Quantitative Assessment for Detection and Monitoring of Coastline Dynamics with Temporal RADARSAT Images

This study aims to detect coastline changes using temporal synthetic aperture radar (SAR) images for the state of Kelantan, Malaysia. Two active images, namely, RADARSAT-1 captured in 2003 and RADARSAT-2 captured in 2014, were used to monitor such changes. We applied noise removal and edge detection filtering on RADARSAT images for preprocessing to remove salt and pepper distortion. Different segmentation analyses were also applied to the filtered images. Firstly, multiresolution segmentation, maximum spectral difference and chessboard segmentation were performed to separate land pixels from ocean ones. Next, the Taguchi method was used to optimise segmentation parameters. Subsequently, a support vector machine algorithm was applied on the optimised segments to classify shorelines with an accuracy of 98% for both temporal images. Results were validated using a thematic map from the Department of Survey and Mapping of Malaysia. The change detection showed an average difference in the shoreline of 12.5 m between 2003 and 2014. The methods developed in this study demonstrate the ability of active SAR sensors to map and detect shoreline changes, especially during low or high tides in tropical regions where passive sensor imagery is often masked by clouds.

Download Full-text

PERBANDINGAN METODE KLASIFIKASI PENUTUP LAHAN BERBASIS PIKSEL DAN BERBASIS OBYEK MENGGUNAKAN DATA PiSAR-L2

Jurnal Penginderaan Jauh dan Pengolahan Data Citra Digital ◽

10.30536/j.pjpdcd.2016.v13.a2561 ◽

2016 ◽

Vol 13 (1) ◽

Author(s):

R. Johannes Manalu ◽

Ahmad Sutanto ◽

Bambang Trisakti

Keyword(s):

Support Vector Machine ◽

Maximum Likelihood ◽

Synthetic Aperture Radar ◽

Spatial Resolution ◽

Synthetic Aperture ◽

Support Vector ◽

Object Based ◽

Mixed Pixels ◽

Salt And Pepper ◽

Neighbor Classifier

PiSAR-L2 program is an experimental program for PALSAR-2 sensor installed on ALOS-2. Research collaboration had been conducted between the Japan Aerospace Exploration Agency (JAXA) and Ministry for Research and Technology of Indonesia in 2012 to assess the ability of PiSAR-L2 data for some applications. This paper explores the utilization of PiSAR-L2 data for land cover classification in forest area using pixel-based and object-based methods, then carried out comparison between the two methods. PiSAR-L2 data full polarization with 2.1 level for Riau province was used. Field data conducted by JAXA team and landcover map from WWF were used as references to collect input and evaluation sample. Pre-processing was done by doing backscatter conversion and filtering, then classification was conducted and it`s accuracy was tested. Two methods were used, 1) Maximum Likelihood Enhance Neighbor classifier for pixel-based and 2) Support Vector Machine for object based classification. The effect of spatial resolution on classification result was also analyzed. The results show that pixel-based produced mixed pixels "salt and pepper", the classification accuracies were 62% for 2.5 m and 83% for 10 m spatial resolution. While the object-based has some advantages: high homogeneity (absence of mixed pixels), clear and sharp boundary among classes, and high accuracy (97% for 10 m spatial resolution), although it was still found errors in some classes. Abstrak Program Polarimetric Interferometric Airborne Synthetic Aperture Radar of L-band version 2 (PiSAR-L2) adalah program eksperimen sensor Phased-Array Synthetic Aperture RADAR-2 (PALSAR-2) yang dipasang pada satelit Advanced Land Observing Satellite-2 (ALOS-2). Kerjasama riset telah dilakukan antara JAXA dan Kementerian Riset dan Teknologi pada 2012 untuk mengkaji kemampuan data PiSAR L-2 yang direkam menggunakan pesawat untuk beberapa aplikasi. Kegiatan ini menggunakan data PiSAR L-2 untuk klasifikasi penutup lahan di wilayah hutan dengan metode klasifikasi berbasis piksel dan berbasis obyek, kemudian membandingkan kedua metode tersebut. Data yang digunakan adalah data PiSAR L-2 polarisasi penuh dengan level 2.1 untuk wilayah Provinsi Riau. Data lapangan diperoleh dari survei lapangan tim JAXA dan peta penutup lahan dari World Wildlife Fund dijadikan sebagai referensi untuk sampel masukan dan pengujian. Pengolahan awal melakukan konversi backscatter dan filtering, kemudian melakukan klasifikasi dan uji akurasi. Dua metode klasifikasi yang digunakan, 1) Metode Maximum Likelihood Enhance Neighbor classifier untuk klasifikasi berbasis piksel dan 2) Metode Support Vector Machine untuk klasifikasi berbasis obyek. Pada kegiatan ini dilakukan analisis pengaruh resolusi spasial terhadap hasil klasifikasi. Hasil memperlihatkan bahwa metode berbasis piksel mempunyai piksel bercampur “salt and pepper”, akurasi klasifikasi adalah 62% untuk spasial resolusi 2.5 m dan 83% untuk spasial resolusi 10 m. Sedangkan klasifikasi berbasis obyek mempunyai kelebihan dengan homogenitas obyek yang tinggi (tidak adanya piksel bercampur), batas antara kelas yang jelas dan tegas, serta akurasi yang tinggi (97% untuk resolusi spasial 10 m), walau masih ada kesalahan pada beberapa kelas penutup lahan.

