The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Packet losses or errors of high compressed video stream during transmission over error-prone channel may cause serious decline in video quality. Error concealment (EC) at decoder side is an effective technology to reduce this video degradation. This paper proposes a Dynamic Temporal Error Concealment (DTEC) algorithm for H.264, which chooses different error concealment approach according to the variance...
Packet losses or errors of compressed video streams during transmission over error-prone channel may cause serious decline in video quality. Error concealment (EC) at decoder side is an effective technology to reduce this degradation. This paper proposes a Directional Temporal Boundary Match Algorithm (DTBMA) for H.264 considering pixel differences in three directions and "guessing" the...
In this paper, 3D image segmentation is implemented on Field Programmable Gate Array (FPGA) hardware. Segmentation is performed using the EM/MPM Bayesian algorithm. This algorithm segments 3D images using neighboring pixels in a Markov Random Field (MRF) clique. We have implemented this iterative algorithm in Xilinx FPGA, and have achieved greater than 100 times improvement over standard desktop computing...
In the field of image analysis and retrieval, the representations based on the shape of edge or boundary can be used to model complex forms and properties. In this paper, we give a detailed description of a new shape feature of edge or boundary, the jag-wave feature, which is usually treated as noise in image processing. The jag-wave feature is defined as a special kind of jagged or waved edge or...
Visual object tracking is a problem that has been studied by the computer community for decades. Computational stereo refers to the problem of determining 3-dimensional structure of a scene from two or more images taken from distinct viewpoints. An approach to detect stereo-moving objects with bio-cameras is presented in this thesis. Stereo and motion are detected simultaneously under a modified formulation...
SSD-based object tracking has shown its improved performance compared with mean-shift and many people have made further improvements based on it. However, how kernels should be designed to better cooperate with SSD metric and Newton-style iteration remains unsolved. Our work is to find out the underlying principles for SSD kernel design, which can help make the tracker more sensitive to the object...
This paper presents a splicing method which is based on the edge detection of SUSAN and artificial fish-swarm algorithm, which solved splicing method about the pictures of seldom characters. Firstly, the images are detected edge by SUSAN algorithm. Secondly, it is removed noise according to the morphological method, and it is blocked by edge. Lastly it obtains the extreme points by artificial fish-swarm...
An adaptive kernel method is proposed for anomaly detection in hyperspectral imagery. The conventional RX anomaly detector suffers from high false alarm rates and low probability of detection due to the assumptions that the local background is Gaussian and homogeneous. Many kernel base anomaly detector are of good nonlinear detection performance, but parameter estimation of the kernel function is...
The paper introduces a new system for objectionable image identification based on shape feature extraction. The system targets 82% of the objectionable nude pictures and wrongly classifies 6.98% of the normal images. The processing speed is 0.115s per common image and 0.31s per pornographic image. The training and testing datasets of benign images are open libraries. The performance of the system...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.