An automatic image registration for applications in remote sensing

Bentoutou, Y.; Taleb, Nasreddine; Kpalma, Kidiyo; Ronsin, Joseph

doi:10.1109/tgrs.2005.853187

Cited by 229 publications

(128 citation statements)

References 29 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…The total processing time is about 15 mins, and the SAR image simulation and CP matching account for 35% and 56%, respectively, which means the correlation computation is time consuming and may be further accelerated through the method proposed in [12][13][14]. By comparing the proposed method with the existed methods in [6,9], where the TGM is the method proposed in [6] and the EBM is the method proposed in [9], we can get that the proposed method is better in accuracy and computation time.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…However, the general methods to acquire the offset are by visually comparing the image pairs [6,9], which need human intervention. An automated method of image offset calculation is proposed in this paper.…”

Section: The Image Offset Calculationmentioning

confidence: 99%

“…Several approaches have been proposed to obtain sub-pixel accuracy in CP matching, such as analytical matching interpolation methods [22] and image-interpolation methods [23]. Since the image interpolation approach is computationally expensive compared to the analytical match-interpolation method [9], the analytical match-interpolation method is used in this paper. In this case, sub-pixel accuracy is achieved by interpolating in the match measure surface to estimate the position of the peak.…”

Section: Control Point Matchingmentioning

confidence: 99%

“…The method first detects CPs in the simulated SAR image via image processing soft, then searches the tie-points in the real SAR image by image matching. Sheng and Alsdorf [6] and Bentoutou et al [9] suggest an edge-based method of CP detection, which does the edge detection firstly, and then detects CPs in the edge image using corner detector. Though these methods can detect a set of reliable CPs, they don't take into account the characters of SAR image under mountainous areas, where the features of layover and shadow are obvious.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Sar Reference Image Preparation for Navigation

Ren¹,

Chang²,

Jin³

et al. 2011

PIER

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: The Image Offset Calculationmentioning

confidence: 99%

Section: Control Point Matchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Sar Reference Image Preparation for Navigation

Ren¹,

Chang²,

Jin³

et al. 2011

PIER

View full text Add to dashboard Cite

show abstract

“…Points [1], [3], [7], Lines, edges and contours, Real objects in the scene such as buildings, Templates: Windows of predefined size.…”

Section: Introductionmentioning

confidence: 99%

Automatic Remote-sensing Image Registration Using SURF

Bouchiha¹,

Besbes²

2013

IJCTE

View full text Add to dashboard Cite

Abstract-Image registration is a key, essential element in analysis of Remote sensing images. Registration is critical both for initial processing and for end-user processing of those image products for data fusion, and change detection. This paper focused on the feature-based category of image registration algorithms. Many techniques for the detection and description of images' local characteristics have been proposed to register a set of images without user intervention. However, it is unclear which descriptors are more appropriate. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the sensor. In our evaluation, we have separated the detector from the descriptor as their performance depends on the interest point detector used. The descriptors are compared according to their recall and runtime efficiency and this deals with several geometric and photometric changes. We also propose an extension to the SURF descriptor and the results show the effectiveness of proposed improvements compared to base SURF method. Furthermore, we observe that the SURF descriptor outperforms the others' descriptors. Finally, based on the test results, we propose an approach to register automatically remotely sensed images.

show abstract