New approach to calculating the fundamental matrix

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 10, No. 3, June 2020, pp. 2357~2366
ISSN: 2088-8708, DOI: 10.11591/ijece.v10i3.pp2357-2366  2357
Journal homepage: http://ijece.iaescore.com/index.php/IJECE
New approach to calculating the fundamental matrix
Ahmed Chater, Abdelali Lasfar
Laboratory of System Analysis Laboratory of System Analysis, Information Processing and Industry Management,
High School of Technology SALE, Mohammed V University, Rabat, Morocco
Article Info ABSTRACT
Article history:
Received May 11, 2019
Revised Nov 15, 2019
Accepted Nov 26, 2019
The estimation of the fundamental matrix (F) is to determine the epipolar
geometry and to establish a geometrical relation between two images of
the same scene or elaborate video frames. In the literature, we find many
techniques that have been proposed for robust estimations such as RANSAC
(random sample consensus), least squares median (LMeds), and M estimators
as exhaustive. This article presents a comparison between the different
detectors that are (Harris, FAST, SIFT, and SURF) in terms of detected
points number, the number of correct matches and the computation speed of
the ‘F’. Our method based first on the extraction of descriptors by
the algorithm (SURF) was used in comparison to the other one because of its
robustness, then set the threshold of uniqueness to obtain the best points and
also normalize these points and rank it according to the weighting function of
the different regions at the end of the estimation of the matrix ''F'' by
the technique of the M-estimator at eight points, to calculate the average
error and the speed of the calculation ''F''. The results of the experimental
simulation were applied to the real images with different changes of
viewpoints, for example (rotation, lighting and moving object), give a good
agreement in terms of the counting speed of the fundamental matrix and
the acceptable average error. The results of the simulation it shows this
technique of use in real-time applications
Keywords:
Eight-point algorithm
Epipolar geometry
Fundamental matrix
Robust detector
Weighting function
Copyright © 2020 Institute of Advanced Engineering and Science.
All rights reserved.
Corresponding Author:
Ahmed Chater,
Laboratory of System Analysis,
Information Processing and industry Management,
High School of Technology SALE,
Mohammed V University,
Rabat, Morocco.
Email: ahmedchater11@gmail.com, ali.lasfar@gmail.com
1. INTRODUCTION
The epipolar the geometry of a scene describes the connection between two or more images of
the same scene from different views by producing the projective geometry between the views.
The calculation of the fundamental matrix (F) which describes the epipolar geometry is used by camera
calibration [1], auto calibration [2], projectile reconstruction [3], reconstruction 3D [4], motion analysis [5],
object mapping and tracking [6], target location 3D and personnel tracking personnel 3D [7, 8].
The calculation of the fundamental matrix requires at least seven or more matching points, these points
determine by two methods that are, manual selection of points this technique is not acceptable because of
the larger error and others by time of the higher processing, it is not practical to treat it from a sequence of
images or video images. The second approach is based on four detectors that are more robust by different
transformations of the scene which are: such as the Harris angle detector [9], (FAST) [10], the robust scaled
invariant characteristic's detector (SIFT) [11] and the robust accelerated characteristics detector (SURF) [12]
were used to detect remarkable points. These remarkable points are then automatically matched in

