Video cameras are no ionger being used only in their traditional role of providing "Viewable pixels, but are rapidly becoming sources of intelligent information about the world. More recently 3D cameras are being...
详细信息
ISBN:
(纸本)1424411807
Video cameras are no ionger being used only in their traditional role of providing "Viewable pixels, but are rapidly becoming sources of intelligent information about the world. More recently 3D cameras are being developed to directly provide 3D measurements of objects and scenes. Appearance and geometry of objects and scenes, and the temporal dynamics of objects are the key information bearing sources for deriving visual intelligence. This talk will highlight sensor data analysis techniques for creating intelligent representations from 2D and 3D sensors. Intelligent sensor data analytics can be performed for mobile as well as widely distributed static sensor platforms. Applications ranging from 3D video manipulation, 3D situational awareness, wide area surveillance and tracking to video/3D object recognition and fingerprinting will be used to illustrate the work.
Parametric active contours have been used extensively in computervision for different tasks like segmentation and tracking. However, all parametric contours are known to suffer from the problem of frequent bunching a...
详细信息
In this study, we aim to determine if iris recognition accuracy might be improved by correcting for the refractive effects of the human eye when the optical axes of the eye and camera are misaligned. We undertake this...
详细信息
Informative Vector Machine (IVM) is an efficient fast sparse Gaussian processs (GP) method previously suggested for active learning. It greatly reduces the computational cost of GP classification and makes the GP lear...
详细信息
This paper describes a patch-based approach for rapid image correlation or template matching. By representing a template image with an ensemble of patches, the method is robust with respect to variations such as local...
详细信息
We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic interest points. We propose a hierarc...
详细信息
We study the influence of numerical conditioning on the accuracy of two closed-form solutions to the overconstrained relative orientation problem. We consider the well known eight-point algorithm and the recent five-p...
详细信息
In this paper, we present a modified hidden Markov model with emission probabilities modelled by kernel density estimation and its use for activity recognition in videos. In the proposed approach, kernel density estim...
详细信息
A well-built dataset is a necessary starting point for advanced computervision research. It plays a crucial role in evaluation and provides a continuous challenge to stateof-the-art algorithms. Dataset collection is,...
详细信息
Template matching of iris images for biométrie recognition typically suffers from both local deformations between the template and query images and large occlusions from the eyelid. In this work, we model deforma...
详细信息
暂无评论