We present a novel formulation of exemplar-based inpainting as a global energy optimization problem, written in terms of the offset map. The proposed energy function combines a data attachment term that ensures the continuity of reconstruction at the boundary of the inpainting domain with a smoothness term that ensures a visually coherent reconstruction inside the hole. This formulation is adapted to obtain a global minimum using the graph cuts algorithm. To reduce the computational complexity, we propose an efficient multiscale graph cuts algorithm. To compensate the loss of information at low resolution levels, we use a feature representation computed at the original image resolution. This permits alleviation of the ambiguity induced by comparing only color information when the image is represented at low resolution levels. Our experiments show how well the proposed algorithm performs compared with other recent algorithms.

We present a method for detecting appearances of logos in low-resolution video sequences. The method is based on matching of SIFT descriptors, plus several heuristics. The logos must come from a small database of possible logos. The emphasis is not on speed but on reliability, although the method can be executed in real time using a parallel computer.

This paper presents a spatial string matching method to incorporate spatial information into the bag-of-words model, which represents an image as an unordered distribution of local features. Spatial constraints among neighboring features are explored in order to achieve better discrimination power for image classification. The features from neighboring points are combined together and taken as a spatial string, and then our method matches the images according to the similarity of string pairs. The categorization problem can be formulated using KNN or SVM classifier based on the spatial string matching kernel. The proposed method is able to capture spatial dependencies across the neighboring features. Experiment results show promising performance for image classification tasks.

A depth image-based error concealment algorithm for 3-D video transmission is proposed, which utilizes the strong correlations between 2-D video and its corresponding the depth map. We first investigate the internal characteristics of the macroblock in the depth map, and then take advantage of these characteristics to recover accurately the lost motion vector for the corrupted blocks, with the joint consideration of the neighbor information and the corresponding depth. Experimental results show that the proposed method provides significant improvements in terms of both objective and subjective evaluations.

During video transmission over error-prone networks, the compressed bit stream is often corrupted by channel errors which may cause the video quality degrading suddenly. In this paper, we present a novel temporal error concealment technique as a post-processing tool at the decoder side for recovering the lost information. In order to recover the lost motion vector, an improved decoder motion vector estimation (DMVE) criterion is introduced which considers temporal correlation and motion trajectory together. We utilize pixels in the two previous frames as well as surrounding pixels of the lost block. The best motion vector is determined according to the criterion, and then the lost pixels are recovered using motion compensation. Simulations show that the proposed technique can achieve remarkable objective (PSNR) and subjective gains in the quality of the recovered video.

During transmission over error-prone networks, the compressed video signal may suffer a large drop in video quality for the block-based motion-compensation scheme. Error recovery is widely used in video decoders to reconstruct corrupted regions. In this paper, we propose a new spatial error recovery method utilizing multi-directional inpainting. It contains eight single-directional inpaintings which perform unsymmetrical matching to search for suitable information and keep local continuity. We also present a linear combination method which merges different directional matching patches to alleviate the error propagations. Experimental results show that the proposed method provides significant gains in both subjective and objective measurements.

In this paper, we present a new motion-compensated interpolation method for frame rate up-conversion based on spatial and temporal correlation. First, the motion vectors (MVs) embedded in the bit-stream are examined and corrected by using the spatial correlation in the MV field. Second, motion trajectory based MV estimation for the block in the interpolated frame is used to gain the initial value. Third, further refinement on the estimated MV is performed based on consideration of the spatial correlation in the interpolated frame and temporal correlation in the before and after frames together. Finally, bi-directional interpolation is applied to obtain final recovered pixels using the refined MV. Experimental results show that the proposed algorithm achieves a significant increase on PSNR and also a great improvement of visual performance.

In video transmission over unreliable channels such as wireless channels or the Internet, transmission errors by for example packet loss are inevitable. For low bit-rate video applications, the loss of a packet may result in the loss of a whole video frame. In this paper, we propose a new algorithm to recover the lost frame. The proposed algorithm explores the spatial and temporal correlation among motion vectors integrative, and then estimates the motion vector field of the lost frame. Finally, adaptive overlapped block motion compensation is used to reconstruct the concealed picture. Results show that the proposed algorithm outperforms other techniques in both PSNR and subjective visual quality.

This paper presents a spatial error concealment technique using "verge points" which are the high-curvature points on image surfaces. Associated with curvature information, the verge points provide important characteristics in reconstructing broken edges. In our method, only a single layer of verge points surrounding the missing area are extracted. The broken edges are reconstructed by pairing these verge points with respect to both the curvature information and their neighboring pixel values. Simulations show that with our pairing criterion, most of the object edges are recovered and our concealment technique yields satisfactory results especially in terms of subjective perception.

Seven variable block sizes are adopted for inter-frame MB (macroblock) coding in H.264. This new feature achieves significant coding gain. However, the computation complexity of the mode decision is extremely high when RD (rate distortion) algorithm is used. In this paper, we propose a fast mode decision algorithm with fast coding block size selection based on MB motion characteristic for inter frames. In this algorithm, the residual_MB is first gotten through motion estimation for the MB. Then, the motion characteristic of the MB is extracted through careful analysis of the texture in the residual_MB. At last, the optimization mode for the MB is decided according to the motion characteristic. Experimental results show that the mode decision can save significantly computational complexity at cost of a little degradation of RD performance.

Periodic broadcasting schemes can improve the efficiency of video-on-demand (VOD) services by reducing the bandwidth requirement to transmit popular videos. The harmonic broadcasting scheme has the best performance in reducing service bandwidth under a given access time, but it uses too many channels. However, a multiplexed harmonic broadcasting scheme that overcomes this drawback is now proposed. This scheme divides each video into equal-sized segments and then broadcasts segments periodically in a small number of sever channels with equal bandwidth. The idea of segment-to-channel mapping in the scheme is inspired by the time division multiplexing system. Each segment is divided equally into several subsegments; subsegments of different segments are multiplexed in a slot with the guarantee of being able to keep playing out continuously for every user. The proposed scheme outperforms the pagoda broadcasting and recursive frequency splitting schemes in reducing the viewers' maximum waiting time, and the scheme requires less client storage.

Efficient streaming media delivery scheme used multimedia service can largely increase system service ability by reducing the resource requirement. Because of the heterogeneity in the underlying network environments, streaming media delivery scheme should provide different, appropriate video quality to serve clients with different bandwidth. In this paper, we present an efficient streaming media delivery scheme with the aid of proxy caching to delivery layered encoded video for heterogeneous clients. The threshold-based multicast technique is used to delivery video streams form server to proxy via backbone network. In order to reduce the bandwidth requirement of the backbone network, we develop an effective approach to determine which layers of which videos should be cached according to the request rates. A simple and efficient replacement algorithm is presented to deal with the varying request rates. Simulation results demonstrate that our scheme achieve significantly bandwidth reduction

In video-on-demand (VOD) system, a periodic broadcast technique like fast broadcasting scheme has been shown to be very effective for serving a popular video in reducing the demand on server bandwidth. A reactive server transmission approach like patching scheme is more suitable for the video that is not popular enough. However, these approaches are not suited for the instance that the level of demand on a video changing greatly with time. In this paper, we propose a novel adaptive hybrid delivery scheme which allocates adaptively transmission resources according to the varying client request rate. The scheme tries to dynamically search the optimal number of channel assigned to the video by the newly updated request rate so as to minimize the bandwidth requirement. Simulation results show that the scheme improves the performance of VOD service significantly in terms of total server bandwidth requirement