Video summarization via minimum sparse reconstruction

The rapid growth of video data demands both effective and efficient video summarization methods so that users are empowered to quickly browse and comprehend a large amount of video content. In this paper, we formulate the video summarization task with a novel minimum sparse reconstruction (MSR) problem. That is, the original video sequence can be best reconstructed with as few selected keyframes as possible. Different from the recently proposed convex relaxation based sparse dictionary selection method, our proposed method utilizes the true sparse constraint L₀ norm, instead of the relaxed constraint _L2,1$L_{2,1}$ norm, such that keyframes are directly selected as a sparse dictionary that can well reconstruct all the video frames. An on-line version is further developed owing to the real-time efficiency of the proposed MSR principle. In addition, a percentage of reconstruction (POR) criterion is proposed to intuitively guide users in obtaining a summary with an appropriate length. Experimental results on two benchmark datasets with various types of videos demonstrate that the proposed methods outperform the state of the art.     

An interactive lung field segmentation scheme with automated capability

Feasible clinical application of any automated segmenting methodology demands more than just accuracy. Amendment to the automated delineation is necessary when the algorithm fails, however, integrated solution to such a scenario is largely absent in literature. Hence in this survey we devised an architecture that does both the automated and interactive lung field localizations using a single segmenting engine—random walker algorithm—so that intuitive amendment is only necessary when the automated generated delineation is unsatisfactory. The algorithm proceeds by first extracting 18 intensity profiles running horizontally, each of them equally spacing apart, and in each intensity profile three extreme points denoting the two lungs and the esophagus are determined through profile matching. This done, the algorithm removes profiles that do not intersect with the lung, and the rest of the extreme points are plugged into random walker algorithm to perform segmentation. The achieved accuracy in localization by the above was 0.8875 in terms of overlap measure (the maximum value for this parameter is 1) over 341 images. In the case where unsatisfactory delineation prompts amendment necessary, the user can interactively segment the lung by just a shift on some of the previous-determined points to the desired locations, and random walker algorithm is run again with the amended input. By such a fusion, the benefits of both the automated and interactive segmentation are shared in a single architecture.     

Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation Function

Bartels–Stewart algorithm is an effective and widely used method with an O(n ³) time complexity for solving a static Sylvester equation. When applied to time-varying Sylvester equation, the computation burden increases intensively with the decrease of sampling period and cannot satisfy continuous realtime calculation requirements. Gradient-based recurrent neural network are able to solve the time-varying Sylvester equation in real time but there always exists an estimation error. In contrast, the recently proposed Zhang neural network has been proven to converge to the solution of the Sylvester equation ideally when time goes to infinity. However, this neural network with the suggested activation functions never converges to the desired value in finite time, which may limit its applications in realtime processing. To tackle this problem, a sign-bi-power activation function is proposed in this paper to accelerate Zhang neural network to finite-time convergence. The global convergence and finite-time convergence property are proven in theory. The upper bound of the convergence time is derived analytically. Simulations are performed to evaluate the performance of the neural network with the proposed activation function. In addition, the proposed strategy is applied to online calculating the pseudo-inverse of a matrix and nonlinear control of an inverted pendulum system. Both theoretical analysis and numerical simulations validate the effectiveness of proposed activation function.     

Learning Image-Text Associations

Web information fusion can be defined as the problem of collating and tracking information related to specific topics on the World Wide Web. Whereas most existing work on Web information fusion has focused on text-based multidocument summarization, this paper concerns the topic of image and text association, a cornerstone of cross-media Web information fusion. Specifically, we present two learning methods for discovering the underlying associations between images and texts based on small training data sets. The first method based on vague transformation measures the information similarity between the visual features and the textual features through a set of predefined domain-specific information categories. Another method uses a neural network to learn direct mapping between the visual and textual features by automatically and incrementally summarizing the associated features into a set of information templates. Despite their distinct approaches, our experimental results on a terrorist domain document set show that both methods are capable of learning associations between images and texts from a small training data set.     

基于光纤环网的隧道火灾监控系统研究

文章对基于光纤环网的隧道群火灾报警系统进行研究,分析了其优缺点,提出了解决办法,并完成改造,应用于实际.     

Layered image coding using the DCT pyramid

A block-based subband image coder that exploits the ability to perform decimation in the discrete cosine transform (DCT) domain to effect a pyramidal data structure is described. The proposed "DCT pyramid" has a distinct feature of improved image rendition properties without the associated blocking artifacts at low bit-rates.