Exponential Stability of Pseudo Almost Periodic Solutions for Cellular Neural Networks with Multi-Proportional Delays

This paper concerns with the pseudo almost periodic solutions for a class of cellular neural networks model with multi-proportional delays. By applying contraction mapping fixed point theorem and differential inequality techniques, we establish some sufficient conditions for the existence and exponential stability of pseudo almost periodic solutions for the model, which improve and supplement existing ones. Moreover, an example and its numerical simulation are given to support the theoretical results.     

Online learning of dynamic multi-view gallery for person Re-identification

Person re-identification receives increasing attentions in computer vision due to its potential applications in video surveillance. In order to alleviate wrong matches caused by misalignment or missing features among cameras, we propose to learn a multi-view gallery of frequently appearing objects in a relatively closed environment. The gallery contains appearance models of these objects from different cameras and viewpoints. The strength of the learned appearance models lies in that they are invariant to viewpoint and illumination changes. To automatically estimate the number of frequently appearing objects in the environment and update their appearance models online, we propose a dynamic gallery learning algorithm. We specifically build up two datasets to validate the effectiveness of our approach in realistic scenarios. Comparisons with benchmark methods demonstrate promising performance in accuracy and efficiency of re-identification.     

A divide-and-conquer hole-filling method for handling disocclusion in single-view rendering

Large holes are unavoidably generated in depth image based rendering (DIBR) using a single color image and its associated depth map. Such holes are mainly caused by disocclusion, which occurs around the sharp depth discontinuities in the depth map. We propose a divide-and-conquer hole-filling method which refines the background depth pixels around the sharp depth discontinuities to address the disocclusion problem. Firstly, the disocclusion region is detected according to the degree of depth discontinuity, and the target area is marked as a binary mask. Then, the depth pixels located in the target area are modified by a linear interpolation process, whose pixel values decrease from the foreground depth value to the background depth value. Finally, in order to remove the isolated depth pixels, median filtering is adopted to refine the depth map. In these ways, disocclusion regions in the synthesized view are divided into several small holes after DIBR, and are easily filled by image inpainting. Experimental results demonstrate that the proposed method can effectively improve the quality of the synthesized view subjectively and objectively.     

Designing an exergaming system for exercise bikes using kinect sensors and Google Earth

This paper proposes an Exergaming system for exercise bikes. With the assistance of a Kinect device and the proposed body-movement-detection algorithm, exercise bike users are required to perform correct neck and shoulder movements to control the airplane trajectory in Google Earth. They can take a flying tour in the virtual reality provided by Google Earth while riding an exercise bike. According to the experimental results, 95 % of the users in the experiment considered the proposed Exergaming system to be very entertaining; more than 85 % of the users affirmed that the assigned neck and shoulder movements effectively help stretch the muscles in these body parts; the detection rate of the proposed body-movement algorithm was over 90 %. Therefore, the proposed Exergaming system is a good assisting system for exercise bikes.     

Mobile multi-view object image search

High user interaction capability of mobile devices can help improve the accuracy of mobile visual search systems. At query time, it is possible to capture multiple views of an object from different viewing angles and at different scales with the mobile device camera to obtain richer information about the object compared to a single view and hence return more accurate results. Motivated by this, we propose a new multi-view visual query model on multi-view object image databases for mobile visual search. Multi-view images of objects acquired by the mobile clients are processed and local features are sent to a server, which combines the query image representations with early/late fusion methods and returns the query results. We performed a comprehensive analysis of early and late fusion approaches using various similarity functions, on an existing single view and a new multi-view object image database. The experimental results show that multi-view search provides significantly better retrieval accuracy compared to traditional single view search.     

Motion vector recovery for video error concealment based on the plane fitting

Multimedia Tools and Applications - In a wireless transmission, the compressed video stream can result in lower quality of image reconstruction with the motion vector mismatch. A motion vector...     

