Change Detection in Optical Satellite Images Based on Local Binary Similarity Pattern Technique

Gupta, Neha; Pillai, Gargi V.; Ari, Samit

doi:10.1109/lgrs.2018.2789404

Cited by 22 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method was not applicable in case of the large-scale annotated data set. Neha Gupta et al [5] used an approach based on the binary descriptor to detect the change using the bitemporal optical satellite images that enabled the smoother visual outcomes. The drawback of the method was that it formed long codes to make the LBSP codes statistically weak.…”

Section: Literature Reviewmentioning

confidence: 99%

A Forest Change Detection using auto Regressive Model-Based Kernel Fuzzy Clustering

Mulik,

Jayashree,

Kulkarni

2019

IJEAT

View full text Add to dashboard Cite

Satellite images are used for applications related to the forest change detection, forest cover management, and so on as remote sensing provides the rich source of information for change detection. In this paper, the vegetation indices play a major role in extracting the useful information from the satellite images and the commonly employed indices. This paper analyzes the imagery data from the remote sensing satellites for detecting the changes in the forest over the year’s 2007-2017 using the pixel-based Bhattacharya distance. The indices from the satellite images are fed to the automatic segmentation model using the proposed Kernel Fuzzy Auto regressive (KFAR) model, which is the modified Kernel Fuzzy C-Means (KFCM) Clustering algorithm with the Conditional Autoregressive Value at Risk (CAVIAR). The forest change detection using the pixel-based Bhattacharya distance follows the segmentation, and the experimentation reveals that the proposed method acquired the minimal MSE and maximal accuracy of 0.0581 and 0.9211.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Forest Change Detection using auto Regressive Model-Based Kernel Fuzzy Clustering

Mulik,

Jayashree,

Kulkarni

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…It benefits HR RS imagery with high spatial heterogeneity and great uncertainty in change detection. There are many methods for capturing spatial context information in RS imagery, such as the neighborhood window [28], Markov random field (MRF) [29], Gabor wavelet transform [30], local binary pattern (LBP) [31], and hypergraph [32]. Among these, LBP has the advantage of grayscale invariance [33].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Change Detection in HR Remote Sensing Imagery Based on Local Histogram Similarity and Progressive Otsu

Shen,

Wei,

Zhang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Unsupervised change detection of land cover in multispectral satellite remote sensing images with a spatial resolution of 2–5 m has always been a challenging task. This paper presents a method of detecting land cover changes in high-spatial-resolution remote sensing imagery. This method has three characteristics: (1) Extended center-symmetric local binary pattern (XCS-LBP) is used to extract image features to emphasize spatial context information in initial change detection. Then, spectral information is combined to improve the accuracy of change detection. (2) The local histogram distance of XCS-LBP features is used as the change vector to improve the expression of change information. (3) A progressive Otsu method is developed for threshold segmentation of the change vector to reduce the false detection rate. Four datasets with different landscape complexities and seven state-of-the-art unsupervised change detection methods were used to test the performance of the proposed method. Quantitative results showed that the proposed method reduced the false detection rate and improved the accuracy of the detection of land cover changes. The F1 score achieved by the proposed method reached 0.8688, 0.8867, 0.7725, and 0.6634, respectively, which are higher than the highest corresponding F1 score achieved by the benchmark methods (0.8533, 0.8549, 0.6545, and 0.5895, respectively).

show abstract

“…In [1], an innovative methodology was proposed for change detection by analyzing pairs of cross-sharpened images which effectively reduced the overestimation of changed areas. Gupta et al [2] implemented the Local Binary Similarity Pattern (LBSP) technique to identify changes in optical satellite images. In this method, a novel threshold technique based on the Hamming distance is proposed to create binary feature vectors and binary change maps.…”

Section: Introductionmentioning

confidence: 99%

A PSO-SVM-Based Change Detection Algorithm for Remote Sensing Optical Images

Shah,

Gupta,

Paul

2024

IEEE Access

View full text Add to dashboard Cite

Change detection is considered as one of the challenging issues in the field of remote sensing. The multi-temporal images used to detect the changes generally have significant illumination variations which affect the performance of a change detection method. To address this issue, a machine learning (ML)based change detection algorithm is proposed for the remote sensing optical images. The proposed method is a combination of Support Vector Machines (SVM) and Particle Swarm Optimization (PSO). In this method, the PSO is utilized in a novel way to provide the optimized feature vectors. These feature vectors are used in SVM to accurately determine the changed and unchanged pixels. The proposed method is very effective in identifying the changes in remote sensing optical images having significant illumination variations. It can give comparatively higher correct classification (PCC) values, and lower false alarm (PFA) as well as total error (PTE) values than the state-of-the-art methods. Experiments on six pairs of Landsat images demonstrate the effectiveness of the proposed method.INDEX TERMS Machine Learning (ML), Particle Swarm Optimization (PSO) and Support Vector Machines (SVM).

show abstract

Change Detection in Optical Satellite Images Based on Local Binary Similarity Pattern Technique

Cited by 22 publications

References 15 publications

A Forest Change Detection using auto Regressive Model-Based Kernel Fuzzy Clustering

A Forest Change Detection using auto Regressive Model-Based Kernel Fuzzy Clustering

Unsupervised Change Detection in HR Remote Sensing Imagery Based on Local Histogram Similarity and Progressive Otsu

A PSO-SVM-Based Change Detection Algorithm for Remote Sensing Optical Images

Contact Info

Product

Resources

About