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.
Motion estimation is a very important topic in computer vision and image sequence compression. However, most commonly used motion estimation algorithms do not take into consideration any motion invariances that a certain local motion might possess. In this paper, a technique for estimating the invariant motion parameters of non-translational motion fields is proposed, which leads to more efficient...
Video surveillance currently is one of the most active research topics in public safety and security, in which foreground extraction is important and fundamental for further processing, such as target tracking, activity recognition, and behavior prediction. In this paper, by assuming the background is highly correlated across different frames, we propose to separate foregrounds via speeded up low...
In this paper, we propose a method for detection and tracking of multiple planes in sequences of Time of Flight (ToF) depth images. Our approach extends the recent J-linkage algorithm for estimation of multiple model instances in noisy data to tracking. Instead of randomly selecting plane hypotheses in every image, we propagate plane hypotheses through the sequence of images, resulting in a significant...
In the recent work of Candes et al, the problem of recovering low rank matrix corrupted by i.i.d. sparse outliers is studied and a very elegant solution, principal component pursuit, is proposed. It is motivated as a tool for video surveillance applications with the background image sequence forming the low rank part and the moving objects/persons/abnormalities forming the sparse part. Each image...
The growth of new image technologies has created a need for techniques that can be used for copyright protection of digital images, video and audio. One approach for copyright protection is to introduce an invisible signal, known as a digital watermark, into an image or video sequence. Wavelet-based watermark exploit the frequency and spatial of the transformed data in multiple resolutions to gain...
Vision based computation of the moving CCD camera in an outdoor environment is one of the most difficult tasks in the computer vision (CV) research field. Currently, to implement only one CV function steadily, one even needs to develop a series of algorithms to meet the computational requirement of the complex environment change inevitably. So the choice of the switch occasion of these different algorithms...
This paper introduces a new sparsity prior to the estimation of dense flow fields. Based on this new prior, a complex flow field with motion discontinuities can be accurately estimated by finding the sparsest representation of the flow field in certain domains. In addition, a stronger additional sparsity constraint on the flow gradients is incorporated into the model to cope with the measurement noises...
This paper introduces a system for three-dimensional (3D) reconstruction of underwater environments using multiple images acquired by an acoustical camera from different points of view. The final target of the work is to produce a full 3D representation of the observed environment to improve its exploration and analysis. Indeed, as the DIDSON acoustic camera provides sequences of 2D images (distance...
In this paper, we propose a robust vehicle tracker for Infrared (IR) videos motivated by the recent advance in compressive sensing (CS). The new eL1-PF tracker solves a sparse model representation of moving targets via L1 regularized least squares. The sparse-model solution addresses real-world environmental challenges such as image noises and partial occlusions. To further improve tracking performance...
This paper proposes the novel robust SRR algorithm that can be effectively applied on the sequence that are corrupted by various noise models and can be applied on the real or standard sequence. First, the proposed SRR algorithm is based on the Geman&McClure norm that used for measuring the difference between the projected estimate of the high quality image and each low high quality image and...
In image denoising techniques, the state-of-the-art Discrete Cosine Transform (DCT) domain filters manifest good performance of reducing additive Gaussian white noise (AGWN). Two DCT domain filters, i.e., the block-matching three-dimensional (BM3D) DCT filter and the shape-adaptive (SA) DCT filter, have been investigated. However, these DCT domain filters introduce the temporal fluctuation artifact...
We present a method for recovering 3D shapes of deformable surfaces from monocular image sequences. State-of-the-art methods on this problem (Salzmann et al., 2007) utilize L??-norm of re-projection residual vectors and formulate the tracking problem as a second order cone programming (SOCP) problem. Instead of using L?? which is sensitive to outliers, we use L2-norm of re-projection errors. Generally,...
This article introduces a new hierarchical version of a set of motion detection algorithms called ????. These new algorithms are designed to preserve as much as possible the computational efficiency of the basic ???? estimation, in order to target real-time implementation for low power consumption processors and embedded systems.
The problem of gait period detection was transformed to that of regional characteristics analysis in a single frame, namely, the gait period was divided according to region characteristic variable in each frame. A method for gait period detection based on regional characteristics analysis is proposed in this paper. Gait video sequences were coarsely classified into frontal and non-frontal ones in...
A method based on the particle filter was proposed to resolve the problem of target track in looking forward sonar image sequences. The theory of particle filter was illustrated, and it was used to estimate the situation of objects in sonar images. Considering the relation between the process noise and the steady results, process noise was set by the adaptive strategy. At last, the results of experiments...
Immersive sound spaces which are synthesized using virtual reality techniques have recently been developed to realize highly realistic telecommunication interactions. In real world soundscapes the sounds we usually listen to include background or ??ambient?? sounds such as the sounds of the ventilation system in a room. However, current virtual auditory display systems generate point sound sources...
Recent results in SRR (Super Resolution Reconstruction) demonstrate that the fusion of a sequence of low-resolution noisy blurred images can produce a higher-resolution image or sequence. Since noise is always present in practical acquisition systems, almost video enhancement algorithms are developed assuming AWGN model for the corrupting noise. When the underlying video measurements are corrupted...
A common method for real time moving object detection in image sequences is background removal, also referred to as background subtraction. The numerous approaches differ in the type of background model used and the procedure used to update the model. This paper discusses modeling each 4 times 4 pixel patch of an image through a set of coefficient vectors which are obtained by means of a discrete...
This paper has brought forth a zero-watermark algorithm for video which is based on the Krawtchouk moment invariants of original images to counterattack RST attack. Due to the stability of the seven lower Krawtchouk moment invariants exhibited in geometrical transformation, the seven moment invariants of the video frames should be calculated first and then construct the watermark sequence with zero-watermarking...
This paper presents a robust image watermarking method in discrete cosine transform (DCT) domain based on chaotic sequences encryption. Exploiting some characteristics of human visual system (HVS) and DC(direct current) components having much larger perceptual capacity than any AC (alternating current)components, watermark is embedded into the DC components of the host image. First, we scramble 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.