Spectral Indexes Evaluation for Satellite Images Classification using CNN

Yaloveha, Vladyslav; Hlavcheva, Daria; Podorozhniak, Andrii

doi:10.31341/jios.45.2.5

Cited by 9 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar increase in OA by fusing VIs was also reported in other studies (between 3-6.7 pp) when using satellite images (Worldview, Sentinel 2) for species classification in urban trees or mountainous protected area [61,63,65]. Hence, fusing Vis, when available, could improve CNN classifiers.…”

Section: The Effects Of Fusing Vis On the Accuracy Of Species Classif...supporting

confidence: 82%

A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings

Imangholiloo,

Luoma,

Holopainen

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Tree species information is important for forest management, especially in seedling stands. To mitigate the spectral admixture of understory reflectance with small and lesser foliaged seedling canopies, we proposed an image pre-processing step based on the canopy threshold (Cth) applied on drone-based multispectral images prior to feeding classifiers. This study focused on (1) improving the classification of seedlings by applying the introduced technique; (2) comparing the classification accuracies of the convolutional neural network (CNN) and random forest (RF) methods; and (3) improving classification accuracy by fusing vegetation indices to multispectral data. A classification of 5417 field-located seedlings from 75 sample plots showed that applying the Cth technique improved the overall accuracy (OA) of species classification from 75.7% to 78.5% on the Cth-affected subset of the test dataset in CNN method (1). The OA was more accurate in CNN (79.9%) compared to RF (68.3%) (2). Moreover, fusing vegetation indices with multispectral data improved the OA from 75.1% to 79.3% in CNN (3). Further analysis revealed that shorter seedlings and tensors with a higher proportion of Cth-affected pixels have negative impacts on the OA in seedling forests. Based on the obtained results, the proposed method could be used to improve species classification of single-tree detected seedlings in operational forest inventory.

show abstract

Section: The Effects Of Fusing Vis On the Accuracy Of Species Classif...supporting

confidence: 82%

A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings

Imangholiloo,

Luoma,

Holopainen

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…To determine changes of forest cover, generalpurpose characteristics of vegetation is needed. This characteristic is Normalized Difference Vegetation Index (NDVI) [14,15]. Only two of eleven bands are used to calculate this index:…”

Section: Datasetmentioning

confidence: 99%

Performance Comparison of U-Net and Linknet With Different Encoders for Reforestation Detection

Podorozhniak,

Onishchenko,

Liubchenko

et al. 2024

A.I.S.

View full text Add to dashboard Cite

The subject of study is analysis of performance of artificial intelligence systems with different architectures for reforestation detection. The goal is to implement, train and evaluate system with different models for deforestation and reforestation detection. The tasks are to study problems and potential solutions in forestry for reforestation detection and present own solution. As part of model comparison, results are presented for different artificial neural network architectures with different encoders. For training and testing purpose custom dataset was created, which includes different areas of territory of Ukraine within different timestamps. Main research methods are literature analysis, experiment and case study. As a result of analysis of modern artificial intelligence methods, machine learning, deep learning and convolutional neural networks, high-precision algorithms U-Net and LinkNet were chosen for system implementation. Conclusions. The studied problem was stated formally and broken down in smaller steps; possible solutions were studied and proposed solution was described in details. Necessary mathematical background for analysis of the performance was provided. As part of the development, accurate deforestation/reforestation module was created. All analysis results were listed and a comparison of the studied algorithms was presented.

show abstract

“…In the context of land classification, this technique can be used to automatically identify and map different land cover types, such as forests, croplands, urban areas, and water bodies, from satellite imagery. There are various popular image classification algorithms that are used in practice, including convolutional neural networks (CNNs) [17,18], support vector machines (SVMs) [19,20], and vision transformers (ViT) [21,22]. Each of these algorithms has their own unique strengths and weaknesses, and they have been shown to generalize well to unseen data.…”

Section: Image Classificationmentioning

confidence: 99%

Automated Detection and Analysis of Massive Mining Waste Deposits Using Sentinel-2 Satellite Imagery and Artificial Intelligence

Silva,

Hermosilla,

Villavicencio

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

This article presents a method to detect and segment mine waste deposits, specifically waste rock dumps and leaching wasted dumps, in Sentinel-2 satellite imagery using artificial intelligence. This challenging task has important implications for mining companies and regulators like the National Geology and Mining Service in Chile. Challenges include limited knowledge of mine waste deposit numbers, as well as logistical and technical difficulties in conducting inspections and surveying physical stability parameters. The proposed method combines YOLOv7 object detection with a vision transformer classifier to locate mine waste deposits, as well as a deep generative model for data augmentation to enhance detection and segmentation accuracy. The ViT classifier achieved 98% accuracy in differentiating five satellite imagery scene types, while the YOLOv7 model achieved an average precision of 81% for detection and 79% for segmentation of mine waste deposits. Finally, the model was used to calculate mine waste deposit areas, with an absolute error of 6.6% compared to Google Earth API results.

show abstract

Spectral Indexes Evaluation for Satellite Images Classification using CNN

Cited by 9 publications

References 23 publications

A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings

A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings

Performance Comparison of U-Net and Linknet With Different Encoders for Reforestation Detection

Automated Detection and Analysis of Massive Mining Waste Deposits Using Sentinel-2 Satellite Imagery and Artificial Intelligence

Contact Info

Product

Resources

About