Fusion classification of multispectral and panchromatic image using improved decision tree algorithm

Shingare, Pratibha; Hemane, Priya M.; Dandekar, Duhita S.

doi:10.1109/icspct.2014.6884944

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probabilities, possibilities and evidence theories were checked in [33] to achieve a robust multispectral fusion scheme. Recent studies [34][35][36][37] consider that proper decision fusion would be accomplished with the use of SVM, Bayesian networks and naïve Bayesian classifiers, weights of evidence models and decision tree algorithms, respectively. Furthermore, in [38], scene contextual information was exploited for fusion; in [39], SVM and RF classifiers were used with three adaptively weighted decision procedures; in [40], four non-parametric classifiers, namely decision tree (DT), RF, SVM and multilayer perceptron (MLP) were utilized; and in [41], a fuzzy classification with a weighted sum of the membership of imaged objects was implemented in the final classification decision.…”

Section: Multispectral Datamentioning

confidence: 99%

See 1 more Smart Citation

Decision Fusion at Pixel Level of Multi-Band Data for Land Cover Classification—A Review

Papadopoulos,

Koukiou,

Anastassopoulos

2024

J. Imaging

View full text Add to dashboard Cite

According to existing signatures for various kinds of land cover coming from different spectral bands, i.e., optical, thermal infrared and PolSAR, it is possible to infer about the land cover type having a single decision from each of the spectral bands. Fusing these decisions, it is possible to radically improve the reliability of the decision regarding each pixel, taking into consideration the correlation of the individual decisions of the specific pixel as well as additional information transferred from the pixels’ neighborhood. Different remotely sensed data contribute their own information regarding the characteristics of the materials lying in each separate pixel. Hyperspectral and multispectral images give analytic information regarding the reflectance of each pixel in a very detailed manner. Thermal infrared images give valuable information regarding the temperature of the surface covered by each pixel, which is very important for recording thermal locations in urban regions. Finally, SAR data provide structural and electrical characteristics of each pixel. Combining information from some of these sources further improves the capability for reliable categorization of each pixel. The necessary mathematical background regarding pixel-based classification and decision fusion methods is analytically presented.

show abstract

Section: Multispectral Datamentioning

confidence: 99%

“…Consequently, the memberships for MODIS data are determined using Formula (1)-normalized Euclidean distance (NED). Equation (37) outlines the computation of NED.…”

Section: Classification Of Image Objectsmentioning

confidence: 99%

Decision Fusion at Pixel Level of Multi-Band Data for Land Cover Classification—A Review

Papadopoulos,

Koukiou,

Anastassopoulos

2024

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Urban characteristics are more distinguishable in the Urban Index (UI) compared to the Normalized Difference Built-up Index (NDBI). The most accurate identifications occur when utilizing band 7 rather than band 5 (Bouhennache et al, 2015;Pratibha et al, 2014). As a result, these UI values were employed instead of data from the Normalized Difference Builtup Index (NDBI).…”

Section: 𝑈𝐼 = 𝑆𝑊𝐼𝑅 -𝑁𝐼𝑅 / 𝑆𝑊𝐼𝑅 + 𝑁𝐼𝑅 (2)mentioning

confidence: 99%

Spatial Matrices of Urban Expansion in Lafia, North-Central Nigeria

Medayese,

Magidimisha-Chipungu,

Chipungu

2023

For. Geo.