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 10, No. 3, June 2020 : 2357 - 2366
2358
the different changes of the scene pose, by applying point matching algorithms. The two detectors SIFT and
SURF, which works well compared to (Harris and FAST) because of the affix transformation. Then takes
a descriptor vector for each characteristic point, behave best in this step to find the correct matches by
different variation. In addition, it has been shown that SURF is much faster and more stable than SIFT in
terms of calculating the fundamental matrix and finding the correct matches, but in terms of points of
interest, the SIFT the detector detects the number of points of interest greater than SURF [12]. After
the detection of the correspondence points by different detectors, the calculation of the fundamental matrix is
done according to two methods. These methods are (linear methods) and (non-linear methods) [13, 14].
The first method and is sensitive to the determination of the correspondence due to the additional noise [15].
The last method is (robust method) which are more tolerant to noisy it is divided into three
techniques which are: Least Median-Squares (LMedS) [16], RANdom SAmple Consensus (RANSAC) [17]
and M-Estimator [18]. These methods are used to classify the matches. The first method, calculates for each
value of ‘F’ the number of points that may be suitable (inliers), the matrix ‘F’ chosen is that which
maximizes this number, Once the aberrant points are eliminated, the matrix ‘F’ is recalculated to obtain
a better estimate. Disadvantage of this method does not include outliers. The second method is LMeds
calculates for each estimation of ‘F’ the Euclidean distance between the points and the epipolar lines,
and the choice of ‘F’ corresponds to the minimization of this distance. Same as the first method does not
count outliers.
Then the third technique that includes our method, based on the M-estimator method who inspired
by the two preceding methods, it consists in dividing the detected points into four sets: inliers, quasi-inliers,
outliers and other. The main contribution of this article is to quickly calculate 'F' by significant
correspondence when using outliers. The problem that deals in our article with how to evaluate
the descriptors extracted by different regions (inliers, quasi-inliers, outliers and other) according to
the optimization function to calculate the fundamental matrix in real-time with considerable error acceptable
with different point variations (rotation, illumination, and displacement etc.).
2. EPIPOLAR GEOMETRY AND CALCULS FUNDAMENTAL MATRIX
All methods of estimating of the fundamental matrix require a number of point matches as an input
element. Outstanding characteristic image points such as corners and edges are usually employed for this
purpose. Among the feature detectors, the Harris Corner detector is the most widely known. It is based on
the computations of the eigenvalues of the second moment matrix and is scale invariant. We have a lot of
detectors and descriptors have been proposed, among which, SIFT, PCA-SIFT [19], gradient location and
orientation histogram (FAST), and ASIFT [20].
Among these techniques, those which, in addition to the point detection position, generate descriptor
vectors are chosen because the characteristic points do not include enough information for an exact match.
Mikolajczyk and Schmid [21] reviewed the (SIFT, PCA-SIFT, FAST) and various others feature detection
techniques and noted that (SIFT) works more than others. Other descriptors in rotation, scale, and point of
view changes, Bauer and al. [22] showed that although SURF has fewer key points and a slightly lower
functionality quality than SIFT, it works faster than SIFT with disparate views, rotation and scale.
So for the quick adaptation required for real-time applications, the authors chose to exploit SURF. Calibrate
the uniqueness threshold to obtain more precise matches with minimum number of points. According to
the previous studies for accuracy of point matching and this article evaluates the effect of changing point of
view, rotation, illumination and moving objects on the accuracy of the matrix resulting fundamental.
2.1. Epipolar geometry
Epipolar geometry is intrinsic to any two camera system regardless of the model used for these
cameras. It was introduced by Longuet-Higgins [23]. This geometry allows establishing a geometric
relationship between two stereo images. The accuracy of the estimation of the epipolar geometry is very
remarkable since it conditions the accuracy of the pairing algorithms between the points of a pair of images,
these algorithms often relying on prior knowledge of this geometry. The camera center of the right camera
( '
O ) as viewed in the image of the left camera ( '
O ). Similarly, the two epipoles
'
e and e belongs to
the right that separates the two cameras. The three points
'
,O O and Mi
define a plane  called epipolar
plane. The epipolar plane crosses the image in a line called the epipolar line. All epipolar lines intersect in
the epipolis. The different relationships between the points that make up the epipolar geometry shown in
Figure 1.

