Eds.), Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023 (pp. 1-14). (Lecture Notes in Electrical Engineering; Vol. 1191 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-2508-3_1

Shekhawat, Neha ; Verma, Seema ; Juwono, F. H. et al. / Weed Localization : Comparison of Different Transfer Learning Models with U-Net. Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023. editor / K.C. Santosh ; Sandeep Kumar Sood ; Hari Mohan Pandey ; Charu Virmani. Springer Science and Business Media Deutschland GmbH, 2024. pp. 1-14 (Lecture Notes in Electrical Engineering).

@inproceedings{f5cfbfdac3f649f6a739acc666d6dcc0,

title = "Weed Localization: Comparison of Different Transfer Learning Models with U-Net",

abstract = "Unwanted plants called weeds challenges the crops for nutrients, water, sunshine, and space in agricultural areas, which lowers crop quality and yield. Farmers have used a variety of techniques and tools to get rid of weeds for millennia. Herbicides are currently being used by farmers to manage weeds, but they are negatively affecting agricultural productivity. Farmers seek to use fewer herbicides to boost crop productivity. To overcome this, precision agriculture is used. To effectively identify weeds in rice fields, unmanned aerial vehicle (UAV) system-based imaging has been used. The usage of UAV and deep learning models has provided effective results in weed detection in the fields. Therefore, in this work, the performance of the UNet model and modified UNet using transfer learning models are analysed to detect weeds using UAV images collected from a rice crop field. U-Net, UNet-VGG16, UNet-VGG19, and UNet-ResNet50 have been compared with the different batch sizes i.e. 16, 32, and 64. Among this UNet-VGG19 95.51\% with a batch size of 16 outperformed. Precision, Recall, and F1-score were also considered to analyze the results.",

keywords = "U-Net, UNet-VGG16, UNet-VGG19 and UNet-ResNet50, Unmanned aerial vehicle (UAV), Weed detection",

author = "Neha Shekhawat and Seema Verma and Juwono, \{F. H.\} and Wei, \{Wong Kitt\} and Catur Apriono and \{Gde Dharma Nugraha\}, I.",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023 ; Conference date: 14-07-2023 Through 15-07-2023",

year = "2024",

doi = "10.1007/978-981-97-2508-3\_1",

language = "English",

isbn = "9789819725076",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1--14",

editor = "K.C. Santosh and Sood, \{Sandeep Kumar\} and Pandey, \{Hari Mohan\} and Charu Virmani",

booktitle = "Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023",

address = "Germany",

}

Shekhawat, N, Verma, S, Juwono, FH, Wei, WK, Apriono, C & Gde Dharma Nugraha, I 2024, Weed Localization: Comparison of Different Transfer Learning Models with U-Net. in KC Santosh, SK Sood, HM Pandey & C Virmani (eds), Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023. Lecture Notes in Electrical Engineering, vol. 1191 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 1-14, 3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023, Faridabad, India, 14/07/23. https://doi.org/10.1007/978-981-97-2508-3_1

Weed Localization: Comparison of Different Transfer Learning Models with U-Net. / Shekhawat, Neha; Verma, Seema; Juwono, F. H. et al.
Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023. ed. / K.C. Santosh; Sandeep Kumar Sood; Hari Mohan Pandey; Charu Virmani. Springer Science and Business Media Deutschland GmbH, 2024. p. 1-14 (Lecture Notes in Electrical Engineering; Vol. 1191 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Weed Localization

T2 - 3rd International Conference on Artificial-Business Analytics, Quantum and Machine Learning: Trends, Perspectives, and Prospects, Com-IT-Con 2023

AU - Shekhawat, Neha

AU - Verma, Seema

AU - Juwono, F. H.

AU - Wei, Wong Kitt

AU - Apriono, Catur

AU - Gde Dharma Nugraha, I.

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - Unwanted plants called weeds challenges the crops for nutrients, water, sunshine, and space in agricultural areas, which lowers crop quality and yield. Farmers have used a variety of techniques and tools to get rid of weeds for millennia. Herbicides are currently being used by farmers to manage weeds, but they are negatively affecting agricultural productivity. Farmers seek to use fewer herbicides to boost crop productivity. To overcome this, precision agriculture is used. To effectively identify weeds in rice fields, unmanned aerial vehicle (UAV) system-based imaging has been used. The usage of UAV and deep learning models has provided effective results in weed detection in the fields. Therefore, in this work, the performance of the UNet model and modified UNet using transfer learning models are analysed to detect weeds using UAV images collected from a rice crop field. U-Net, UNet-VGG16, UNet-VGG19, and UNet-ResNet50 have been compared with the different batch sizes i.e. 16, 32, and 64. Among this UNet-VGG19 95.51% with a batch size of 16 outperformed. Precision, Recall, and F1-score were also considered to analyze the results.

AB - Unwanted plants called weeds challenges the crops for nutrients, water, sunshine, and space in agricultural areas, which lowers crop quality and yield. Farmers have used a variety of techniques and tools to get rid of weeds for millennia. Herbicides are currently being used by farmers to manage weeds, but they are negatively affecting agricultural productivity. Farmers seek to use fewer herbicides to boost crop productivity. To overcome this, precision agriculture is used. To effectively identify weeds in rice fields, unmanned aerial vehicle (UAV) system-based imaging has been used. The usage of UAV and deep learning models has provided effective results in weed detection in the fields. Therefore, in this work, the performance of the UNet model and modified UNet using transfer learning models are analysed to detect weeds using UAV images collected from a rice crop field. U-Net, UNet-VGG16, UNet-VGG19, and UNet-ResNet50 have been compared with the different batch sizes i.e. 16, 32, and 64. Among this UNet-VGG19 95.51% with a batch size of 16 outperformed. Precision, Recall, and F1-score were also considered to analyze the results.

KW - U-Net, UNet-VGG16, UNet-VGG19 and UNet-ResNet50

KW - Unmanned aerial vehicle (UAV)

KW - Weed detection

UR - https://www.scopus.com/pages/publications/85205343273

U2 - 10.1007/978-981-97-2508-3_1

DO - 10.1007/978-981-97-2508-3_1

M3 - Conference contribution

AN - SCOPUS:85205343273

SN - 9789819725076

T3 - Lecture Notes in Electrical Engineering

SP - 1

EP - 14

BT - Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023

A2 - Santosh, K.C.

A2 - Sood, Sandeep Kumar

A2 - Pandey, Hari Mohan

A2 - Virmani, Charu

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 14 July 2023 through 15 July 2023

ER -

Shekhawat N, Verma S, Juwono FH, Wei WK, Apriono C , Gde Dharma Nugraha I. Weed Localization: Comparison of Different Transfer Learning Models with U-Net. In Santosh KC, Sood SK, Pandey HM, Virmani C, editors, Advances in Artificial-Business Analytics and Quantum Machine Learning - Select Proceedings of the 3rd International Conference, Com-IT-Con 2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 1-14. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-97-2508-3_1

Weed Localization: Comparison of Different Transfer Learning Models with U-Net

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this