Automatic Detection of Subsidence Troughs in SAR Interferograms Based on Circular Gabor Filters

Automatic Subsidence Troughs Detection in SAR Interferograms Using Circlet Transform

“…Many studies have shown the use of the DInSAR methodology to assess the ground deformation [ 6 , 7 , 8 , 9 ]. Over the past few years, a lot of effort has been put in the automation of DInSAR [ 10 , 11 , 12 ] or PSInsar procedures [ 13 ]. The development of an effective method of automatic detection of deformation patterns in the SAR interferograms is difficult due to the presence of noise and irregularities.…”

“…The searching patterns are detected on the basis of values of accumulated votes higher than the predefined threshold value. The Hough transform [ 20 ] together with methods based on the convolution of the image with a bank of circular wavelets [ 12 ], template recognition [ 21 ], or deep convolutional neural network [ 22 ] were used for the deformation patterns detection in the SAR interferograms. None of them proved to be capable of the reliable detection of irregular circular fringes on the noisy SAR interferograms.…”

Automatic Detection of Subsidence Troughs in SAR Interferograms Using Mathematical Morphology

“…There are many scientific papers on this problem that use different methods. In [10], the automatic detection of subsidence troughs in SAR interferograms based on circular Gabor filter was proposed. Its detection rate varied from 30% to 53% with a relatively low number of false alarms.…”

“…Each of those methods has its limitations, which is why their efficiency in trough detection in noisy satellite images is low. Methods [10][11][12][13] use circular or elliptical troughs in the detection process. In many cases, the shape of the troughs on interferograms is deformed, which significantly reduces the effectiveness of these solutions.…”

“…Moreover, the proposed method is much less computationally expensive, which is quite important due to the large size of the processed SAR images. However, most of the solutions [10][11][12][13][14][15] can be used to support the detection of subsidence in larger SAR images, but they are not suitable for fully automated operations.…”