Int J Elec & Comp Eng ISSN: 2088-8708 
New approach to calculating the fundamental matrix (Ahmed Chater)
2359
Figure 1. Epipolar geometry were Mi is a 3D point O , and '
O , are camera centers, are epipoles,
and el and ' '
el are epipolar lines
2.2. Fundamental matrix
The fundamental matrix gives the transformation by drawing a selected point in one of the images as
an epipolar line on the other image, thus projecting a point on a line. Mathematically, the epipolar constraint
probably translated by the fundamental matrix as indicated in the following equation:
'
0
T
m Fmi i  (1)
where ‘F’ is a matrix of dimension 3x3 and of rank-2, and determined from ‘F’ and zero, the (1) is
the relationship which relies the points of the left image noted ( , , )iii im x y w and points of the right image
noted
' ' ' '
( , , )i i i im x y w .
3. METHODS TO CALCULATS THE FUNDAMENTAL MATRIX
These techniques can be organized in linear methods in linear and iterative or robust methods [17].
Linear methods, introduced by Longuet-Higgins [23], are very sensitive to noise due to mismatching
the iterative methods used by the Levenberg-Marquardt [24] optimization technique, can, for their part,
generate a bad location of the points in the image, and the robust methods, M-Estimators [18], are able to
give an accurate result with noisy images and managed the outliers by the weighting function.
3.1. Linear method
This collection of linear equations allowed to establish the epipolar geometry in a given pair of
images. The main utility of this technique is its simplicity only seven points are needed for the estimation of '
F'. However, this becomes a disadvantage when some points are badly located [25]. The (1) is the relation
linking a point ( , , )iii im x y w from the right image to a point
' ' ' '
( , , )i i i im x y w from the left image.
This equation can be rewritten in homogeneous coordinates in a linear form:
0Af  (2)
with 11 12 13 21 22 23 31 32 33[ , , , , , , , , ]T
f f f f f f f f f f
' ' '.
1 1 2 2
' ' '.1 1 2 2
' ' '.1 1 2 2
' ' '.
1 1 2 2
' ' '.
1 1 2 2
' ' '.
1 1 2 2
' ' '.
1 1 2 2
' ' '.
1 1 2 2
' ' '.
1 1 2 2
T
x x x x x xn n
x y x y x yn n
x w x w x wn n
y x y x y xn n
A y y y y y yn n
y w y w y wn n
y x y x y xn n
w y w y w yn n
w w w w w wn n
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 ISSN: 2088-8708
2360
In practice, there are larger than 7 corresponding points. If we ignore the constraint on the rank of
the matrix 'F', which is equal to 2, we can use the least squares method to solve the following equation:
2'
min ( )
T
m Fmi ii
 (3)
By imposing a constraint making the norm of F equal to 1, the problem becomes a classic minimization
problem in the following form [26]:
2
min .
1
A Fn
F
F 



(4)
The resolution is then carried out employing the technique of multipliers of Grange.
min ( , )F
F
  (5)
The solution for 'F' is the eigenvector which matches to the small eigenvalue λ. The estimation of
the fundamental matrix can be done more simply by study the eight-point algorithm but the solution obtained
is not necessarily optimal. But, the fundamental matrix has two interesting characteristics: its rank is 2 and it
is 3×3. By using these characteristics related to the detector quality, it probably improves the methods of
estimating 'f'. There is a posteriori solution to find a matrix of null determinant from near ‘F’. The proximity
of the two matrices is estimated by the so-called Frobenius norm [27]. For to obtain ̂ the matrix F is
decomposed into the following form by a technique of SVD type (Singular Value Decomposition):
or S diag( , ,1 )2 3   is a diagonal matrix with 1 2 3    and U and V orthogonal matrices one can
then demonstrate that the matrix.
^ ^
. .
T
F U S V (6)
With
^
( , ,0)1 2S diag   is the rank 2 matrix that minimizes the Frobenius norm [27]. Of
^
F F .
This algorithm has been perfected by Hartley [28] to make it even more robust. Thus, he proposed an
algorithm: eight normalize points [29]. It has shown that the application of the eight-point algorithm is often
unstable.
The solution proposed is to replace the origin in each of the images by the centroid of the paired points.
Then, a scaling factor is applied so that the mean norm of the vectors associated with the points is equal
to 2 . These two operations amount to multiplying the points of the left (right) image by a matrix (3×3).
These two operations amount to multiplying the points of the left (right) image by a matrix (3×3).
This approach has greatly improved the outcome of the eight-point method.
3.2. Nonlinear method ( robust methods)
The LMeds [16] method calculates for each estimation of 'F', the Euclidean distance between
the points and the epipolar lines, and the choice of 'F' corresponds to the minimization of this distance.
It directly related to the distance (d) from point im to its epipolar right. A first idea is then to use a nonlinear
criterion minimizing the sum:
2( , )
1
n
d m Li r
i


