Classification of complex environments using pixel level fusion of satellite data

Vibhute, Amol D.; Kale, K. V.; Gaikwad, Sandeep V.; Dhumal, Rajesh K.; Nagne, Ajay D.; Varpe, Amarsinh B.; Nalawade, Dhananjay B.; Mehrotra, S. C.

doi:10.1007/s11042-020-08978-4

Cited by 13 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The discriminant functions that need to be applied to each pixel of a picture to attain maximum likelihood classification are found using Eq. 5 [24], [27].…”

Section: ) Maximum Likelihood Classificationmentioning

confidence: 99%

“…The testing samples were used to perform the accuracy assessment. The confusion matrix has been used in conjunction with the kappa coefficient to produce PA, OA, and user's accuracy (UA) [24]. The efficacy of each class was evaluated using the producers' and users' accuracy methodologies.…”

Section: Analyzing the Accuracy Of The Classificationmentioning

confidence: 99%

“…The implemented methodology's workflow B. NDVI-based crop feature extraction:A useful tool for distinguishing between areas that are not vegetated and those that are, as well as among living and dead vegetation, is a vegetation index. Among the most popular indices used in several types of research is the NDVI[24]. Consequently, the NDVI approach was used in the current study to extract the crop features for every category of interest from Sentinel-2 data.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Mapping Crop Types At a 10 m Scale Using Sentinel-2 Data and Machine Learning Methods

Khan,

H. Patil,

D. Vibhute

et al. 2024

IJCDS

View full text Add to dashboard Cite

Crop classification plays a vital role in crop status monitoring, crop area estimation, and food production. Remote sensing data is widely accepted for crop classification at remote locations. However, crop classification is challenging due to spectral and spatial similarities, complex land structures, temporal inconsistencies, and environmental parameters. Machine learning models must be robust, particularly when dealing with a variety of crop types and changing environmental factors. This study examines the extent to which various algorithms generalize, emphasizing the importance of adaptability to various farming systems and geographical conditions. It explores transfer learning and ensemble approaches as possible ways to improve the resilience and flexibility of the model. In the present study, an effort has been made to identify, classify, and map multiple crops from the complex environment using the Sentinel-2 dataset and advanced machine learning methods such as random forest, Spectral Angle Mapper (SAM), Maximum Likelihood Classifier (MLC), K-means clustering and Iterative Self-Organizing Data Analysis Technique (ISODATA). The crop spectral features were identified using the Normalized Difference Vegetation Index (NDVI). The NDVI outcomes ranged between -0.91 and 0.54, which were then used to identify crop areas. Ground reference data, Google map, and Google Earth data were used to determine the crop classes, train the data, and validate the results. The five major crops viz. Cotton, Paddy, Orchard, Yellow split Pigeon peas, Chickpeas, and Other crops were identified and classified efficiently. According to the experimental results, the random forest approach had the best overall accuracy, 87.71%, and a kappa value of 0.86 than other methods. Alternatively, the ISODATA method provided an overall accuracy of 85.01% with a kappa value of 0.82. The agricultural decision-makers can use the results of this study for decision-making and management.

show abstract

“…The discriminant functions that need to be applied to each pixel of a picture to attain maximum likelihood classification are found using Eq. 5 [24], [27].…”

Section: ) Maximum Likelihood Classificationmentioning

confidence: 99%

Section: Analyzing the Accuracy Of The Classificationmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Mapping Crop Types At a 10 m Scale Using Sentinel-2 Data and Machine Learning Methods

Khan,

H. Patil,

D. Vibhute

et al. 2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…In the present study, we have used a pixel-based machine learning classification approach using SVM. The SVM is a statistical non-parametric method based on a supervised process [10] that requires very few training pixels to produce better accuracy. In addition, SVM works superior in the spectral feature change of the road material and intensity change [11].…”

Section: Svm Based Image Classificationmentioning

confidence: 99%

“…Thus, the binary SVM approach is computed directly for roads and non-roads types in the present study. The SVM method based on Radial Basis Function (RBF) kernel [10,12] has been used due to its high performance to classify the hyperspectral image into two classes, i.e., road and others using sufficient training pixels with Eq. ( 1).…”

Section: Svm Based Image Classificationmentioning

confidence: 99%

Machine Learning Approach for Road-Line Extraction in Complex Urban Environments from High-Resolution Hyperspectral Image

Vibhute¹,

Kale²,

Gaikwad³

et al. 2023

Advances in Intelligent Systems Research

Self Cite

View full text Add to dashboard Cite

Road network extraction and road line extraction from remote sensing images is still challenging task due to the complex structure of urban areas. The spectral response, design, shape, size, shadow, a contrast of roads, and other urban features are similar, which causes inaccurate results. The present paper investigates the asphalt road line extraction from high spatial-spectral resolution hyperspectral imagery. The implemented approach is based on a machine-learning algorithm, i.e., Support Vector Machines (SVM), structural information, and road line filtering. Road and non-road classification have been done using the SVM algorithm, generating a road map. In the second step, mathematical morphology was used to extract the road network with enhanced precision. Unwanted material has been removed using the granulometry approach. Finally, accurate and comprehensive road line extraction has been done by median filtering. The results have shown 85.13% correctness with 79.93% completeness of the implemented methodology. The experimental results are helpful for transportation analysis, traffic management, cartography, urban planning, and its management.

show abstract

Multi-focus image fusion using edge discriminative diffusion filter for satellite images

Fiza,

Safinaz

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Classification of complex environments using pixel level fusion of satellite data

Cited by 13 publications

References 28 publications

Mapping Crop Types At a 10 m Scale Using Sentinel-2 Data and Machine Learning Methods

Mapping Crop Types At a 10 m Scale Using Sentinel-2 Data and Machine Learning Methods

Machine Learning Approach for Road-Line Extraction in Complex Urban Environments from High-Resolution Hyperspectral Image

Multi-focus image fusion using edge discriminative diffusion filter for satellite images

Contact Info

Product

Resources

About