Automatic Change Analysis in Satellite Images Using Binary Descriptors and Lloyd–Max Quantization

Abstract

In this letter, we present a novel technique for unsupervised change analysis that leads to a method of ranking the changes that occur between two satellite images acquired at different moments of time. The proposed change analysis is based on binary descriptors and uses the Hamming distance as a similarity metric. In order to render a completely unsupervised solution, the obtained distances are further classified using vector quantization methods (i.e., Lloyd's algorithm for optimal quantization). The ultimate goal in the change analysis chain is to build change intensity maps that provide an overview of the severeness of changes in the area under analysis. In addition, the proposed analysis technique can be easily adapted for change detection by selecting only two levels for quantization. This discriminative method (i.e., between changed/unchanged zones) is compared with other previously developed techniques that use principal component analysis or Bayes theory as starting points for their analysis. The experiments are carried on Landsat images at a 30-m spatial resolution, covering an area of approximately 59 × 51 km 2 over the surroundings of Bucharest, Romania, and containing multispectral information.

Retrieval of Similar Evolution Patterns from Satellite Image Time Series

“…One possible method for the analysis of satellite image time series (SITS) is to compare two satellite images captured at two successive moments of time, over the same area of interest [1][2][3][4]. These methods are generally called change detection methods.…”

Change detection in Landsat images based on local neighbourhood information

“…Many unsupervised reported techniques [4][5][6][7][8][9][10][11] provide change detection map either based on difference image or by analysing bitemporal images separately. A number of change detection techniques are reported based on the difference image and this difference image is created by applying algebraic operation on bitemporal images.…”

“…More recently, few change detection techniques have analysed the bitemporal satellite images separately to generate the binary change map. In [11], the binary descriptors for each pixel are generated by analysing the bitemporal images separately, where the local neighbourhood information are utilised around each pixel. Then, the obtained binary descriptors of bitemporal images are used to calculate the hamming distance of each pixel, and binary change map is generated by applying the Lloyd-Max's algorithm on hamming distance of each pixel.…”

“…In general, inclusion of local neighbourhood information makes change detection algorithm's performance better [4,8,10,11,[13][14][15][16][17][18][19][20]. However, most of these techniques perform change detection analysis either on difference image or features obtained from two images, and this analysis uses an iterative procedure, which is applied for all pixels of the image.…”

Sparsity-Driven Change Detection in Multitemporal SAR Images

“…In this method, the maximally-stable-extremal-region analysis of each scale prevents from a complete texture loss during the scale space construction. Feature space transformations are often used to reduce data dimensionality [8], [9]. For example, Celik [10] uses principal component analysis (PCA) for dimensionality reduction.…”