(7)
With
'
( , )
' 2 2( . ) ( . )
1 2
Tm Fmi i
d m Li r
F m F mi i


where the term

2361
Where the term '
( . )F mi i
is ieme
element vector 'F' which give a symmetrical role to the two images,
get coherent epipolar geometry, should minimize both creatures the distance between points and the epipolar
line. This technique gives very good results compared to those obtained with linear methods and iterative
methods that minimize the distance separating the points and the Epipolar lines although iterative methods
are more specific than linear methods they cannot get cleared of outliers.
Among the robust methods that are RANSAC and M-Estimators they are three widely robust
techniques in the research. The first method, for its part, calculates for each value of 'F' the number of points
that may be suitable (inliers). The matrix 'F' chosen is that which maximizes this number. Once the aberrant
points are eliminated, the matrix 'F' is recalculated to obtain a better estimation. Although M-Estimators
inspired by the two preceding methods, it consists in dividing the detected points into two sets: inliers and
quasi-inliers [30, 31].
The latter technique is based on solving the following expression.
2
min wiF  ri
i
(8)
iw : Is the weighting function.
 
12 12 13
' '( , , ) , , '
21 22 23
31 32 33
f f f
T
x y w f f f x y wi i i i
f f f
 
 
 
 
  
r
i
' ' ' ' ' ' ' '
'12 21 31 21 22 23 13 23 33r f x x f y x f wx f x y f y y f wy f x w f y w f wwi i i i i i i i i i i i i        
We have added a modification to the weighting function called the separation factor by different sets
of points detected on the images as shown above.
 
1
' '',
0
ri i
ri
w w p pi i i i riri
ri
 
   

 



 

    


 
with:  Factor to ensure delimitation (inliers, quasi-inliers, outliers and other)  . The robust standard
deviation can be expressed as follows:
( )median ri

 .  : Proportional factor whose range is (0,1).
Researches have confirmed that the technique LMeds gives a better result than RANSAC method in terms of
accuracy, LMeds and RANSAC are considered similar; they consist to select randomly the set of points used
for the approximation of the fundamental matrix.
The difference exist between this two methods in the way to determinate the chosen 'F'. LMeds
calculate the 'F' from the distance between the points and the epipolar lines where it seeks to minimize
the median. RANSAC calculate the matrix 'F' from the number of inliers. However, M-Estimator leads to
a good result in the existence of a Gaussian noise at the selected points of the image, the robustness of this
method is manifested in the reduction of aberrant values.
4. ALGORITHM PROPOSED
However, M-Estimator leads to a good result in the presence of Gaussian noise at selected points in
the image, the robustness of this method is manifested in the reduction of outliers. First, two images of
the same scene are loaded by different variations, then the following algorithms are applied (Harris, FAST,
SIFT and SURF) and after the comparison between the one found to be the most robust SURF by
different variations. Then we take the descriptor of the latter and normalize for all and then choose the eight
random points to find the dimension matrix (8x9) and then decompose by the SVD method to find the 3x3
property matrix followed by equal rank 2, determine and zero. Finally we add the optimization function to
find the optimal solution (F) under iterative algorithm. The basic steps of the proposed technique are detailed
in the algorithm as shown in Figure 2.