Download Full-text

Reduction of Spatially Correlated Speckle in Textured SAR Images

International Journal of Computing ◽

10.47839/ijc.20.3.2276 ◽

2021 ◽

pp. 319-327

Author(s):

Oleksii Rubel ◽

Vladimir Lukin ◽

Sergiy Krivenko ◽

Vladimir Pavlikov ◽

Simeon Zhyla ◽

...

Keyword(s):

Complex Structure ◽

Noise Removal ◽

Synthetic Aperture ◽

Sar Images ◽

Spatially Correlated ◽

Sensing Systems ◽

Remote Sensing Systems ◽

Non Gaussian ◽

Synthetic Aperture Radars ◽

Sentinel 2

Synthetic aperture radars (SARs) provide a lot of images that can be used for numerous applications. A problem with acquired images is that they are corrupted by speckle which is a noise-like phenomenon with multiplicative nature. In addition, speckle is non-Gaussian and it is often spatially correlated. A typical task in SAR image processing is despeckling and many methods have been already proposed. However, most of them do not take noise spatial correlation into account during denoising. In this paper, we show how this can be done in despeckling based on discrete cosine transform. The use of frequency-dependent thresholds leads to sufficient improvement of denoising efficiency in terms of visual quality metrics. Moreover, we consider quite complex structure texture images for which noise removal is usually problematic and can lead to information loss. Comparison to the well-known local statistic Lee and Frost filters, extended DCT-based filter is carried out for different remote sensing systems including Sentinel-1 and Sentinel-2.

Download Full-text

A “Salt and Pepper” Noise Reduction Scheme for Digital Images Based on Support Vector Machines Classification and Regression

The Scientific World JOURNAL ◽

10.1155/2014/826405 ◽

2014 ◽

Vol 2014 ◽

pp. 1-15

Author(s):

Hilario Gómez-Moreno ◽

Pedro Gil-Jiménez ◽

Sergio Lafuente-Arroyo ◽

Roberto López-Sastre ◽

Saturnino Maldonado-Bascón

Keyword(s):

Support Vector Machines ◽

Noise Reduction ◽

Digital Images ◽

State Of The Art ◽

Noise Removal ◽

Support Vector ◽

Salt And Pepper Noise ◽

Vector Machines ◽

Classification And Regression ◽

Salt And Pepper

We present a new impulse noise removal technique based on Support Vector Machines (SVM). Both classification and regression were used to reduce the “salt and pepper” noise found in digital images. Classification enables identification of noisy pixels, while regression provides a means to determine reconstruction values. The training vectors necessary for the SVM were generated synthetically in order to maintain control over quality and complexity. A modified median filter based on a previous noise detection stage and a regression-based filter are presented and compared to other well-known state-of-the-art noise reduction algorithms. The results show that the filters proposed achieved good results, outperforming other state-of-the-art algorithms for low and medium noise ratios, and were comparable for very highly corrupted images.

Download Full-text

Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion

Sensors ◽

10.3390/s21051643 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1643

Author(s):

Ming Liu ◽

Shichao Chen ◽

Fugang Lu ◽

Mengdao Xing ◽

Jingbiao Wei

Keyword(s):

Synthetic Aperture Radar ◽

False Alarm ◽

False Alarm Rate ◽

Target Detection ◽

Synthetic Aperture ◽

False Alarms ◽

Sar Image ◽

Constant False Alarm Rate ◽

Sar Images ◽

Complex Scenes

For target detection in complex scenes of synthetic aperture radar (SAR) images, the false alarms in the land areas are hard to eliminate, especially for the ones near the coastline. Focusing on the problem, an algorithm based on the fusion of multiscale superpixel segmentations is proposed in this paper. Firstly, the SAR images are partitioned by using different scales of superpixel segmentation. For the superpixels in each scale, the land-sea segmentation is achieved by judging their statistical properties. Then, the land-sea segmentation results obtained in each scale are combined with the result of the constant false alarm rate (CFAR) detector to eliminate the false alarms located on the land areas of the SAR image. In the end, to enhance the robustness of the proposed algorithm, the detection results obtained in different scales are fused together to realize the final target detection. Experimental results on real SAR images have verified the effectiveness of the proposed algorithm.

Download Full-text