A Unifying Framework for Mutual Information Methods for Use in Non-linear Optimisation

Robotics and Autonomous Systems

2013

In this paper we propose a new way to achieve a navigation task (visual path following) for a non-holonomic vehicle. We consider an image-based navigation process. We show that it is possible to navigate along a visual path without relying on the extraction, matching and tracking of geometric visual features such as keypoint. The new proposed approach relies directly on the information (entropy) contained in the image signal. We show that it is possible to build a control law directly from the maximisation of the shared information between the current image and the next key image in the visual path. The shared information between those two images is obtained using mutual information that is known to be robust to illumination variations and occlusions. Moreover the generally complex task of features extraction and matching is avoided. Both simulations and experiments on a real vehicle are presented and show the possibilities and advantages offered by the proposed method.

Section: Navigation Using Mutual Information 321 Visual Servoing Umentioning

confidence: 99%

Using mutual information for appearance-based visual path following

Robotics and Autonomous Systems

2013

“…By analogy with classical Hessian computation in SSD minimization, second order derivatives are usually neglected in the Hessian matrix computation [21,5,6]. In our approach we compute the Hessian matrix using the second order derivatives that are, in our point of view, required to obtain a precise estimation of the motion.…”

Section: Derivative Function Analysismentioning

confidence: 99%

“…Indeed approximating the Hessian matrix as it is proposed in [21,5,6] do not gives an estimation of the Hessian matrix after convergence (see the green curve in 4 for the MI function). No approximation on the Hessian of MI simplifies the problem as the Gauss-Newton approach does for the SSD.…”

Section: Conditioning the Optimizationmentioning

confidence: 99%

Accurate real-time tracking using mutual information

2010 IEEE International Symposium on Mixed and Augmented Reality

2010

In this paper we present a direct tracking approach that uses Mutual Information (MI) as a metric for alignment. The proposed approach is robust, real-time and gives an accurate estimation of the displacement that makes it adapted to augmented reality applications. MI is a measure of the quantity of information shared by signals that has been widely used in medical applications. Since then, and although MI has the ability to perform robust alignment with illumination changes, multi-modality and partial occlusions, few works propose MI-based applications related to object tracking in image sequences due to some optimization problems. In this work, we propose an optimization method that is adapted to the MI cost function and gives a practical solution for augmented reality application. We show that by refining the computation of the Hessian matrix and using a specific optimization approach, the tracking results are far more robust and accurate than the existing solutions. A new approach is also proposed to speed up the computation of the derivatives and keep the same optimization efficiency.To validate the advantages of the proposed approach, several experiments are performed. The ESM and the proposed MI tracking approaches are compared on a standard dataset. We also show the robustness of the proposed approach on registration applications with different sensor modalities: map versus satellite images and satellite images versus airborne infrared images within different AR applications.

“…Considering information contained in the image and not the image itself allows to be independent from perturbation or from the image modality. Such approach has been widely used for multi-modal medical image registration [16] [8] and more recently in tracking [6].…”

Section: B Overview and Related Workmentioning

confidence: 99%

Entropy-based visual servoing

2009 IEEE International Conference on Robotics and Automation

2009

Abstract-In this work we propose a new way to achieve visual servoing using directly the information (as defined by Shannon) of the image. A metric derived from information theory, mutual information, is considered. Mutual information is widely used in multi-modal image registration (medical applications) since it is insensitive to changes in the lighting condition and to a wide class of non-linear image transformation. In this paper mutual-information is used as a new visual feature for visual servoing and allows us to build a new control law to control the 6 dof of the robot. Among various advantages, this approach does not require any matching nor tracking step, is robust to large illumination variation and allows to consider, within the same task, different image modalities. Experiments that demonstrate these advantages conclude the paper.