Detection and recognition of a vehicle license plate is a fundamental requirement of any intelligent transport system, primarily to support activities like finding a stolen vehicle, vehicle surveillance/tracking, parking-toll collection, traffic flow planning and management, etc. However, a license plate can easily be stolen and/or changed by those with criminal intent to conceal their identity. This paper proposes a new vehicle identification system to obtain high degree of accuracy and success rate by not only considering the license plate but also shape of the vehicle. The proposed system is based on four steps: license plate detection, license plate recognition, license plate jurisdiction (province) detection and the vehicle shape detection. In the proposed system, the features are converted into local binary pattern (LBP) and Histogram of Oriented Gradients (HOG) as training dataset. To obtain high degree of accuracy in real-time application, a novel method based on cascaded classifiers is used to update the system. The proposed system allows us to store features of vehicles and related information in the database, thus, allowing us to automatically detect any discrepancy between a license plate and vehicle associated with it.

This paper presents a simple, yet effective, method to recover the affine structure of a scene from a (stereo) pair of stationary zooming cameras. The proposed method solely relies on point correspondences across images and no knowledge about the scene whatsoever is required. Our method exploits implicit properties of the projective camera matrices of zooming cameras and allows to estimate the affine structure of a scene by solving a linear system of equations. The 3D reconstruction results obtained by using our method, on both real and simulated data, have remarkably validated its feasibility.

This paper deals with the problem of retrieving the affine structure of a scene from two or more images of parallel planes. We propose a new approach that is solely based on plane homographies, calculated from point correspondences, and that does not require the recovery of the 3D structure of the scene. Neither vanishing points nor lines need to be extracted from the images. The case of a moving camera with constant intrinsic parameters and the one of cameras with possibly different parameters are both addressed. Extensive experiments with both synthetic and real images have validated our approach.

This paper proposes a new method for identifying parallel planes in a scene from three or more uncalibrated images. By using the fact that parallel planes intersect at infinity, we were able to devise a linear relationship between the inter-image homographies of the parallel planes and the plane at infinity. This relationship is combined with the so-called modulus constraint for identifying pairs of parallel planes solely from point correspondences. Experiments with both synthetic and real images have validated our method.

In this paper, we propose a new approach for extracting major planes of the scene from uncalibrated pairs of images. In contrast to existing methods, our method does not make any assumption on the images or co-planarity of points. The proposed method takes two uncalibrated images as input, extracts and matches interest points, and then performs plane identification and matching defined by sets of three points. For each set of three points, a plane homography is then calculated. Once all possible planes have been identified, a merging stage is carried out to improve the robustness and to make sure that same planes are associated with a single homography. Furthermore, the method is capable to distinguish between physical and virtual planes. Experiments on a variety of real images demonstrate the validity of the proposed approach.

This paper presents a new method to achieve fast dense matching in a pair of uncalibrated images. Classical area-based dense matching methods suffer from the high computational time resulting from intensive correlation calculations during the search/selection process. In contrast to conventional methods that are based on similarity and correlation techniques, this method is based on enforcing known geometric constraints and uses correlations only on a very small number of points. In particular, this paper proposes a hybrid matching technique that segment the image into two sets: the edge and the nonedge regions. For the edge regions, where discontinuities usually occur, the correlation-based classical matching method is used whereas, for nonedge regions, a segment mapping is used to achieve a correlation-free pixel matching. This segment mapping implicitly enforces all the four well known constraints in stereo matching: epipolar, continuity, uniqueness and, order constraints. The experiments on real images validated our method and showed drastic CPU-time reduction compared to classical methods.

In this paper, new equations for the self-calibration of a moving camera with unchanged intrinsic parameters are proposed. Unlike most existing methods that require solving equations in three or more unknowns, our equations are only bivariate. The two unknowns, in our equations, are the scale factors that are responsible for the nonlinearity of Kruppa's equations due to a triplet of images. Once the scale factors are calculated, Kruppa's coefficients are linearly retrieved. The results of our experiments, conducted on simulated and real data, are also presented.