View full text Add to dashboard Cite

Rapid urbanisation in African cities has caused considerable problems by hindering their ability to meet infrastructure and service needs, resulting in rising land-use consumption. This study examines how land use/land cover change in Lafia, a city in North-central Nigeria, has impacted the city's boundaries between 1999 and 2019 and includes a projection using GIS simulation of land use/ land cover to 2029. The methodology includes remote sensing techniques, spatiotemporal analysis of geographical measurements, and statistical models. This study involved spatial analysis and projection of city growth from 1999 to 2029 in Lafia using GIS. This analysis focuses on the changes in built-up areas, vegetal cover, bare land, and water bodies using land-use/landcover data. The results indicated significant urban expansion and its impact on the city's spatial patterns. The Urban Expansion Differentiation Index (UEDI) and Urban Expansion Intensity Index (UEII)were used to assess urban sprawl and socioeconomic patterns such as population density and density gradient. High residential and employment densities, varied land uses, continuous development, and multi-modal transportation are all important for sustainable urban growth. The study indicates a direct relationship between population growth and urban expansion, as seen in Lafia. Furthermore, the findings suggest that cities grow beyond their typical boundaries, resulting in peri-urban expansion, as shown in the Alakio districts of the Lafia Metropolis. The study findings have important implications for urban growth policy and land use/land cover change. They will contribute to a better understanding of the effects of urban growth on the spatial matrix and morphology of cities, assisting city planners in recognizing these effects. Furthermore, the study adds evidence to the continuing debate about urban expansion, liveability, and spatial sustainability in African cities. The thorough examination of land use/land cover change in Lafia sheds light on the spatial dynamics of urbanisation and its implications for sustainable urban development.

show abstract

“…The first approach involves pan-sharpening the MS data to generate a fused image, followed by classification. Several studies have employed this method, including those by Shackelford and Davis (2003), Castillejo-González et al (2009), Amro et al (2011), Shingare et al (2014), Huang et al (2015Huang et al ( , 2021, Masi et al (2016), Zhong et al (2016), and. The second approach entails extracting distinct features from both the panchromatic (PAN) and MS data, which are subsequently fused for classification.…”

Section: Introductionmentioning

confidence: 99%

Multispectral remote sensing and DANet model improve the precision of urban park vegetation detection: an empirical study in Jinhai Park, Shanghai

Wei,

Cao,

Wang

et al. 2023

Front. Ecol. Evol.

View full text Add to dashboard Cite

IntroductionThe precise detection of vegetation in urban parks is crucial for accurate carbon sink calculations and planting assessments, particularly in high-density cities. Unlike traditional methods designed for forest vegetation, the detection and classification of urban park vegetation face challenges such as unclear boundaries, multiple vegetation categories, low image resolution, labor-intensive manual calculations, and unreliable modeling results. However, by utilizing unmanned aerial vehicles (UAVs) equipped with high-resolution visible and multispectral (MS) remote sensing cameras, it becomes possible to label images with green normalized difference vegetation index (GNDVI) and full-spectral three-channel information.MethodsBy employing a dual attention convolutional neural network (DANet) model that incorporates image fusion, DANet, and feature decoding networks, the high-precision detection of urban park vegetation can be significantly improved.ResultsEmpirical validation carried out in Jinhai Park since 2021 has provided evidence of the effectiveness of the DANet model when utilizing early fusion and feature fusion techniques. This model achieves an accurate detection rate of 88.6% for trees, 92.0% for shrubs, 92.6% for ground cover, and 91.8% for overall vegetation. These detection rates surpass those achieved using only visible images (88.7%) or GNDVI images (86.6%).DiscussionThe enhanced performance can be attributed to the intelligent capabilities of the double-in network. This high-precision detection model provides more precise scientific and technical support for subsequent park carbon sink calculations, assessments of existing vegetation for planting designs, and evaluations of urban ecological impacts.

show abstract

Fusion classification of multispectral and panchromatic image using improved decision tree algorithm

Cited by 11 publications

References 10 publications

Decision Fusion at Pixel Level of Multi-Band Data for Land Cover Classification—A Review

Decision Fusion at Pixel Level of Multi-Band Data for Land Cover Classification—A Review

Spatial Matrices of Urban Expansion in Lafia, North-Central Nigeria

Multispectral remote sensing and DANet model improve the precision of urban park vegetation detection: an empirical study in Jinhai Park, Shanghai

Contact Info

Product

Resources

About