 ISSN: 2088-8708
2362
Figure 2. Proposed algorithms for calculating the fundamental matrix and the projection error
by the evaluation of the matching
5. SIMULATIONS RESULTS AND DISCUSSIONS
In this section, we study four detectors to extract points of interest and descriptors we use
the following techniques (Harris, FAST, SIFT and SURF) according to the following variation (lighting,
rotation and views of moving objects). In the first test, we will match the four detectors with the RANSAC
statistical technique that determines the correct correspondence, this technique applies to several real images
for a variation of a moving object. The Figure 3 illustrates this variation. We can see from the results
obtained in several tests and from the figure above. The two detectors (Harris and FAST) are sensitive to this
variation which gives the highest error but the time to calculate acceptable, on the other hand, the (SIFT and
SURF) obtain good results in terms of errors but the time to calculate an average with this variation.
(a) (b)
(c) (d)
Figure 3. The correspondence of the original image in motion, (a) SURF, (b) Harris,
(c) FAST and, (d) SIFT
In the second test, we will apply the previous technique under several real images with the variation
of rotation. The Figure 4 below illustrates this variation. We can see from the results obtained in several tests
and from the Figure 4. The two detectors (Harris and FAST) are sensitive to this variation which gives
the highest error but the time to calculate acceptably. Then, the (SIFT and SURF) obtain good results in
terms of errors but the time to calculate an average with this variation. In the third test, we will apply
the previous technique under several real images with the variation the change of lighting. The Figure 5
illustrates this variation.

2363
(a) (b)
(c) (d)
Figure 4. The correspondence of the original image in rotation, (a) Harris, (b) SURF, (c) FAST, (d) SIFT
(a) (b)
(c) (d)
Figure 5. The correspondence of the original image by the change of lighting, (a) SURF, (b) Harris,
(c) SIFT, (d) FAST
We found the same remark as the previous variations, always the time to calculate short by both
techniques (Harris and FAST) but the higher error. Then the two techniques (SIFT and SURF) the time to
calculate the average and the acceptable error. The proposed technique: extraction of the pairings by
the detector (SURF) with the modification of the threshold, then standardization of the data, then associated
with the statistical technique (M-estimator) to optimize the calculation of 'F' and the sampson error as
a function of 'F'. The result of the proposed method applied on the real images with different variations of
point of view (the object in movement (a), lighting (b) and rotation (c).) are represented in Figure 6.
The results obtained from several tests of successful results in terms of calculating 'F' with
acceptable error. The Table 1 summarizes the results of the simulation in terms of the number of points
detected and correspondence. The number of points detected and the similarity depend for example on
the position of the images (rotation, change of brightness, moving object). The Figure 7 below shows
the optimization of the fundamental matrix by different transformations of the scene (rotation, change of
brightness, moving object) according to four detectors.

 ISSN: 2088-8708
2364
(a) (b) (c)
Figure 6. The correspondence of the original image by changing the point of view moving object,
(a) Lighting, (b) Rotation, and (c) Uniqueness threshold
Table1. Results of the comparison of the image with change of (a) Rotation,
(b) Lighting, and (c) Moving object
Algorithm Without changing the unity threshold With modification
the unity thresholdHarris FAST SIFT SURF
Kypt1
a 309 270 529 432 82
b 273 200 300 135 18
c 264 120 200 111 43
Kypt2
a 328 260 480 439 63
b 271 180 241 126 21
c 325 70 260 88 35
Matches
a 112 54 200 150 8
b 50 42 270 73 8
c 32 16 90 19 8
Figure 7. The time to calculate the fundamental
matrix by different variations
Figure 8. Average error of the projection
Our approach which gives good results in terms of speed for the calculation of 'F' compared to other
methods not exceeding 0.8 s on average, as shown in the figure above, the results of this approach can be
used in real-time stereo image analysis applications. The Figure 8 shows the estimation of the projection
error by different transformations of the scene (rotation, change of brightness, moving object) as a function
of four detectors. This approach given the acceptable average error does not exceed 1.4 pixels for the moving
object, the rotation 1.5 pixels and 1.3 pixels for the lighting. On the other hand, the detectors (SIFT and
SURF), given a good accuracy of projection error, does not exceed 1.5 pixel whatever the change on average,
by the detectors (Harris and FAST) are sensitive to the different variations.
6. CONCLUSION
In this article, we have proposed a new approach to calculate F. Our method based first on
the extraction of descriptors by the algorithm (SURF) was used compared to the other because of its
robustness by different variations in the pose of images. then normalized these points and modified