In stereopsis, correspondence is a central problem that is known to suffer from several inherent difficulties. Single-lens stereo systems have brought a geometrical solution to some of the problems of stereopsis. The plenoptic camera is one of those systems that we found to simplify the process of depth recovery, but whose main limitation lies in its small baseline. For this particular reason, matches in the plenoptic camera are obtained more easily, however, this trades off against the accuracy with which they are recovered. In this paper, we show how its lack of accuracy due to a small baseline can be made up for to some extent, by using a multibaseline estimate in lieu of the commonly used equal-baseline estimate.

In this paper, we propose a new method to simultaneously achieve segmentation and dense matching in a pair of stereo images. In contrast to conventional methods that are based on similarity or correlation techniques, this method is based on geometry, and uses correlations only on a limited number of key points. Stemming from the observation that our environment is abundant in planes, this method focuses on segmentation and matching of planes in an observed scene. Neither prior knowledge about the scene nor camera calibration are needed. Using two uncalibrated images as inputs, the method starts with a rough identification of a potential plane, defined by three points only. Based on these three points, a plane homography is then calculated and, used for validation. Starting from a seed region defined by the original three points, the method grows the current region by successive move/confirmation steps until occlusions and/or surface discontinuity occur. In this case, the homography-based mapping of points between the two images will not be valid anymore. This condition is detected by the correlation, used in the confirmation process. In particular, this method grows a region even across different colors as long as the region is planar. Experiments on real images validated our method and showed its capability and performance.

The problem of synthesizing novel views consists of generating new views of a scene using at least two reference views. Although novel views might be rendered after the explicit 3D reconstruction of the scene, image based view synthesis is currently the most attractive approach. Image based view synthesis may be achieved through either epipolar geometry or trilinear tensors. We present a different approach based on plane homographies for image based view synthesis. Two cases are investigated here. In the first case, we assume that two physical planes in the scene can be identified and we show that a minimum of six matched points across three images is sufficient for view synthesis. In the second case however, we do not make any assumption and we show that we can calculate two plane homographies and use them for view synthesis. Experimental results on both real and simulated images show the feasibility and accuracy of our approach.

In the computation of the 3D structure, it has been demonstrated that by introducing a third camera provides improvement over the use of two views only. In this paper, we propose a new algebraic derivation for the projection matrix of the third camera. This derivation is obtained by using the relationships between the projection matrices, the epipolar geometry and the trilinear tensors. Compared to previous methods, our method has the advantage to work in the special case where the camera centers are collinear. In addition, it has the advantage of simplicity and it is very straightforward to implement since it is a linear method. In our experiments, we used the view synthesis to high-light the quality of the computed projective structure. Tests have been performed on both synthetic and real data.

This paper addresses the problem of computing the camera motion and the Euclidean 3D structure of an observed scene using uncalibrated images. Given at least two images with pixel correspondences, the motion of the camera (translation and rotation) and the 3D structure of the scene are calculated simultaneously. We do not assume the knowledge of the intrinsic parameters of the camera. However, an approximation of these parameters is required. Such an approximation is all the time available, either from the camera manufacturer's data or from former experiments. Classical methods based on the essential matrix are highly sensitive to image noise. This sensitivity is amplified when the intrinsic parameters of the cameras contain errors. To overcome such instability, we propose here a method where a particular choice of a 3D Euclidean coordinate system with a different parameterization of the motion/structure problem allowed us to reduce significantly the total number of unknowns. In addition, the simultaneous calculation of the camera motion and the 3D structure has made the computation of the motion and structure less sensitive to the errors in the values of the intrinsic parameters of the camera. All steps of our method are linear. However, a final nonlinear optimal step might be added to improve the accuracy of the results and to allow the orthogonality of the rotation matrix to be taken into account. Experiments with real images validated our method and showed that a good quality motion/structure can be recovered from a pair of uncalibrated images. Intensive experiments with simulated images have shown the relationship between the errors on the intrinsic parameters and the accuracy of the recovered 3D structure.

