A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

Li, Miao; Zang, Shuying; Zhang, Bing; Li, Shanshan; Wu, Changshan

doi:10.5721/eujrs20144723

Cited by 440 publications

(271 citation statements)

References 120 publications

Supporting

Mentioning

234

Contrasting

Unclassified

Order By: Relevance

“…Numerous methods are presented in the literature which can be categorized based on different criteria, such as pixel-wise, sub-pixel-wise object-based image classification (Li et al 2014). During the past decades, due to the coarse resolution of satellite imagery, the analysis was at the pixel level in most classification techniques.…”

Section: Introductionmentioning

confidence: 99%

“…These techniques were only based on the spectral information of individual pixels. Minimum Distance Classifier, Mahalanobis Distance Classifier, Parallelepiped, Maximum-Likelihood Classifier, Support Vector Machine (SVM), Decision Tree, Random Forest (RF), and Artificial Neural Network are some supervised pixel-based methods (Perakis, Kyrimis, and Kungolos 2000;Deer and Eklund 2003;Dwivedi, Kandrika, and Ramana 2004;Marconcini, Camps-Valls, and Bruzzone 2009;Jiang et al 2012;Adam et al 2014), while ISODATA and K-means are the two most popular unsupervised techniques for remotely sensed data (Zhang, Cao, and Gu 2005;Alajlan et al 2012;Li et al 2014).…”

Section: Introductionmentioning

confidence: 99%

“…As a result, sub-pixel methods, such as fuzzy classification and spectral mixture analysis techniques, have been proposed to address the spectral mixing problem (Adams, Smith, and Johnson 1986;Wu et al 2003;Li et al 2014). Very High-resolution (VHR) sensors can acquire hyperspectral images, and the spectral and spatial information provide the opportunity of better land cover mapping (Bioucas-Dias et al 2013;Fauvel et al 2013;Liu and Bo 2015).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Object-based classification of hyperspectral data using Random Forest algorithm

Amini

Homayouni

Safari

et al. 2018

Geo-spatial Information Science

View full text Add to dashboard Cite

This paper presents a new framework for object-based classification of high-resolution hyperspectral data. This multi-step framework is based on multi-resolution segmentation (MRS) and Random Forest classifier (RFC) algorithms. The first step is to determine of weights of the input features while using the object-based approach with MRS to processing such images. Given the high number of input features, an automatic method is needed for estimation of this parameter. Moreover, we used the Variable Importance (VI), one of the outputs of the RFC, to determine the importance of each image band. Then, based on this parameter and other required parameters, the image is segmented into some homogenous regions. Finally, the RFC is carried out based on the characteristics of segments for converting them into meaningful objects. The proposed method, as well as, the conventional pixel-based RFC and Support Vector Machine (SVM) method was applied to three different hyperspectral data-sets with various spectral and spatial characteristics. These data were acquired by the HyMap, the Airborne Prism Experiment (APEX), and the Compact Airborne Spectrographic Imager (CASI) hyperspectral sensors. The experimental results show that the proposed method is more consistent for land cover mapping in various areas. The overall classification accuracy (OA), obtained by the proposed method was 95.48, 86.57, and 84.29% for the HyMap, the APEX, and the CASI datasets, respectively. Moreover, this method showed better efficiency in comparison to the spectralbased classifications because the OAs of the proposed method was 5.67 and 3.75% higher than the conventional RFC and SVM classifiers, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Object-based classification of hyperspectral data using Random Forest algorithm

Amini

Homayouni

Safari

et al. 2018

Geo-spatial Information Science

View full text Add to dashboard Cite

show abstract

“…Traditionally, the statistical models of classification are used for photogrammetric image recognition, which can be controlled (supervised) or uncontrolled (unsupervised) [6,7]. Figure 3 shows a scheme of the classification methods.…”

Section: Main Partmentioning

confidence: 99%

Conditions and limitations of digital satellite image pre-processing for the further 3D modeling

Hnatushenko

Kavats

Kubanek

et al. 2016

J. Appl. Math. Comput. Mech.

View full text Add to dashboard Cite

Abstract. Today, 3D models of complex urban buildings are one of the most popular applications of 3D modeling. 3D models of complex urban buildings provide high data interpretation that accurately transfers information about objects or area changes and allows one to solve a number of applied tasks. The quality of the 3D models depends on the quality of the initial images and the method of the object recognition. First of all, the 3D-model building requires identification and classification building borders, which requires determination of the building roof form. The article reviews the existing classification and recognition methods for the 3D further modeling.

show abstract

“…Traditional image classification techniques include pixel-based (e.g., supervised Maximum Likelihood Classification (MLC) and unsupervised e.g., K-means or ISODATA), sub-pixel-based (e.g., Fuzzy, neural networks regression modeling, etc. ), and object-based techniques (e.g., segmentation) [28]. Unsupervised classification does not require training data, unlike supervised classification [27].…”

Section: Introductionmentioning

confidence: 99%

Post-War Land Cover Changes and Fragmentation in Halgurd Sakran National Park (HSNP), Kurdistan Region of Iraq

Hamad

Kolo

Balzter

2018

Land

View full text Add to dashboard Cite

Context:The fundamental driving force of land use and land cover (LULC) change is related to spatial and temporal processes caused by human activities such as agricultural expansion and demographic change. Landscape metrics were used to analyze post-war changes in a rural mountain landscape, the protected area of Halgurd-Sakran National Park (HSNP) in north-east Iraq. Therefore, the present work attempts to identify the temporal trends of the most fragmented land cover types between two parts of the national park. Objectives: The objectives of this study are to compare two land cover classification algorithms, maximum likelihood classification (MLC) and random forest (RF) in the upper and lower parts of HSCZ, and to examine whether landscape configuration in the park has changed over time by comparing the fragmentation, connectivity and diversity of LULC classes. Methods: Two Landsat images were used to analyze LULC fragmentation and loss of habitat connectivity (before and after the Fall of Baghdad in 2003). Seven landscape pattern metrics, percentage of land (PLAND), number of patch (NP), largest patch index (LPI), mean patch size (MPS), euclidian nearest neighborhood distance (ENN_AM), interspersion and juxtaposition (IJI) and cohesion at class level were selected to assess landscape composition and configuration. Results: A significant change in LULC classes was noticed in the lower part of the park, especially for pasture, cultivated and forest-lands. The fragmentation trends and their changes were observed in both parts of the park, however, more were observed in the lower part. The inherent causes of these changes are the socio-economic factors created by the 1991-2003 UN post-war economic sanctions. The changes increased during sanctions and decreased afterwards. The fall of Baghdad in 2003, followed by rapid economic boom, marked the greatest cause in land use change, especially in changes-susceptible cultivated areas. Conclusions: Shrinkage of forest patches in the lower part of the park increases the distance between them, which contributes to a decline in biological diversity from decreasing habitat area. Lastly, the results confirm the applicability of the combined method of remote sensing and landscape metrics.

show abstract

A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information

Cited by 440 publications

References 120 publications

Object-based classification of hyperspectral data using Random Forest algorithm

Object-based classification of hyperspectral data using Random Forest algorithm

Conditions and limitations of digital satellite image pre-processing for the further 3D modeling

Post-War Land Cover Changes and Fragmentation in Halgurd Sakran National Park (HSNP), Kurdistan Region of Iraq

Contact Info

Product

Resources

About