Robust Optical and SAR Image Registration Based on Phase Congruency Scale Space

Li, Zeyi; Zhang, Haitao; Chen, Junyu; Huang, Yihang

doi:10.1109/lgrs.2022.3188010

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aforementioned problems also exist in SAR image registration applications. For these issues, the scale difference has been well addressed with the scale space theory already [9][10][11] . It makes the various features related to the scale parameters so that ones can detect and describe key points at the appropriate scale level.…”

Section: Introductionmentioning

confidence: 99%

“…Based on the abovementioned, attempts have gradually been made to explore the feature map, which is derived from the original image and is stable in various aspects [1][2][3][4]6,7,11,14] . The traditional difference-based gradient, which is employed in SIFT to generate descriptors, is unstable in the SAR image.…”

Section: Introductionmentioning

confidence: 99%

“…After Mehrotra et al [16] demonstrated that the Gabor odd filter is an efficient and robust mean of edge detection, the Gabor odd filter-based ratio operator was adopted for SAR image matching by Sourabh et al [4] . On the other hand, a dimensionless quantity, i.e., the phase congruency (PC), attracts more and more attention and performed well in edge detection [13 and registration [11,14] for SAR images. Moreover, Li et al designed a maximum index map (MIM) for feature description [3] , which brought outstanding performance in multi-modal image matching.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel speckle-robust feature map and research on rotation invariance of feature maps in the SAR image

Li,

Wang,

et al. 2023

Third International Conference on Computer Vision and Pattern Analysis (ICCPA 2023)

View full text Add to dashboard Cite

The feature map is often used for describing the characteristics of key points in image registration applications. Due to feature information being sensitive to rotation and noise, the values of calculation methods for various feature maps would change in different rotation or noise conditions. Consequently, it is unfavorable to obtain the stable descriptor for the same feature point in different images. Specifically, speckle noise damages the synthetic aperture radar (SAR) image seriously, which makes SAR image registration more difficult. In this paper, a novel feature map, which is robust to speckle noise, is proposed. A fully size-adaptive sliding window method is embedded into the ratio of exponentially weighted average method for its noise robustness improvement. Then, a series of Monte Carlo experiments compare the rotation and speckle stabilities among various feature map methods comprehensively. The experimental results reflect that the proposed feature map method is stable while speckle noise increases, and it has less mean orientation difference than others. Moreover, the data of experimental results can be used to support many other analyses on feature maps.

show abstract

Section: Introductionmentioning

confidence: 99%