Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification
The automatic identification of plant species using unmanned aerial vehicles (UAVs) is a valuable tool for ecological research. However, challenges such as reduced spatial resolution due to high-altitude operations, image degradation from camera optics and sensor limitations, and information loss ca...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/8/11/645 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846153727966183424 |
|---|---|
| author | Girma Tariku Isabella Ghiglieno Anna Simonetto Fulvio Gentilin Stefano Armiraglio Gianni Gilioli Ivan Serina |
| author_facet | Girma Tariku Isabella Ghiglieno Anna Simonetto Fulvio Gentilin Stefano Armiraglio Gianni Gilioli Ivan Serina |
| author_sort | Girma Tariku |
| collection | DOAJ |
| description | The automatic identification of plant species using unmanned aerial vehicles (UAVs) is a valuable tool for ecological research. However, challenges such as reduced spatial resolution due to high-altitude operations, image degradation from camera optics and sensor limitations, and information loss caused by terrain shadows hinder the accurate classification of plant species from UAV imagery. This study addresses these issues by proposing a novel image preprocessing pipeline and evaluating its impact on model performance. Our approach improves image quality through a multi-step pipeline that includes Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) for resolution enhancement, Contrast-Limited Adaptive Histogram Equalization (CLAHE) for contrast improvement, and white balance adjustments for accurate color representation. These preprocessing steps ensure high-quality input data, leading to better model performance. For feature extraction and classification, we employ a pre-trained VGG-16 deep convolutional neural network, followed by machine learning classifiers, including Support Vector Machine (SVM), random forest (RF), and Extreme Gradient Boosting (XGBoost). This hybrid approach, combining deep learning for feature extraction with machine learning for classification, not only enhances classification accuracy but also reduces computational resource requirements compared to relying solely on deep learning models. Notably, the VGG-16 + SVM model achieved an outstanding accuracy of 97.88% on a dataset preprocessed with ESRGAN and white balance adjustments, with a precision of 97.9%, a recall of 97.8%, and an F1 score of 0.978. Through a comprehensive comparative study, we demonstrate that the proposed framework, utilizing VGG-16 for feature extraction, SVM for classification, and preprocessed images with ESRGAN and white balance adjustments, achieves superior performance in plant species identification from UAV imagery. |
| format | Article |
| id | doaj-art-6794512fa3c54b8e9c1ab337b41110da |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-6794512fa3c54b8e9c1ab337b41110da2024-11-26T18:00:41ZengMDPI AGDrones2504-446X2024-11-0181164510.3390/drones8110645Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image ClassificationGirma Tariku0Isabella Ghiglieno1Anna Simonetto2Fulvio Gentilin3Stefano Armiraglio4Gianni Gilioli5Ivan Serina6Department of Information Engineering (DII), University of Brescia, Via Branze 38, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering and Mathematics, University of Brescia, Via Branze 43, 25123 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering and Mathematics, University of Brescia, Via Branze 43, 25123 Brescia, ItalyRiD Lab, Department of Civil, Environmental, Architectural Engineering and Mathematics, University of Brescia, Via Branze 43, 25123 Brescia, ItalyMuseum of Natural Sciences, 25128 Brescia, ItalyAgrofood Research Hub, Department of Civil, Environmental, Architectural Engineering and Mathematics, University of Brescia, Via Branze 43, 25123 Brescia, ItalyDepartment of Information Engineering (DII), University of Brescia, Via Branze 38, 25123 Brescia, ItalyThe automatic identification of plant species using unmanned aerial vehicles (UAVs) is a valuable tool for ecological research. However, challenges such as reduced spatial resolution due to high-altitude operations, image degradation from camera optics and sensor limitations, and information loss caused by terrain shadows hinder the accurate classification of plant species from UAV imagery. This study addresses these issues by proposing a novel image preprocessing pipeline and evaluating its impact on model performance. Our approach improves image quality through a multi-step pipeline that includes Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) for resolution enhancement, Contrast-Limited Adaptive Histogram Equalization (CLAHE) for contrast improvement, and white balance adjustments for accurate color representation. These preprocessing steps ensure high-quality input data, leading to better model performance. For feature extraction and classification, we employ a pre-trained VGG-16 deep convolutional neural network, followed by machine learning classifiers, including Support Vector Machine (SVM), random forest (RF), and Extreme Gradient Boosting (XGBoost). This hybrid approach, combining deep learning for feature extraction with machine learning for classification, not only enhances classification accuracy but also reduces computational resource requirements compared to relying solely on deep learning models. Notably, the VGG-16 + SVM model achieved an outstanding accuracy of 97.88% on a dataset preprocessed with ESRGAN and white balance adjustments, with a precision of 97.9%, a recall of 97.8%, and an F1 score of 0.978. Through a comprehensive comparative study, we demonstrate that the proposed framework, utilizing VGG-16 for feature extraction, SVM for classification, and preprocessed images with ESRGAN and white balance adjustments, achieves superior performance in plant species identification from UAV imagery.https://www.mdpi.com/2504-446X/8/11/645deep learning (VGG-16)image preprocessingmachine learning classifiersplant species identificationunmanned aerial vehicles (UAVs) |
| spellingShingle | Girma Tariku Isabella Ghiglieno Anna Simonetto Fulvio Gentilin Stefano Armiraglio Gianni Gilioli Ivan Serina Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification Drones deep learning (VGG-16) image preprocessing machine learning classifiers plant species identification unmanned aerial vehicles (UAVs) |
| title | Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification |
| title_full | Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification |
| title_fullStr | Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification |
| title_full_unstemmed | Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification |
| title_short | Advanced Image Preprocessing and Integrated Modeling for UAV Plant Image Classification |
| title_sort | advanced image preprocessing and integrated modeling for uav plant image classification |
| topic | deep learning (VGG-16) image preprocessing machine learning classifiers plant species identification unmanned aerial vehicles (UAVs) |
| url | https://www.mdpi.com/2504-446X/8/11/645 |
| work_keys_str_mv | AT girmatariku advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification AT isabellaghiglieno advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification AT annasimonetto advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification AT fulviogentilin advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification AT stefanoarmiraglio advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification AT giannigilioli advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification AT ivanserina advancedimagepreprocessingandintegratedmodelingforuavplantimageclassification |