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.
In order to transmit live video or video streaming at low bit-rates, the encoder usually needs to reduce the frame rate to cope with the available bandwidth. In this paper, a new dynamic frame-skipping scheme for live video encoding based on motion detection in the adaptive length sliding window is proposed. The length of a sliding window can be adjusted according to bandwidth variation in order to...
In this paper we evaluate the use of Restricted Bolzmann Machines (RBM) in the context of learning and recognizing human actions. The features used as basis are binary silhouettes of persons. We test the proposed approach on two datasets of human actions where binary silhouettes are available: ViHASi (synthetic data) and Weizmann (real data). In addition, on Weizmann dataset, we combine features based...
Gaze movement plays an important role in human visual search system. How to simulate such a system to efficiently encode and decode gaze movement for target searching is a meaningful issue. There are two key points that should be addressed for this issue. First, eye movement is affected by the visual context that includes more than one object in images. It is important to study how to encode the spatial...
A new method for the automatic detection of moving objects directly in the H.264 compressed domain is proposed in this paper. The method takes advantage of the multiple block sizes, which are used during the inter-mode decision by the H.264 encoder. The different blocks/sub-blocks are combined with their associated motion vectors in order to denote a moving object. The method works in the compressed...
Background modeling plays an important role in video surveillance, yet in complex scenes it is still a challenging problem. Among many difficulties, problems caused by illumination variations and dynamic backgrounds are the key aspects. In this work, we develop an efficient background subtraction framework to tackle these problems. First, we propose a scale invariant local ternary pattern operator,...
Techniques for modeling the background of a video sequence can be useful in alternative video coding approaches. Sprite coding has been evolved to provide high quality decoded video frames after transmission by a reduced amount of bits. However, it has also been shown that this works only for a certain kind of video sequences. It also meets quality limits due to the Sprite generation step. To tackle...
We present a novel and efficient multi-view depth map enhancement method proposed as a post-processing of initially estimated depth maps. The proposed method is based on edge, motion and scene depth-range adaptive median filtering and allows for an improved quality of virtual view synthesis. To enforce the spatial, temporal and inter-view coherence in the multi-view depth maps, the median filtering...
One approach that can be used to increase compression efficiency beyond the data rates achievable by state-of-the-art video codecs is to use content-based methods whereby not all the pixels are conventionally encoded. An approach to reduce the data rate is to use different coding methods for pixels belonging to areas containing large amount of detail that are costly to encode, for example textures...
In most of recent video coding standards based on block-based hybrid coding scheme, especially in the state-of-the-art H.264/AVC standard, motion vector information occupies a considerable portion of the whole compressed bitstream. Therefore, the efficient coding of motion vectors has become an essential objective to further reduce the bitrate. In this paper, we propose a novel motion vector coding...
H.264 is the newest video encoding algorithm introduced by ITU, which adopts block matching algorithm (BMA) and supports multiple reference frame. If video sequences only have single moving object and background pictures, using BMA may lead to prediction error and even decreased coding efficiency. And in the object based coding, additional bits for encoding the shape of the objects are required and...
To overcome inaccurate boundary matching algorithm bringing on the miss of the best motion vector and resulting in the bad error concealment effect, the paper proposed a novel effective temporal error concealment algorithm. Using effective temporal-spatial correlation of the motion vectors, it will adaptive construct a limited candidate motion vectors set among the motion vectors of neighboring macroblocks...
In this work, we investigate a working memory approach for efficient temporal prediction in H.264 video coding. After video frames are encoded, objects are extracted, analyzed, and indexed in a dynamic database which acts as a working memory for the H.264 video encoder. During the encoding process, objects with similar spatial characteristics are retrieved from the working memory and used for motion...
We present a novel multi-view depth map enhancement method deployed as a post-processing of initially estimated depth maps, which are incoherent in the temporal and inter-view dimensions. The proposed method is based on edge and motion-adaptive median filtering and allows for an improved quality of virtual view synthesis. To enforce the spatial, temporal and inter-view coherence in the multiview depth...
Since H.264 is a high performance coding standard in with high computational requirements, it is hard to implement on portable devices. According to the human visual system (HVS) research, human eyes can only focus on one area in a frame, which is called region-of-interest (ROI). This phenomenon gives a chance to code all macroblocks unequally. In this work, the ROI is detected using texture contrast...
In recent years there has been a growing interest in developing novel techniques for increasing the coding efficiency of video compression methods. We approach the problem by not encoding all the pixels, in particular, regions belonging to areas that the viewer will not perceive the specific details in the scene could be skipped or encoded at a much lower data rate. This approach can also be expanded...
Motivated by theoretical analysis of the curve fitting problem based on equivalent kernel, in this paper we propose a local adaptive learning and fusion model for side information interpolation in distributed video coding. In the proposed model, each pixel in the interpolated frame is approximated as the linear combination of samples within a local spatio-temporal window using kernel parameters as...
In asymmetric stereoscopic video coding, one view can be coded in a lower resolution of the other. In this scenario, stereoscopic video can be compressed with only moderately increased bandwidth and complexity compared to 2D monoview video coding. The subjective quality degradation of this scenario can be negligible compared to coding two views with original resolution. The low-resolution view can...
An auto-regressive (AR) based side information (SI) generation is proposed in this paper for block based chessboard pattern Wyner-Ziv (WZ) coding, where each WZ frame is split into two sets at encoder and then encoded separately. At the decoder, one set of the WZ frame will be firstly reconstructed, and then proposed AR model is used to generate the SI of the other set, where each pixel is generated...
Unsupervised detection of pan and zoom in soccer sequences allows automatic classification of shots and match analysis. In this work we propose a pan and zoom (both in and out) detector specifically designed for low resolution soccer sequences. Our implementation is based on the analysis of the distribution of the motion vectors, already available in the encoded sequence, among a specific subset of...
The loss of packets is unavoidable when compressed video data is transmitted over error prone channels. In this study, an error resilient coding scheme based on pixel lines decimation is proposed to enhance performance of error concealment for both intra and inter frames. At the encoder, an input picture is decimated by pixel lines into two similar sub-pictures and then they are merged together before...
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.