This paper addresses the problem of computing the Euclidean 3D structure of an observed scene. Given at least 2 images with pixel correspondences, the 3D structure of the scene and the motion of the camera (translation and rotation) are calculated simultaneously. We study here the effect of inaccurate intrinsic parameters on the quality of the recovered reconstruction. Classical methods based on the essential matrix computation have proven to be very unstable when the intrinsic parameters of the cameras are not known exactly. To overcome such unstability, we used a method where a particular choice of a 3D Euclidean coordinate system with a different parameterization of the motion/structure problem allowed us to reduce significantly the total number of unknowns. In addition, the simultaneous calculation of the camera motion and the 3D structure has made the computation of the motion and structure less sensitive to the errors in the values of the intrinsic parameters of the camera. Experiments with real images validated our method and experiments with simulated data showed how the errors on the intrinsic parameters affect the accuracy of the reconstruction.

This paper addresses the problem of computing the fundamental matrix which describes a geometric relationship between a pair of stereo images: the epipolar geometry. In the uncalibrated case, epipolar geometry captures all the 3D information available from the scene. It is of central importance for problems such as 3D reconstruction, self-calibration and feature tracking. Hence, the computation of the fundamental matrix is of great interest. The existing classical methods14 use two steps: a linear step followed by a nonlinear one. However, in some cases, the linear step does not yield a close form solution for the fundamental matrix, resulting in more iterations for the nonlinear step which is not guaranteed to converge to the correct solution. In this paper, a novel method based on virtual parallax is proposed. The problem is formulated differently; instead of computing directly the 3 × 3 fundamental matrix, we compute a homography with one epipole position, and show that this is equivalent to computing the fundamental matrix. Simple equations are derived by reducing the number of parameters to estimate. As a consequence, we obtain an accurate fundamental matrix with a stable linear computation. Experiments with simulated and real images validate our method and clearly show the improvement over the classical 8-point method.

The paper addresses the problem of computing the fundamental matrix which describes a geometric relationship between a pair of stereo images: the epipolar geometry. We propose a novel method based on virtual parallax. Instead of computing directly the 3/spl times/3 fundamental matrix, we compute a homography with one epipole position, and show that this is equivalent to computing the fundamental matrix. Simple equations are derived by reducing the number of parameters to estimate. As a consequence, we obtain an accurate fundamental matrix of rank two with a stable linear computation. Experiments with simulated and real images validate our method and clearly show the improvement over existing methods.>

This paper presents a method for doing motion segmentation for autonomous vehicles which drive on planar surfaces. There are two distinct types of independent motion that may occur within an image sequence taken from a moving vehicle. The first generic type of independent motion is when the projected motion of points on the independent object violate the epipolar constraint. The second case is where the epipolar constraint is not violated. This paper demonstrates that it is possible to detect this second type of independent motion by looking for progressive dis-occlusion of the road. A novel collision prediction method is also given. The method predicts the projection of a corridor down which the AGV will travel. This prediction may be used for time to contact collision prediction and the corridor width embodies an estimate of the vehicles size.>

It is possible to recover the three-dimensional structure of a scene using images taken with uncalibrated cameras and pixel correspondences betweeen these images. But such reconstruction can only be performed up to a projective transformation of the 3-D space. Therefore, constraints have to be put on the reconstructed data to get the reconstruction in the Euclidean space. Such constraints arise from knowledge of the scene, such as the location of points, geometrical constraints on lines, etc. The kind of constraints that have to be added are discussed, and it is shown how they can be fed in a general framework. Experimental results on real data prove the feasibility, and experiments on simulated data address the accuracy of the results.>