An adaptive image registration method based on SIFT features and RANSAC transform

Hossein-Nejad, Zahra; Nasri, Mehdi

doi:10.1016/j.compeleceng.2016.11.034

Cited by 76 publications

(28 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SfM consists of three main steps: extracting image features; matching features among 2D images; and estimating 3D shapes. Image features do not rely on the position of shots taken and allow a single feature to be correctly matched with high probability (Lowe, 2004), such as scale invariant feature transform (Dou and Li, 2013;Hossein-Nejad and Nasri, 2017). Effective pixels ×10 4 pixel 2420…”

Section: Proposed Machining Procedures 31 Creation Of 3d Model By On-mentioning

confidence: 99%

Complicated workpiece shape machining using optimal target shape position and orientation on a multifunctional machine tool

Kumanotani

Nakamoto

2018

JAMDSM

View full text Add to dashboard Cite

In order to machine complicated workpiece shapes, it is essential for operators to avoid detrimental collisions between machine structures and workpieces. Therefore, a machine simulator based on 3D models is usually utilized prior to machining operations to ensure this problem is avoided. On the other hand, a multifunctional machine tool with both machining and additive manufacturing (AM) functions is recently developed to realize high flexibility and productivity. However, it is difficult to predict and control workpiece shapes created by AM. Such shapes are generally different from the 3D model prepared in advance. The differences may happen unexpected collisions on a multifunctional machine tool. Additionally, machining productivity may decrease when a NC program is generated with an original 3D model that is different from the actual workpiece shape. Thus, this study aims to realize highly efficient machining of complicated workpiece shapes corresponding to actual workpiece shapes as created by AM. In order to eliminate differences between the 3D model and the actual workpiece shape, a 3D model is firstly created by measuring the shape and position of the workpiece on a multi-functional machine tool. Then, appropriate position and orientation of the target shape is decided to minimize tool path distance. From results of a case study, it is appeared that the proposed machining procedure can improve machining efficiency of complicated workpieces as created by AM.

show abstract

Section: Proposed Machining Procedures 31 Creation Of 3d Model By On-mentioning

confidence: 99%

Complicated workpiece shape machining using optimal target shape position and orientation on a multifunctional machine tool

Kumanotani

Nakamoto

2018

JAMDSM

View full text Add to dashboard Cite

show abstract

“…Scale-Invariant Feature Transform (SIFT) algorithm has been widely used as the mainstream algorithm for image matching because of its strong robustness to illumination and scale rotation [9,14]. However, the cost is an increase in computation time [8,22]. With the increasing high demand for the matching speed, ORB algorithm was proposed, which is at two orders of magnitude faster than SIFT and one order of magnitude faster than SURF [23].…”

Section: Introductionmentioning

confidence: 99%

Mismatch Removal Based on Gaussian Mixture Model for Aircraft Surface Texture Mapping

Niu

Wang

Tan

2020

ITC

View full text Add to dashboard Cite

Aiming at the fact of lower efficiency and higher time cost for feature matching in aircraft surface texture mapping process, a novel mismatch removal method based on Gaussian mixture model is proposed to increase correct corresponding feature matching point pairs. The detection and initial point sets for corresponding pairs are carried out, and a vector field is interpolated between the two matching of ORB feature points. The Gaussian mixture model(GMM) is introduced and a prior is taken to force the smoothness of the field, which is based on the Tikhonov regularization in vector-valued reproducing kernel Hilbert space(RKHS). In order to obtain the optimal estimation, the MAP solution of a Bayesian model with latent variables, which could be performed by Expectation Maximization (EM) algorithm, is utilized to determine the correct correspondence. The experimental results show that the algorithm could remove mismatches effectively and the classification for feature points is excellent. The calculation time is greatly reduced, which enhanced real-time performance of aircraft surface texture mapping process.

show abstract

“…Each of the mentioned registration steps plays an important role in the registration process. However, among them one of the important steps is the feature matching step (Hossein-Nejad and Nasri, 2016). Feature matching directly affects the results of image registration.…”

Section: Introductionmentioning

confidence: 99%

“…Feature matching directly affects the results of image registration. At present, the methods of feature matching mainly includes: cross-correlation (Guizar, 2008;Wolberg and Zokai, 2000), FFT-based cross-correlation (Chen et al, 1995;Foroosh et al, 2002;Gilbert, 2002;Reddy and Chatterji, 1996a;Reddy and Chatterji, 1996b),least squares technique (He et al, 2007;Zhao et al, 2016),image matching based on SIFT (Hossein-Nejad and Nasri, 2016;Yi et al, 2008). The least squares method is suitable for cases where the error points are less.…”

Section: Introductionmentioning

confidence: 99%

Accurate Registration of the Chang’e-1 Iim Data Based on Lro Lroc-Wac Mosica Data

Yang

Kang

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:In the detection of the moon, the visible and near-infrared reflectance data of the lunar material are important information sources for lunar chemical substances and mineral inversion. The Interferometer Imaging Spectrometer (IIM) aboard the Chang'E-1 lunar orbiter is the first multispectral imaging spectrometer for Chinese lunar missions. In this paper, we use the mosaic image of global moon acquired by the Wide-angle Camera (WAC) of the Lunar Reconnaissance Orbiter Camera (LROC) to realize the accurate registration of Chang'E-1 IIM hyperspectral images. Due to the lack of GCPs, the emphasis of this work is to find a huge number of homologous points. The method proposed in this paper is to obtain several homologous points by manually matching, and then we utilize those points to calculate the initial homography matrix of LROC-WAC image and IIM image. This matrix is used to predict the area on IIM image where homologous points may be located, and the locations of the homologous points are determined by the orientation correlation in frequency domain. Finally we save the parts of homologous points which satisfied the conversion relationship of initial homography matrix to calculate homography matrix again. We use this iterative way to obtain a more accurate location of the homologous points. In this process, we take into account that the geometric deformations of different regions on IIM image are quite different. Therefore, we added image threshold segmentation based on the initial homography matrix in the experiment, and completed the above work of finding the homologous points on the segmented images. The final realization of registration accuracy of IIM images are in 1-2 pixels (RMSE). This provides a reliable data assurance for the subsequent study of using IIM images to inverse the lunar elements.

show abstract

An adaptive image registration method based on SIFT features and RANSAC transform

Cited by 76 publications

References 17 publications

Complicated workpiece shape machining using optimal target shape position and orientation on a multifunctional machine tool

Complicated workpiece shape machining using optimal target shape position and orientation on a multifunctional machine tool

Mismatch Removal Based on Gaussian Mixture Model for Aircraft Surface Texture Mapping

Accurate Registration of the Chang’e-1 Iim Data Based on Lro Lroc-Wac Mosica Data

Contact Info

Product

Resources

About