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.
We propose a method to detect abnormal crowd behavior using integrated multiple behavior models. Traditional abnormal detection methods are based only on personal behavior models. However, a single behavior model cannot accurately reflect complex crowd behavior. To solve this problem, we introduce an integrated multiple behavior model for accurate abnormal behavior detection in a complex crowd scene...
This paper presents an approach to identify a weapon from a single image using a weapon ontology. Ontological nodes selected by experts store convex hull (CH) sequences for their descendants, whereas the ontological leafs are labeled with object boundary sequences. The latter are generated from object boundary vertices, while the CH sequences are generated from objects' CHs. The object's boundary...
In cardiac gated SPECT, image reconstruction suffers from several degrading factors including limited data counts, depth-dependent blur, attenuation, scatter, and motion blur. In our recent work it was demonstrated that use of motion-compensated temporal processing could lead to improved accuracy in 4D reconstruction. In this work we investigate how different optical flow estimation methods can affect...
We present a variant of the classic problem of anomaly detection in hyperspectral imagery. In this variant, the anomalous signatures are assumed to be additive and to exhibit spectra that are sparse - that is, only a few of the many hyperspectral channels are significantly nonzero.
Major challenges in brain research include understanding how the brain retrieves, processes, and transmits information along with understanding how information is stored. Therefore, connectivity analyses are vital in exploring information flow and temporal interactions between particular brain regions. This paper presents the results of two different types of connectivity analysis on previously acquired...
Sport video shot classification is a basic step in the sport video processing. For many purposes such as event detection and summarization, shot classification is needed for content filtering. In this paper, we present a new method for soccer video shot classification. At first, in-field and out-of-field frames are separated. In in-field frames three features based on number of connected components...
This paper presents a system that can automatically determine whether the quality of a retinal image is sufficient for computer-based diabetic retinopathy (DR) screening. The system integrates global histogram features, textural features, and vessel density, as well as a local non-reference perceptual sharpness metric. A partial least square (PLS) classifier is trained to distinguish low quality images...
This paper presents the effectiveness of locally tuned sine nonlinear (LTSN) image enhancement technique on poor contrast and low quality images that exhibit dark shadows and over exposed regions due to the limited dynamic ranges of imaging and display devices. We use a wide area motion imagery data [1] to evaluate the performance of the LTSN method. A quantitative evaluation is performed by estimating...
Improvement in the quality of Liquid Crystal Displays (LCD) triggers a significant surge in the 3DTV market. A large segment of the 3DTV market has adopted active shutter glasses (active 3DTV). In this system, crosstalk is an important factor that affects the viewing quality of active 3DTV. This paper proposes a mathematical model for crosstalk and analyses the temporal, spatial, LCD-based and liquid...
In this paper, we outline an algorithm for the automatic segmentation of sparse data in order to detect possible terrain-deformation phenomena. Segmentation is accomplished through a graph cut technique. In the graph structure, for each edge, we derive a unique energy by combining multiple independent energies tailored toward accurately locating the boundaries of spot-like, subsiding regions. We then...
This paper proposes a novel background subtraction method to detect microcalcifications. The proposed method is a Laplacian pyramid scheme with the low pass filter replaced by the squeeze box filter (SBF). The SBF was originally developed to remove speckle noise from medical B mode ultrasound images. The SBF is adapted to identify the background of mammographic images. Thus microcalcifications can...
Extensive research has been conducted relating the natural scene statistics of luminance and depth; however, very little work has been done on analyzing the statistical relationships between depth and chromatic information. In this paper, we examine and derive statistical models between disparity and both luminance and chrominance information by transforming natural images into the more perceptually...
We describe a study that aims towards enhancing our understanding of the perception of H.264/AVC compressed stereoscopic 3D videos, in particular spatial video quality, depth quality, visual comfort and overall 3D video quality. The results of this study indicate that the human subjects have diverse opinions on depth quality scores but a high agreement on spatial video quality. Their agreement on...
A Computer Aided Diagnosis system based on multiscale amplitude-modulation frequency-modulation (AM-FM) methods has been recently developed for discriminating between normal and pathological retinal images. The original Matlab implementation of this system required large amounts of computational time and memory resources that would not permit real-time patient consultation. In this manuscript, we...
Most of the driver assistance systems do not produce accurate results in poor weather conditions. Poor visibility is considered to be a main reason for accidents. The researchers have paid attention on developing various driver assistance systems in order to assure road safety. Image degradation is a severe problem in computer vision applications such as driver assistance systems, terrain classification...
In this paper, we introduce a new method to detect dust clouds on NOAA-AVHRR satellite images. The approach involves the use of the region growing segmentation algorithm. The region growing starts with a set of seed points obtained from the band math image, which is known to be a good indicator of dust clouds due to physical reasons, and the result will be a binary image that represents the improved...
We developed a measure of cytoskeletal linearity in order to study the biological properties of normal and hyperphosphorylated Microtubule Associated Protein Tau (MAPT). The effect of site-specific tau phosphorylation on the microtubule network was examined and the stability of the actin cytoskeletal was evaluated to determine its state under the influence of P-tau. A custom ImageJ plugin using the...
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.