2365
the uniqueness threshold to obtain the best points, after ranking them by the weighting function to estimate
the "F" matrix using the eight-point M-estimator technique, for the purpose of calculating the mean error and
the calculation speed "F", and then we compare our method to the other method which is based on
the combination of the following detectors (SIFT, FAST, and Harris) by the RANSAC algorithm
standardized at eight points. The results of the experimental simulation were applied to the real images with
different changes in viewpoints, for example (rotation, lighting and moving object), giving a good agreement
in terms of computational speed of the fundamental matrix which does not exceed 800 ms and the acceptable
average error does not exceed 1.5 pixel whatever the change. So this approach capable of analyzing moving
scenes, for example 3D reconstruction, path conflict analysis.
ACKNOWLEDGEMENTS
This work is supported by Laboratory of System Analysis, Information Processing and Management
industry, High School of Technology SALE. University, Mohammed V in Rabat, Morocco.
REFERENCES
[1] G. Csurka, C. Zeller, Z. Zhang, O. Faugeras, "Characterizing the uncertainty of the fundamental matrix," Comput.
Vis. Image Underst, vol. 68(1), pp. 18-36, 1996.
[2] Moisan, Lionel, Pierre Moulon, and Pascal Monasse, "Fundamental matrix of a stereo pair, with a contrario
elimination of outliers," Image Processing On Line, vol. 6(2016), pp. 89-113, 2016.
[3] H.C. Longuet-Higgins, "A computer algorithm for reconstruction a scene from two projections," Nature, vol. 293,
pp. 133-135, 1981.
[4] M. Saxena, Ashutosh, Sung H. Chung, and Andrew Y. Ng. "3-d depth reconstruction from a single still
image." International journal of computer vision, vol. 76(1), pp. 53-69, 2008.
[5] S. Köhler, M. Goldhammer, K. Zindler, K. Doll and K. Dietmeyer, "Stereo-Vision-Based Pedestrian's Intention
Detection in a Moving Vehicle," 2015 IEEE 18th International Conference on Intelligent Transportation Systems,
Las Palmas, pp. 2317-2322, 2015.
[6] J. Teizer and P.A. Vela, "Personnel tracking on construction sites using video cameras," Adv. Eng. Inf, vol. 23(4),
pp. 452-462, 2009.
[7] Beyl, Tim, et al., "3D Perception Technologies for Surgical Operating Theatres," Studies in health technology and
informatics, vol. 220, pp. 45-50, 2016.
[8] B. Kueng, E. Mueggler, G. Gallego and D. Scaramuzza, "Low-latency visual odometry using event-based
feature tracks," 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon,
pp. 16-23, 2016.
[9] C. Harris and M. Stephens, "A combined corner and edge detector," in Proceedings of the Alvey Vision Conference,
pp. 90-96, 1988.
[10] S. D. Babacan, R. Molina, and A. K. Katsaggelos, "Fast bayesian compressive sensing using Laplace priors," 2009
IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei, pp. 2873-2876, 2009.
[11] Lowe and David G, "Distinctive image features from scale-invariant keypoints," International journal of computer
vision, vol. 60(2), pp. 91-110, 2004.
[12] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "SURF: speeded up robust features, Comput," Vision – ECCV 2006,
pp. 404-417, 2006.
[13] Q.T. Luong, R. Deriche, O. Faugeras, and T. Papadopoulo, "On Determining the Fundamental Matrix: Analysis of
Different Methods and Results," INRIA Sophia Antipolis, France, 1993.
[14] Sebastián, José M., et al., "Uncalibrated visual servoing using the fundamental matrix," Robotics and Autonomous
Systems, vol. 57(1), pp. 1-10, 2009.
[15] C. A. Sari, E. H. Rachmawanto, and D. R. I. M. Setiadi, "Robust and imperceptible image watermarking by DC
coefficients using singular value decomposition," 2017 4th International Conference on Electrical Engineering,
Computer Science and Informatics (EECSI), Yogyakarta, pp. 1-5, 2017.
[16] Poursaeed, Omid, et al., "Deep fundamental matrix estimation without correspondences," Proceedings of
the European Conference on Computer Vision (ECCV), 2018.
[17] Huang, Jing-Fu, Shang-Hong Lai, and Chia-Ming Cheng, "Robust fundamental matrix estimation with accurate
outlier detection," Journal of information science and engineering, vol. 23(4), pp. 1213-1225, 2007.
[18] Tyler and David E., "A distribution-free $ M $-estimator of multivariate scatter," The annals of Statistics,
vol. 15(1), pp. 234-251, 1987.
[19] Wu, Jian, et al., "A Comparative Study of SIFT and its Variants," Measurement science review,
vol. 13(3), pp. 122-131, 2013.
[20] Morel, Jean-Michel, and Guoshen Yu, "ASIFT: A new framework for fully affine invariant image
comparison," SIAM journal on imaging sciences, vol. 2(2), pp. 438-469, 2009.
[21] Mikolajczyk, Krystian, et al., "A comparison of affine region detectors," International journal of computer vision,
vol. 65(1-2), pp. 43-72, 2005.

