Region Covariance: A Fast Descriptor for Detection and Classification

Abstract

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 fetures is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix. European Conference on Computer Vision (ECCV)This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. Abstract. 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.

A survey on face detection in the wild: Past, present and future

“…HoG and LBP were also combined in [88], which achieved excellent performance in human detection with partial occlusion handling. Region covariance is another statistics based feature, proposed in [89] for generic object detection and texture classification tasks. To extract these features the covariance matrices among the color channels and gradient images are computed instead of the histograms.…”

“…A number of follow-up works showed that there is indeed information in the results from the previous nodes, and it is best to reuse them [80,19] etc. Spectral histogram [86] Spatial histogram (LBP-based) [87] HoG and LBP [88] Region covariance [89] SURF [102,103] Composite Joint Haar-like features [62] features Sparse feature set [90] LGB, BHOG [22] Integral Channel Features on HoG and LUV (Headhunter) [26] HoG, HSV, RGB, LUV, Grayscale, Gradient Magnitude [105] Shape features Boundary/contour fragments [94,95] Edgelet [96] Shapelet [97] instead of starting from scratch at each new node. For instance, in [110], the use of a "chain" structure was proposed to integrate historical knowledge into successive boosting learning.…”

Gabor wavelets combined with volumetric fractal dimension applied to texture analysis

“…For fast computation, integral image technique is used (Tuzel et al, 2006). The P and Q tensor used for the computation are defined by:…”

Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models

“…In our implementation, we use 8 bins for each channel to form a 24-element vector. To describe the image texture, we use a descriptor based on covariance matrices of image features proposed in [21]. It has been shown to give good performance for texture classification and object categorization.…”

“…In our implementation, correlation coefficient is chosen for simplicity. The distance measurement of covariance matrices is determined by solving a generalized eigenvalues problem, which is described in [21].…”