Sar Image Matching Method Based on Improved Sift for Navigation System

Ren, Sanhai; Chang, Wenge; Liu, Xiangjun

doi:10.2528/pierm11042705

Cited by 5 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the accuracy of the method is better in high elevations, and decreases in the low elevations. In order to improve the accuracy, some methods, such as SIFT [1], could be used in the flat areas. Otherwise, though SAR backscatter variations due to land covers may affect image matching, the effective outlier screening procedures developed to remove erroneous tie-points make the proposed method relatively immune to the backscatter variations in the real SAR image.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…The navigation system matches the real-time image and a geo-referenced image (also called reference image) to obtain the position update information, and corrects the cumulated error of INS by fusing the update information with INS measurements [1]. The accuracy of reference image affects the performance of scene matching, and plays an important role on the final accuracy of navigation.…”

Section: Introductionmentioning

confidence: 99%

“…It is a pity that few technologies of SAR reference image preparation are available from the open literature. According to the principles of scene matching navigation [1], this paper prepares SAR reference image by means of geometric correction.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Sar Reference Image Preparation for Navigation

Ren¹,

Chang²,

Jin³

et al. 2011

PIER

Self Cite

View full text Add to dashboard Cite

Abstract-The preparation of good navigational synthetic aperture radar (SAR) reference image is critical to the SAR scene matching aided navigation system, especially for complex terrain. However, few papers discuss the problem, and almost none of the methods proposed by them are fully automatic. Based on the practical requirements, a fully automated method of SAR reference image preparation is introduced. Firstly, a number of distinctive control points (CP) in the simulated SAR image is detected based on a method of image segmentation and clustering. Then, the corresponding tie-points in the real SAR image are searched based on local similarity by means of template matching. To improve the accuracy of CP, a method for segmentation threshold calculation, outlier screening and sub-pixel location computation is presented. Finally, the real SAR image is warped to the simulated one, and then projected to the frame of digital elevation model (DEM) by the polynomial mapping function. Experimental results on real data sets demonstrate the accuracy and efficiency of the proposed method.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Sar Reference Image Preparation for Navigation

Ren¹,

Chang²,

Jin³

et al. 2011

PIER

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, these moment-based methods lose their functions here, since the wavelet transform used in our method will change the distribution of gray-level. Some matching methods decrease the sensitivity to scaling change by extracting features in the scale space, and achieve satisfactory results [7][8][9]. Therefore, a new method is presented to decrease the sensitivity to rotation and scaling change in this article, using the fusion of multi-scale circular template.…”

Section: The Robust Matching Schemementioning

confidence: 99%

“…More recently, the methods underpinned by local descriptors, i.e., Scale Invariant Feature Transform (SIFT), have been employed in image matching widely [7][8][9]. This approach is regarded as one of the robust feature-based matching methods against the rotation, scaling, and illumination change.…”

Section: Introductionmentioning

confidence: 99%

A Fast and Robust Scene Matching Method for Navigation

Ren¹,

Chang²

2014

PIER M

Self Cite

View full text Add to dashboard Cite

Abstract-The selection of matching method is critical to the scene matching navigation system, as it determines the accuracy of navigation. A coarse-to-fine matching method, which combines the area-based and feature-based matching method, is presented to meet the requirements of navigation, including the real-time performance, the sub-pixel accuracy and the robustness. In the coarse matching stage, the real-time performance is achieved by a pyramid multi-resolution technique, and the robustness is improved by multi-scale circular template fusion. In the precise matching stage, an improved SIFT method is introduced to calculate the matching position and the rotation angle. To validate the method, some experiments are completed. The results show that the proposed method can achieve the sub-pixel matching accuracy and improve the angle accuracy to 0.1 • .

show abstract

A Union Matching Method for SAR Images Based on SIFT and Edge Strength

Chen¹,

Chen

2014

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Multiplicative speckle noise often significantly affects the accuracy and adaptability of the scale-invariant feature transform (SIFT) matching method for synthetic aperture radar (SAR) images. To address this problem, this study proposes a union matching method based on the SIFT and edge strength of the SAR image. First, the rotation constraint iteratively refines the initial SIFT match set based on the parameter decomposition of the common geometry transformation model. Using this model, square summation strength (SSS) similarity is then determined. To get the optimal SIFT matches in the searching space, SSS matching based on pixel migration is applied. Furthermore, we outlined the optimization procedure of a union matching strategy. In the iterative process of global searching, the correctly matched tie-points are added individually. Finally, the accuracy, adaptability, and precision of the proposed method are validated through matching experiments on SAR images. Results showed that the proposed method is accurate and robust with respect to the automatic matching of SAR images.Index Terms-Image matching, pixel migration, synthetic aperture radar (SAR) image, scale-invariant feature transform (SIFT), union matching.

show abstract

Sar Image Matching Method Based on Improved Sift for Navigation System

Cited by 5 publications

References 12 publications

Automated Sar Reference Image Preparation for Navigation

Automated Sar Reference Image Preparation for Navigation

A Fast and Robust Scene Matching Method for Navigation

A Union Matching Method for SAR Images Based on SIFT and Edge Strength

Contact Info

Product

Resources

About