the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
A Comparison of CFAR Object Detection Algorithms for Iceberg Identification in L- and C-band SAR Imagery of the Labrador Sea
Laust Færch
Wolfgang Dierking
Nick Hughes
Anthony P. Doulgeris
Abstract. In this study, we pursue two objectives: first, we compare six different “Constant-False-Alarm-Rate" (CFAR) algorithms for iceberg detection in SAR images, and second, we investigate the effect of radar frequency by comparing the detection performance at C- and L-band. The SAR images were acquired over the Labrador Sea under melting conditions. In an overlapping optical Sentinel-2 image, 492 icebergs were identified in the area. They were used for an assessment of the algorithms’ capabilities to accurately detect them in the SAR images and for the determination of the number of false alarms and missed detections. By testing the detectors at varying probability of false alarm (PFA) levels, the optimum PFA for each detector was found. Additionally, we considered the effect of iceberg sizes in relation to image resolution. The results showed that the overall highest accuracy was achieved by applying a Log-normal CFAR detector to the L-band image (F-score of 70.4 %), however, only for a narrow range of PFA values. Three of the tested detectors provided high F-scores above 60 % over a wider range of PFA values both at L- and C-band. Low F-scores were mainly caused by missed detections of small (< 60 m) and medium-sized (60–120 m) icebergs, with approximately 20–40 % of the medium icebergs and 85–90 % of small icebergs being missed by all detectors. The iDPolRad detector which is sensitive to volume scattering is less suitable under melting conditions.
Laust Færch et al.
Status: open (extended)
-
RC1: 'Comment on tc-2023-17', Anonymous Referee #1, 15 Mar 2023
reply
The preprint version of the paper “A Comparison of CFAR Object Detection Algorithms for Iceberg Identification in L- and C-band SAR Imagery of the Labrador Sea” is of very high quality and ready for publication. The study is explained in a comprehensive and clear way, figures and tables are all fine.
The only weakness in the study presented in the preprint is that all tests were performed on only one C and one co-located L-band SAR image, i.e. they capture the same sea state and wind conditions. That is, the ocean backscatter does not vary much. Since the core of CFAR algorithms is based on the evaluation of ocean backscatter (and certain backscatter distributions such as e.g. gamma, log-normal), using only one image for each band is not the best basis for comparing different CFAR algorithms.
Citation: https://doi.org/10.5194/tc-2023-17-RC1
Laust Færch et al.
Laust Færch et al.
Viewed
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
234 | 78 | 10 | 322 | 5 | 4 |
- HTML: 234
- PDF: 78
- XML: 10
- Total: 322
- BibTeX: 5
- EndNote: 4
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1