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.
Visualization of the 3D point cloud model has played a crucial part in augmented reality and virtual reality for a long time. Besides, the technique of modeling also greatly benefit the application related to understanding crowd dynamics. In this paper, we introduce a technique to restore the the background area occluded by the front objects from a single viewpoint. In our procedure, we adopt the...
A major cause of deaths among the elderly relates to accidental falls. Such falls are of particular medical concern to this population because they often result in severe injuries, since senior citizens usually live alone and cannot ask for help when accidents happen. In this paper, we propose a fall detection system with the help of a Gaussian mixture background model to build the background before...
Clustered graphs have been widely consisted in Graph Drawing to overcome the problem of drawing large (or huge) graphs with thousands, or perhaps millions of nodes. Force-directed algorithm is one of the available approaches to draw such graphs with good layouts. However, the force directed methods are often produce very different layout outcomes based on different clustering algorithms that greatly...
To achieve fast and accurate text detection from videos, we propose an efficient coarse-to-fine scheme comprising three stages: key frame extraction, candidate text line detection and fine text detection. Key frames, which are assumed to carry texts, are extracted based on multi-threshold difference of color histogram (MDCH). From the key frames, candidate text lines are detected by morphological...
Edge preserving smoothing prior to image segmentation is very important, since the image detailed information is mostly in edges, and smoothing uncorrupted pixels can sharply reduce the image quality. Hence, a novel noise detection method is essential to identify the noised pixels and noise-free pixels. In this paper, the noise detection is based on the difference between the pixel of interest value...
Most learning-based video semantic analysis methods require a large training set to achieve good performances. However, annotating a large video is laborintensive. This paper introduces how to construct the training set and reduce user involvement. There are four selection schemes proposed: clustering-based, spatial dispersiveness, temporal dispersiveness, and sample-based which can be used construct...
Accurate liver segmentation from abdominal computed tomography (CT) images is one of the most important steps for computer aided diagnosis (CAD) for liver CT. Recently, interactive segmentation plays an important role in liver segmentation. In this paper we propose a fast hybrid method for liver segmentation from abdominal CT image. Firstly, the CT image is enhanced and denoised by linear stretch...
In this paper, a color analysis post-processing deblocking filter is proposed to reduce the blocking effects. This proposed algorithm is suitable for the current block-based video standards without any modification. The proposed algorithm uses Sobel operator and Wavelet Transform to accurately detect the blocking effects at 4times4 or 8times8 blocking boundaries automatically. In the filtering stage,...
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.