Selim Benhimane

Learn More
The tracking algorithm presented in this paper is based on minimizing the sum-of-squared-difference between a given template and the current image. Theoretically, amongst all standard minimization algorithms, the Newton method has the highest local convergence rate since it is based on a second-order Taylor series of the sum-of-squared-differences. However,(More)
The objective of this paper is to propose a new homography-based approach to image-based visual tracking and servoing. The visual tracking algorithm proposed in the paper is based on a new efficient second-order minimization method. Theoretical analysis and comparative experiments with other tracking approaches show that the proposed method has a higher(More)
In this paper we present two efficient GPU-based visual hull computation algorithms. We compare them in terms of performance using image sets of varying size and different voxel resolutions. In addition, we present a real-time 3D reconstruction system which uses the proposed GPU-based reconstruction method to achieve real-time performance (30 fps) using 16(More)
Unlike dense stereo, optical flow or multi-view stereo, templatebased tracking lacks benchmark datasets allowing a fair comparison between state-of-the-art algorithms. Until now, in order to evaluate objectively and quantitatively the performance and the robustness of template-based tracking algorithms, mainly synthetically generated image sequences were(More)
This paper addresses the problem of motion estimation and 3-D reconstruction through visual tracking with a single-viewpoint sensor and, in particular, how to generalize tracking to calibrated omnidirectional cameras. We analyze different minimization approaches for the intensity-based cost function (sum of squared differences). In particular, we propose(More)
For a large class of applications, there is time to train the system. In this paper, we propose a learning-based approach to patch perspective rectification, and show that it is both faster and more reliable than state-of-the-art ad hoc affine region detection methods. Our method performs in three steps. First, a classifier provides for every keypoint not(More)
We present a method to automatically determine a set of feature descriptors that describes an object such that it can be localized under a variety of viewpoints. Based on a set of synthetically generated views, local image features are detected, described and aggregated in a database. Our proposed method evaluates matches between these database features to(More)
In this paper, we present a generic and flexible system for vision-based robot control. The system integrates several research areas (visual matching, visual tracking and visual servoing) in a unifying framework. In this framework, the flexibility is obtained using a template matching algorithm based on an efficient second-order minimization. Contrarily to(More)