Structural sensitivity analysis of flexible multibody systems modeled with the floating frame of reference approach using the adjoint variable method

For the efficient analysis and optimization of flexible multibody systems, gradient information is often required. Next to simple and easy-to-implement finite difference approaches, analytical methods, such as the adjoint variable method, have been developed and are now well established for the sensitivity analysis in multibody dynamics. They allow the computation of exact gradients and require normally less computational effort for large-scale problems. In the current work, we apply the adjoint variable method to flexible multibody systems with kinematic loops, which are modeled using the floating frame of reference formulation. Thereby, in order to solve ordinary differential equations only, the equations of motion are brought into minimal form using coordinate partitioning, and the constraint equations at position and velocity level are incorporated in the adjoint dynamics. For testing and illustrative purposes, the procedure is applied to compute the structural gradient for a flexible piston rod of a slider–crank mechanism.     

Dual graph regularized NMF model for social event detection from Flickr data

In this work, we aim to discover real-world events from Flickr data by devising a three-stage event detection framework. In the first stage, a multimodal fusion (MF) model is designed to deal with the heterogeneous feature modalities possessed by the user-shared data, which is advantageous in computation complexity. In the second stage, a dual graph regularized non-negative matrix factorization (DGNMF) model is proposed to learn compact feature representations. DGNMF incorporates Laplacian regularization terms for the data graph and base graph into the objective, keeping the geometry structures underlying the data samples and dictionary bases simultaneously. In the third stage, hybrid clustering algorithms are applied seamlessly to discover event clusters. Extensive experiments conducted on the real-world dataset reveal the MF-DGNMF-based approaches outperform the baselines.     

The joint movement of pebbles in solving the ($$N^2-1$$)-puzzle suboptimally and its applications in rule-based cooperative path-finding

The present paper deals with the problem of solving the (\(n^2 - 1\))-puzzle and cooperative path-finding (CPF) problems sub-optimally by rule-based algorithms. To solve the puzzle, we need to rearrange \(n^2 - 1\) pebbles in the \(n \times n\)-sized square grid using one vacant position to achieve the goal configuration. An improvement to the existing polynomial-time algorithm is proposed and experimentally analyzed. The improved algorithm represents an attempt to move pebbles in a more efficient way compared to the original algorithm by grouping them into so-called snakes and moving them together as part of a snake formation. An experimental evaluation has shown that the snakeenhanced algorithm produces solutions which are 8–9 % shorter than the solutions generated by the original algorithm. Snake-like movement has also been integrated into the rule-based algorithms used in solving CPF problems sub-optimally, which is a closely related task. The task in CPF consists in moving a group of abstract robots on an undirected graph to specific vertices. The robots can move to unoccupied neighboring vertices; no more than one robot can be placed in each vertex. The (\(n^2 - 1\))-puzzle is a special case of CPF where the underlying graph is a 4-connected grid and only one vertex is vacant. Two major rule-based algorithms for solving CPF problems were included in our study—BIBOX and PUSH-and-SWAP (PUSH-and-ROTATE). The use of snakes in the BIBOX algorithm led to consistent efficiency gains of around 30 % for the (\(n^2 - 1\))-puzzle and up to 50 % in for CPF problems on biconnected graphs with various ear decompositions and multiple vacant vertices. For the PUSH-and-SWAP algorithm, the efficiency gain achieved from the use of snakes was around 5–8 %. However, the efficiency gain was unstable and hardly predictable for PUSH-and-SWAP.     

Minimal explanations of missing values by chasing acquisitional data

Acquisitional issues widely exist in GPS and sensor networks. They pertain to where, when, and how often data is physically acquired (sampled) and delivered to some query processing systems. Due to the dynamic environment that the data is acquired with the change of monitoring time, acquisitional data are typically a time-stamped stream where a time-stamped value could either contain noises or be missing. Aiming to improve the quality of data acquisition, we focus on the explanations of missing values in this paper. Several techniques have been developed to provide the explanation on relational data, however, they cannot be directly applied in acquisitional stream data due to its dynamic feature, such as the “change” of acquisitional stream data between two adjacent monitoring time is often constrained by some rules. We show that an explanation could be incorrect or unreasonable if those constraints are not taken into account. We propose one novel chasing technique by considering both spatial and temporal correlations to explain missing values and guarantee a minimal explanation. Experimental results show that our approach can efficiently return high-quality and minimal explanations of missing values.