scispace - formally typeset
Search or ask a question

Showing papers in "Journal of Visual Communication and Image Representation in 2008"


Journal ArticleDOI
TL;DR: It is argued that video summarisation would benefit from greater incorporation of external information, particularly user based information that is unobtrusively sourced, in order to overcome longstanding challenges such as the semantic gap and providing video summaries that have greater relevance to individual users.

468 citations


Journal ArticleDOI
TL;DR: This work proposes a new method for compressing facial images, based on the K-SVD algorithm, and presents this new method, analyze its results and compare it to several competing compression techniques.

332 citations


Journal ArticleDOI
TL;DR: This work develops an efficient scheme for dominant color extraction and proposes a modification for the MPEG-7 dissimilarity measure, which effectively improves the accuracy of perceptive similarity.

166 citations


Journal ArticleDOI
TL;DR: A proposed scheme for estimating JND (just-noticeable difference) with explicit formulation for image pixels, by summing the effects of the visual thresholds in sub-bands, demonstrates favorable results in noise shaping and perceptual visual distortion gauge for different images, in comparison with the relevant existing JND estimators.

108 citations


Journal ArticleDOI
TL;DR: A novel face segmentation algorithm based on facial saliency map (FSM) for head-and-shoulder type video application that is capable of segmenting the face area quite effectively.

88 citations


Journal ArticleDOI
TL;DR: A novel approach to impulsive noise detection in color images is introduced and a switching filter between the arithmetic mean filter (AMF) and the identity operation is proposed, which achieves a trade-off between noise suppression and signal-detail preservation.

78 citations


Journal ArticleDOI
TL;DR: An approach for detecting ball in broadcast soccer videos using hybrid techniques for identifying ball in medium and long shots and dynamic programming is applied to find the longest path of the graph which gives the actual ball trajectory.

46 citations


Journal ArticleDOI
TL;DR: Design options and experimental results indicate that a simple SVC specific adaptation MANE does clearly outperform the gBSD based adaptation variants, and the conceptual advantages of the description driven approach may outweigh the performance drawbacks in specific applications.

36 citations


Journal ArticleDOI
TL;DR: The distributed approach reduces signaling overhead as well as avoiding scalability issues that come with centralized processing in MANETs, and shows a significant performance gain over both single-server systems and previously proposed multi-source systems.

34 citations


Journal ArticleDOI
TL;DR: A new adaptive slice-size selection technique for efficient slice-level parallelism of H.264/AVC encoding on a multi-core processor using fast macroblock mode selection as a pre-processing step is proposed.

33 citations


Journal ArticleDOI
TL;DR: This work examines the performance of this new distance measure for color image retrieval tasks, by focusing on three parameters: the transformation of the 2D image to a 1D string, the color to character correspondence, and the image size.

Journal ArticleDOI
TL;DR: This paper proposes to study the contribution of multiple SI estimations (in the temporal and view directions) to the global performances of DVC, and proposes new symmetric schemes for longer group of pictures (GOP) in multi-view DVC and shows that it can further exploit the long-term correlations using a new kind of estimation, called diagonal.

Journal ArticleDOI
TL;DR: It is demonstrated that, by making full use of estimated channel state information (CSI) through feedback, a cascade of adaptive operations can be designed to satisfy maximum throughput for scalable video over MIMO systems.

Journal ArticleDOI
TL;DR: The experimental results show that the proposed approach for multiple-people detection and tracking using stereo vision is able to deal with occlusions and to effectively determine both the 3D position of the people being tracked and their 2D head locations in the camera image, and everything is realized in real time.

Journal ArticleDOI
TL;DR: This paper circumvents the need for a multivariate ordering, and proposes a method for directly computing the multivariate extrema of vector sets, using the @a-trimming principle in combination with lexicographical ordering.

Journal ArticleDOI
TL;DR: An algorithm is proposed that can reduce the complexity of the codec by reducing the block mode decision process adaptively by using the direct prediction methods based on block correlation and adaptive rate distortion cost threshold for early stopping.

Journal ArticleDOI
TL;DR: This is the first edge-preserving algorithm for color contrast enhancement in color space and it can enhance the color contrast as the previous algorithm does, but also has an edge- Preservation effect.

Journal ArticleDOI
TL;DR: Novel side information creation techniques are proposed in this paper along with a new frame interpolation framework able to generate higher quality side information at the decoder able to outperform H.264/AVC Intra by up to 3dB with a lower encoding complexity.

Journal ArticleDOI
TL;DR: This work presents a novel approach for optimizing H.264/AVC video compression by dynamically allocating computational complexity and bits for encoding each coding element within a video sequence, according to its predicted MAD.

Journal ArticleDOI
TL;DR: In this article, the authors present an approach for optimizing H.264/AVC video compression by dynamically allocating computational complexity (such as a number of CPU clocks) and bits for encoding each c...

Journal ArticleDOI
TL;DR: This work describes a method for representing 3D (three-dimensional) tree objects by means of a chain code and obtains some tree descriptors of objects on real images, which preserves the shape of trees and allows us to know their geometrical and topological properties.

Journal ArticleDOI
TL;DR: A bit-depth scalable coding solution that is compatible to the scalable extension of H.264/AVC, also known as Scalable Video Coding (SVC), capable of providing an 8-bit AVC main profile or high profile compliant base layer which is multiplexed with a high bit depth enhancement layer through macroblock level inter-layer bit- depth prediction.

Journal ArticleDOI
TL;DR: A novel deblocking algorithm is proposed based on three filtering modes in terms of the activity across block boundaries that outperforms other deblocking algorithms in respect to PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural SIMilarity).

Journal ArticleDOI
He Guo1, Xinyuan Fu1, Feng Chen1, Hongji Yang1, Yuxin Wang1, Han Li1 
TL;DR: A detailed analysis of the 2D deformation algorithm based on non-linear least squares optimization, and it is proved that different mesh structure is of critical importance to deforming result, is provided.

Journal ArticleDOI
TL;DR: A new framework to extract visual attention regions in images using robust subspace estimation and analysis techniques using simple features like hue and intensity endowed with scale adaptivity in order to represent smooth and textured areas in an image.

Journal ArticleDOI
TL;DR: A two-prong approach to achieve rate-distortion (R-D) optimal extraction of SVC bitstreams is proposed and adaptation rules promise R-D convexity along optimal extraction paths and permit the use of steepest-descent strategy to discover the optimal/near-optimal paths.

Journal ArticleDOI
TL;DR: Experimental results demonstrate that this multiple faces tracking system can automatically find new coming faces and recover from occlusion, and run with a high computation efficiency, run at about 20 frames/s.

Journal ArticleDOI
TL;DR: An AMP scheme based on a discontinuity model for intra-media synchronization of video applications over the best-effort networks is introduced and a practical algorithm is established that enables an efficient playout speed control to enhance the intra- media synchronization quality.

Journal ArticleDOI
TL;DR: This paper intends to quantify the distribution of DCT residues with respect to video source and to derive an R-D model to show the advantage of the proposed distribution model.

Journal ArticleDOI
TL;DR: A novel hardware implementation of a disparity estimation scheme targeted to real-time Integral Photography (IP) image and video sequence compression and features minimized memory read operations and extensive simultaneous processing, while taking into concern the memory and data bandwidth limitations of a single FPGA implementation.