SAR-SIFT: A SIFT-Like Algorithm for SAR Images

By Flora Dellinger, Julie Delon, Yann Gousseau, Julien Michel, Florence Tupin. IEEE Transactions on Geoscience and Remote Sensing, 2015

549 citations recorded by the source corpus.

The scale-invariant feature transform (SIFT) algorithm and its many variants are widely used in computer vision and in remote sensing to match features between images or to localize and recognize objects. However, mostly because of speckle noise, it does not perform well on synthetic aperture radar (SAR) images. In this paper, we introduce a SIFT-like algorithm specifically dedicated to SAR imaging, which is named SAR-SIFT. The algorithm includes both the detection of keypoints and the computation of local descriptors. A new gradient definition, yielding an orientation and a magnitude that are robust to speckle noise, is first introduced. It is then used to adapt several steps of the SIFT algorithm to SAR images. We study the improvement brought by this new algorithm, as compared with existing approaches. We present an application of SAR-SIFT to the registration of SAR images in different configurations, particularly with different incidence angles.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/17c475192195124af6cbf0a46dcce462b1bbad03

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Richard Bamler
2. Xiaoxiang Zhu
3. Maoguo Gong
4. Qingwu Hu
5. Mingyao Ai
6. Feng Xu
7. Lichao Mou
8. Jiayuan Li

In Computer Vision and Pattern Recognition

1. Lichao Mou
2. Xiaoxiang Zhu
3. L. Jiao
4. Wenping Ma
5. Maoguo Gong
6. Richard Bamler
7. Qingwu Hu
8. Mingyao Ai

Citations in the corpus

• Remote Sensing Image Registration With Modified SIFT and Enhanced Feature Matching (2017, methodology): “Considering the results in Table I, SIFT, SAR-SIFT, and SURF fail to register the test pair P-A.”
• Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives (2020, background): “Experimental results indicate that this deep learning-based method outperforms state-of-the-art matching approaches [169], [170].”
• RIFT: Multi-Modal Image Matching Based on Radiation-Variation Insensitive Feature Transform (2019, methodology): “SAR-SIFT [16] introduces a new gradient definition based on the specific characteristics of SAR images to improve the robustness to speckle noise.”