Match-time covariance for descriptors
نویسندگان
چکیده
Local descriptor methods are widely used in computer vision to compare local regions of images. These descriptors are often extracted relative to an estimated scale and rotation to provide invariance up to similarity transformations. We call this extract-time covariance (ETC) following the language of [1]. ETC is an imperfect process, however, and can produce errors downstream. Figure 1 illustrates the deterioration of common methods under changing scale and rotation.
منابع مشابه
Object Detection and Matching with Mobile Cameras Collaborating with Fixed Cameras
A system is presented to detect and match any objects with mobile cameras collaborating with fixed cameras observing the same scene. No training data is needed. Various object descriptors are studied based on grids of region descriptors. Region descriptors such as histograms of oriented gradients and covariance matrices of different set of features are evaluated. A detection and matching approa...
متن کاملImage segmentation with superpixel-based covariance descriptors in low-rank representation
This paper investigates the problem of image segmentation using superpixels. We propose two approaches to enhance the discriminative ability of the superpixel’s covariance descriptors. In the first one, we employ the Log-Euclidean distance as the metric on the covariance manifolds, and then use the RBF kernel to measure the similarities between covariance descriptors. The second method is focus...
متن کاملA Master-Slave Approach to Detect and Match Objects Across Several Uncalibrated Moving Cameras
Most multi-camera systems assume a well structured environment to detect and match objects across cameras. Cameras need to be fixed and calibrated. In this work, a novel system is presented to detect and match any objects in a network of uncalibrated fixed and mobile cameras. A master-slave system is presented. Objects are detected with the mobile cameras (the slaves) given only their observati...
متن کاملHuman Detection Based on Covariance Features and SVM
Detecting pedestrians is a challenging problem owing to the motion of the subjects, the camera and the background and to variations in pose, appearance, clothing, illumination and background clutter. The Region Covariance Matrix (RCM) descriptors show experimentally significantly out-performs existing feature sets for pedestrian detection. In this paper, we present an efficient features extract...
متن کاملStochastic Dykstra Algorithms for Metric Learning on Positive Semi-Definite Cone
Recently, covariance descriptors have received much attention as powerful representations of set of points. In this research, we present a new metric learning algorithm for covariance descriptors based on the Dykstra algorithm, in which the current solution is projected onto a half-space at each iteration, and runs at O(n) time. We empirically demonstrate that randomizing the order of half-spac...
متن کامل