Madrigal F.,Research Center En Matematicas Cimat Ac |
Hayet J.-B.,Research Center En Matematicas Cimat Ac
Machine Vision and Applications | Year: 2017
In this paper, the problem of automated scene understanding by tracking and predicting paths for multiple humans is tackled, with a new methodology using data from a single, fixed camera monitoring the environment. Our main idea is to build goal-oriented prior motion models that could drive both the tracking and path prediction algorithms, based on a coarse-to-fine modeling of the target goal. To implement this idea, we use a dataset of training video sequences with associated ground-truth trajectories and from which we extract hierarchically a set of key locations. These key locations may correspond to exit/entrance zones in the observed scene, or to crossroads where trajectories have often abrupt changes of direction. A simple heuristic allows us to make piecewise associations of the ground-truth trajectories to the key locations, and we use these data to learn one statistical motion model per key location, based on the variations of the trajectories in the training data and on a regularizing prior over the models spatial variations. We illustrate how to use these motion priors within an interacting multiple model scheme for target tracking and path prediction, and we finally evaluate this methodology with experiments on common datasets for tracking algorithms comparison. © 2017 Springer-Verlag Berlin Heidelberg
A robust optimization hybrid algorithm for solving the direct kinematics of the general Gough-Stewart platform [Solución de la cinemática directa de la plataforma Gough-Stewart general usando un algoritmo híbrido de optimización]
Hernandez-Martinez E.E.,National Polytechnic Institute of Mexico |
Valdez-Pena S.I.,Research Center En Matematicas Cimat Ac |
Sanchez-Soto E.,University of Papaloapan
Revista Internacional de Metodos Numericos para Calculo y Diseno en Ingenieria | Year: 2013
The direct kinematics problem for parallel robots can be stated as follows: given values of the joint variables, the corresponding Cartesian variable values, the pose of the end-effect or, must be found. Most of the times the direct kinematics problem involves the solution of a system of non-linear equations. The most efficient methods to solve such kind of equations assume convexity in a cost function which minimum is the solution of the non-linear system. In consequence, the capacity of such methods depends on the knowledge about an starting point which neighboring region is convex, hence the method can find the global minimum. This article propose a method based on probabilistic learning about an adequate starting point for the Dogleg method which assumes local convexity of the function. The proposed method efficiently avoids the local minima, without need of human intervention or apriori knowledge, thus it shows a more robust performance than the simple Dogleg method or other gradient based methods. To demonstrate the performance of the proposed hybrid method, numerical experiments and the respective discussion are presented. The proposal can be extended to other structures of closed-kinematics chains, to the general solution of systems of non-linear equations, and to the minimization of non-linear functions. © 2011 CIMNE (Universitat Politècnica de Catalunya). Publicado por Elsevier España, S.L. Todos los derechos reservados.
Victorin G.B.,Digipro |
Hayet J.B.,Research Center En Matematicas Cimat Ac
Computacion y Sistemas | Year: 2012
This paper proposes a novel robust approach to perform inter-camera and ground-camera calibration in the context of visual monitoring of human-populated areas. By supposing that the monitored agents evolve on a single plane and that the cameras intrinsic parameters are known, we use the image trajectories of moving objects as tracked by standard trackers in a RANSAC paradigm to estimate the extrinsic parameters of the different cameras. We illustrate the performance of our algorithm on several challenging experimental setups and compare it to existing approaches.
Madrigal F.,Research Center En Matematicas Cimat Ac |
Hayet J.-B.,Research Center En Matematicas Cimat Ac |
Rivera M.,Research Center En Matematicas Cimat Ac
Machine Vision and Applications | Year: 2015
This article describes an original strategy for enhancing current state-of-the-art trackers through the use of motion priors, built as data-driven probabilistic motion models for moving targets. Our priors have a simple form and can replace advantageously more traditional models, such as the constant velocity or constant acceleration models, that are of common use in visual tracking systems, but that are also prone to fail in handling critical scene-related constraints on the targets motion. These priors are learned based on local motion observed in the video stream(s) and, given that the obtained representation may be incomplete and noisy, we regularize it in a second phase. The hybrid discrete–continuous motion priors are then used within two classical target tracking approaches: (1) as a sampling distribution in a particle filter framework and (2) as a weighting prior in a detection-based framework. For both tracking schemes, we present promising results with our motion prior approach, on classical benchmark datasets from the visual surveillance tracking literature. © 2015, Springer-Verlag Berlin Heidelberg.