 ISSN: 2088-8708
2366
[22] J. Bauer, N. Sunderhauf, and P. Protzel, "Comparing Several Implementations of Two Recently Published Feature
Detectors," In Proc. of the International Conference on Intelligent and Autonomous Systems, IAV, Toulouse,
France, 2007.
[23] H. C. Longuet-Higgins, A Computer Algorithm for Reconstructing a Scene from Two Projections, Morgan
Kaufmann Publishers Inc., 1987.
[24] Yu, Hao, and Bogdan M. Wilamowski, "Levenberg-marquardt training," Industrial electronics handbook
vol. 5 chapter 12, 2011.
[25] CHATER, A and LASFAR, A., "Robust Harris Detector Corresponding and Calculates the Projection Error Using
the Modification of the Weighting Function," International Journal of Machine Learning and Computing,
vol. 9(1), 2019.
[26] Z. Zhang, "Determing the epipolar geometry and its uncertainty," A review International Journal of Computer
Vision, vol. 27(2), pp. 161-198, 1996.
[27] P.H.S. Torr and D.W. Murray, "The development and comparison of robust methods for estimating the fundamental
matrix," Int. J. Comput. Vision, vol. 24(3), pp. 271-300, 1997.
[28] Hartley, Richard, Andrew Zisserman, Multiple view geometry in computer vision, Cambridge university press, 2003.
[29] Longuet-Higgins and H. Christopher, "A computer algorithm for reconstructing a scene from two
projections," Nature, vol. 293, 1981.
[30] A. Chater and A. Lasfar, "Detection of image descriptors and modification of the weighting function for the
estimation of the fundamental matrix using robust methods," Journal of Engineering and Applied Sciences, vol. 13,
pp. 1835-1843, 2018.
[31] A. Chater and A. Lasfar, "Comparison of robust methods for extracting descriptors and facial matching," 2019
International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), Fez, Morocco,
pp. 1-4, 2019.

New approach to calculating the fundamental matrix

More Related Content

What's hot (17)

Similar to New approach to calculating the fundamental matrix (20)

More from IJECEIAES (20)

Recently uploaded (20)

New approach to calculating the fundamental matrix