Abderrahim Saaidi

Camera self-calibration with varying intrinsic parameters by an unknown three-dimensional scene

This work proposes a method of camera self-calibration having varying intrinsic parameters from a sequence of images of an unknown 3D object. The projection of two points of the 3D scene in the image planes is used with fundamental matrices to determine the projection matrices. The present approach is based on the formulation of a nonlinear cost function from the determination of a relationship between two points of the scene and their projections in the image planes. The resolution of this function enables us to estimate the intrinsic parameters of different cameras. The strong point of the present approach is clearly seen in the minimization of the three constraints of a self-calibration system (a pair of images, 3D scene, any camera): The use of a single pair of images provides fewer equations, which minimizes the execution time of the program, the use of a 3D scene reduces the planarity constraints, and the use of any camera eliminates the constraints of cameras having constant parameters. The experiment results on synthetic and real data are presented to demonstrate the performance of the present approach in terms of accuracy, simplicity, stability, and convergence.

Image mosaicing using voronoi diagram

In this article, we propose a new method of image stitching that computes, in a robust manner, the transformation model applied to creating a panorama that is close to reality. The random selection of matching points used in existing methods, using Random Sample Consensus (RANSAC) or the threshold of the execution process (iteration number) cannot generally provide sufficient precision. Our approach, in this regard, comes to solve this problem. The calculation of the transformation model is based on the VORONOI diagram that divides images into regions to be used in the matching instead of control points. In this case, the transformation estimation will be based on the regions seeds that provide the best correlation score. Among the advantages of our method is solving problems related to outliers that can, in existing methods, affect the reliability of the mosaic. The results obtained are satisfactory in terms of stability, quality, execution time and reduction of the computational complexity.

A flexible technique based on fundamental matrix for camera self-calibration with variable intrinsic parameters from two views

Self-calibrate cameras with varying focal length.Automatic estimation of the intrinsic parameters of the camera.Works freely in the domain of self-calibration without any prior knowledge about the scene or on the cameras. We propose a new self-calibration technique for cameras with varying intrinsic parameters that can be computed using only information contained in the images themselves. The method does not need any a priori knowledge on the orientations of the camera and is based on the use of a 3 D scene containing an unknown isosceles right triangle. The importance of our approach resides at minimizing constraints on the self-calibration system and the use of only two images to estimate these parameters. This method is based on the formulation of a nonlinear cost function from the relationship between two matches which are the projection of two points representing vertices of an isosceles right triangle, and the relationship between the images of the absolute conic. The resolution of this function enables us to estimate the cameras intrinsic parameters. The algorithm is implemented and validated on several sets of synthetic and real image data.

Multi-view passive 3D reconstruction: Comparison and evaluation of three techniques and a new method for 3D object reconstruction

In this article, we focus on the comparison of the passive techniques of multi-view 3D reconstruction, namely the following techniques : Passive Stereo vision, Shape from Silhouette and Space Carving. Available data in the Passive techniques are no more than one or many images taken from different point of views (using one or several cameras). These images will be used in order to render the three-dimensional scene. Our study is based on the quality of the solution (3D Model obtained) and the calculation time. In passive stereo vision, the quality of the results is evaluated in terms of the value of the re-projection error. Also we will evaluate each technique separately. In the end, to enjoy the benefits of the techniques studied we proposed a method based on the extraction of silhouette images and the matching between images to make full 3D object reconstruction. The results of our own implementation of the different techniques studied and the proposed method enable to compare and evaluate these techniques, and to show the quality of the results obtained by the proposed method.

A new method of camera self-calibration with varying intrinsic parameters using an improved genetic algorithm

In this paper, we present a new method of camera self-calibration with varying intrinsic parameters by an improved genetic algorithm. Firstly, the simplified Kruppa equation (the case of varying intrinsic parameters) defined by Hartley is translated into the optimized cost function. Secondly, the minimization of the cost function is calculated by an optimized modified genetic algorithm. Finally, the intrinsic parameters of the camera are obtained. Comparing to traditional optimization methods, the camera self-calibration with varying intrinsic parameters by this approach can avoid being trapped in a local minimum and converge quickly to the optimal solution without initial estimates of the camera parameters. Our study is performed on synthetic and real data to demonstrate the validity and performance of the presented approach. The results show that the proposed technique is both accurate and robust.

Self-calibration based on a circle of the cameras having the varying intrinsic parameters

The problem examined in this article is a cameras self-calibration having the varying intrinsic parameters with an unknown planar scene. This method is based on the use of two points through which passes a circle. The planar scene considered permits to calculate the projection matrices of any two points of the scene in used images. These matrices can minimize a non-linear cost function to optimize the initial intrinsic parameters.

Robust point matching via corresponding circles

The matching points extracted from images play a very important role in many applications and particularly in computer vision. The use of point sets as being characteristics that describe the entire images brought into play, it greatly contributes to the reduction of the execution time, unlike the use of all the information contained in these images. The major problem of the matching process is the possibility to generate a large number of false correspondences, or outliers, in addition to a limited number of true correspondences (inliers). The objective of this paper is to propose a robust algorithm to eliminate or reduce the false correspondences, or outliers, among the putative set extracted from stereoscopic images. The principle of our method is based on the notion of belonging to the corresponding circles and the concept of similarity of stereoscopic images. The results largely reflect the efficiency and performance of our algorithm in comparison to the other used methods in this framework like RANSAC algorithm.

Human Tracking Based on Appearance Model

The Mean Shift algorithm for tracking the location of an object has recently gained considerable interest because of its speediness and efficiency. However, the appearance description using only color features cannot provide enough information when the target and its background have similar colors. In response to this problem, an improved human tracking system based on Mean Shift algorithm is incorporated in this paper. The proposed method combines color-texture features and background information to find the most distinguished features between the target and background for target representation. The experimental results show that the proposed method presents a good compromise between computational cost and accuracy; its performance is compared with recent state-of-the-art algorithm on Benchmark dataset and it achieved excellent results.

Securing the architecture of the JPEG compression by an dynamic encryption

In this article, we investigate image security for transmission in digital networks using a hybrid coding based on juxtaposed encryption and compression. We have proposed a new approach that integrates a dynamic Hill-Cipher encryption added to the step of quantizing of JPEG compression. A step by step demonstration is given in order to show the functioning of the crypto compression scheme constructed. This explanation justifies how to strategically integrate different operations of our crypto compression system. The effectiveness and robustness of our scheme is validated by measuring its security strength, its computational cost and the quality of reconstructed images (PSNR). The results showed that our new idea by both its generic fast encryption and its simple adaptation provides a reasonable complexity and a good compromise between security and compression rate, this crypto compression scheme is efficient and recommended for networks with low bandwidth especially for low-power devices.

Benchmarking AES and chaos based logistic map for image encryption

In this paper, an analysis study of two encryption algorithms applied to images is performed in order to assess their robustness in terms of security. The first is the classical cryptosystem known as Advanced Encryption Standard (AES) and the second is issued from the study of chaotic signals called the logistic map. The experimental results and their analysis show that AES encryptions is more secure, but on the other hand the logistic map exhibits good encryption speed.