1,721,010 research outputs found
Fast construction of covariance matrices for arbitrary size image windows
No full textWe present a novel, integral image based algorithm to compute feature covariance matrices within all arbitrary size rectangular regions in an image. This technique significantly improves the computational load of covariance matrix extraction process by taking advantage of the spatial arrangement of points. Covariance is an essential measure of how much the deviation of two or more variables or processes match. In our case, these variables correspond to point features such as coordinate, color, gradient, orientation, and filter responses. Integral images are intermediate image representations used for calculation of region sums. Each point of the integral image is a summation of all the points inside the rectangle bounded by the upper left corner of the image and the point of interest. Using this representation, any rectangular region sum can be computed in constant time. We follow a similar idea for fast calculation of region covariance. We construct integral images for all separate features as well as integral images of the multiplication of any two feature combinations. Using these set of integral images and region corner point coordinates, we directly extract the covariance matrix coefficients. We show that the proposed integral image based method decreases the computational load to quadratic time
Multi-Kernel Object Tracking
Get PDFIn this paper, we present an object tracking algorithm for the low-frame-rate video in which objects have fast motion. The conventional mean-shift tracking fails in case the relocation of an object is large and its regions between the consecutive frames do not overlap. We provide a solution to this problem by using multiple kernels centered at the high motion areas. In addition, we improve the convergence properties of the mean-shift by integrating two likelihood terms, background and template similarities, in the iterative update mechanism. Our simulations prove the effectiveness of the proposed method
Object tracking in low-framerate video
No full textIn this paper, we present an object detection and tracking algorithm for low-frame-rate applications. We extend the standard mean-shift technique such that is is not limited within a single kernel but uses multiple kernels centered around high motion areas obtained by change detection. We also improve the convergence properties of the mean-shift by integrating two additional likelihood terms using object templates. Our simulations prove the effectiveness of the proposed method both under heavy occlusions and low frame rates down to 1-fps
Bayesian Background Modeling for Foreground Detection
No full textWe propose a Bayesian learning method to capture the background statistics of a dynamic scene. We model each pixel as a set of layered normal distributions that compete with each other. Using a recursive Bayesian learning mechanism, we estimate not only the mean and variance but also the probability distribution of the mean and covariance of each model. This learning algorithm preserves the multimodality of the background process and is capable of estimating the number of required layers to represent each pixel
Ç�� � Ø ÌÖ � ��Ò � �Ò ÄÓÛ �Ö�Ñ � Ê�Ø � Î���Ó
No full textIn this paper, we present an object detection and tracking algorithm for low-frame-rate applications. We extend the standard mean-shift technique such that it is not limited within a single kernel but uses multiple kernels centered around high motion areas obtained by change detection. We also improve the convergence properties of the mean-shift by integrating two additional likelihood terms. Our simulations prove the effectiveness of the proposed method
Region covariance: A fast descriptor for detection and classification
No full textAbstract. We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix.
- …
