An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios

Machine vision has significant advantages in a wide range of agricultural applications; however, acquiring a large number of high-quality image resources is often challenging in actual agricultural production due to environmental and equipment conditions. Therefore, crop image augmentation technique...

Full description

Saved in:
Bibliographic Details
Main Authors: Peng Lu, Wengang Zheng, Xinyue Lv, Jiu Xu, Shirui Zhang, Youli Li, Lili Zhangzhong
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/14/11/1893
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154821462130688
author Peng Lu
Wengang Zheng
Xinyue Lv
Jiu Xu
Shirui Zhang
Youli Li
Lili Zhangzhong
author_facet Peng Lu
Wengang Zheng
Xinyue Lv
Jiu Xu
Shirui Zhang
Youli Li
Lili Zhangzhong
author_sort Peng Lu
collection DOAJ
description Machine vision has significant advantages in a wide range of agricultural applications; however, acquiring a large number of high-quality image resources is often challenging in actual agricultural production due to environmental and equipment conditions. Therefore, crop image augmentation techniques are particularly important in crop growth analysis. In this paper, greenhouse tomato plants were used as research subjects to collect images of their different fertility stages with flowers and fruits. Due to the different durations of each fertility period, there is a significant difference in the number of images collected. For this reason, this paper proposes a method for balanced amplification of significant feature information in images based on geometric position. Through the geometric position information of the target in the image, different segmentation strategies are used to process the image and supervised and unsupervised methods are applied to perform balanced augmentation of the image, which is combined with the YOLOv7 algorithm to verify the augmentation effect. In terms of the image dataset, the mixed image dataset (Mix) is supplemented with mobile phone images on top of in situ monitoring images, with precision increased from 70.33% to 82.81% and recall increased from 69.15% to 81.25%. In terms of image augmentation, after supervised balanced amplification, the detection accuracy is improved from 70.33% to 77.29%, which is suitable for supervised balanced amplification. For the mobile phone dataset (MP), after amplification, it was found that better results could be achieved without any amplification method. The detection accuracy of the mixed dataset with different data sources matching the appropriate amplification method increased slightly from 82.81% to 83.59%, and accurate detection could be achieved when the target was shaded by the plant, and in different environments and light conditions.
format Article
id doaj-art-0dc1c2f9955640e49db7ef4409f0d90b
institution Kabale University
issn 2077-0472
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-0dc1c2f9955640e49db7ef4409f0d90b2024-11-26T17:43:14ZengMDPI AGAgriculture2077-04722024-10-011411189310.3390/agriculture14111893An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing ScenariosPeng Lu0Wengang Zheng1Xinyue Lv2Jiu Xu3Shirui Zhang4Youli Li5Lili Zhangzhong6College of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, ChinaIntelligent Equipment Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaMachine vision has significant advantages in a wide range of agricultural applications; however, acquiring a large number of high-quality image resources is often challenging in actual agricultural production due to environmental and equipment conditions. Therefore, crop image augmentation techniques are particularly important in crop growth analysis. In this paper, greenhouse tomato plants were used as research subjects to collect images of their different fertility stages with flowers and fruits. Due to the different durations of each fertility period, there is a significant difference in the number of images collected. For this reason, this paper proposes a method for balanced amplification of significant feature information in images based on geometric position. Through the geometric position information of the target in the image, different segmentation strategies are used to process the image and supervised and unsupervised methods are applied to perform balanced augmentation of the image, which is combined with the YOLOv7 algorithm to verify the augmentation effect. In terms of the image dataset, the mixed image dataset (Mix) is supplemented with mobile phone images on top of in situ monitoring images, with precision increased from 70.33% to 82.81% and recall increased from 69.15% to 81.25%. In terms of image augmentation, after supervised balanced amplification, the detection accuracy is improved from 70.33% to 77.29%, which is suitable for supervised balanced amplification. For the mobile phone dataset (MP), after amplification, it was found that better results could be achieved without any amplification method. The detection accuracy of the mixed dataset with different data sources matching the appropriate amplification method increased slightly from 82.81% to 83.59%, and accurate detection could be achieved when the target was shaded by the plant, and in different environments and light conditions.https://www.mdpi.com/2077-0472/14/11/1893image equalisation amplificationinformation on salient featuressupervised and unsupervisedequalisation amplificationaccurate detection
spellingShingle Peng Lu
Wengang Zheng
Xinyue Lv
Jiu Xu
Shirui Zhang
Youli Li
Lili Zhangzhong
An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios
Agriculture
image equalisation amplification
information on salient features
supervised and unsupervised
equalisation amplification
accurate detection
title An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios
title_full An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios
title_fullStr An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios
title_full_unstemmed An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios
title_short An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios
title_sort extended method based on the geometric position of salient image features solving the dataset imbalance problem in greenhouse tomato growing scenarios
topic image equalisation amplification
information on salient features
supervised and unsupervised
equalisation amplification
accurate detection
url https://www.mdpi.com/2077-0472/14/11/1893
work_keys_str_mv AT penglu anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT wengangzheng anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT xinyuelv anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT jiuxu anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT shiruizhang anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT youlili anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT lilizhangzhong anextendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT penglu extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT wengangzheng extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT xinyuelv extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT jiuxu extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT shiruizhang extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT youlili extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios
AT lilizhangzhong extendedmethodbasedonthegeometricpositionofsalientimagefeaturessolvingthedatasetimbalanceproblemingreenhousetomatogrowingscenarios