Performance evaluation of object detection algorithms for video surveillance

In this paper, we propose novel methods to evaluate the performance of object detection algorithms in video sequences. This procedure allows us to highlight characteristics (e.g., region splitting or merging) which are specific of the method being used. The proposed framework compares the output of the algorithm with the ground truth and measures the differences according to objective metrics. In this way it is possible to perform a fair comparison among different methods, evaluating their strengths and weaknesses and allowing the user to perform a reliable choice of the best method for a specific application. We apply this methodology to segmentation algorithms recently proposed and describe their performance. These methods were evaluated in order to assess how well they can detect moving regions in an outdoor scene in fixed-camera situations.     

An effective admission control mechanism for variable-bit-rate video streams

For admission control in real-time multimedia systems, buffer space, disk bandwidth and network bandwidth must be considered. The CBR-based mechanisms do not use system resources effectively, since media data is usually encoded with VBR compression techniques. We propose an admission control mechanism based on a VBR data model that has a dynamic period length. In our mechanism, the period can be adaptively changed to maximize the performance, considering both disk bandwidth and buffer space. To compare the performance, extensive simulations are conducted on RR, SCAN, and GSS schemes which have the dynamic period length and the static period length.     

Dual-plan bandwidth smoothing for layer-encoded video

Traditional bandwidth smoothing techniques can be naturally supported by the renegotiated constant bit rate (RCBR) service model, but renegotiation failure in RCBR may cause buffer underflow and interrupt the playback of video. To address this concern, a novel dual-plan bandwidth smoothing (DBS) scheme is proposed in this paper by taking advantage of the SNR scalability of layer-encoded video. Upon renegotiation failure, the proposed scheme can adaptively discard certain enhancement layers to guarantee continuous video playback at the original frame rate. Experiments are carried out to demonstrate the validity of the proposed scheme. The impacts of renegotiation interval, granularity of enhancement layers, and playback buffer size on resulted video quality are also studied. From the simulation results, it is shown that the performance of the RCBR-based DBS scheme can be improved by 1) reducing the minimum time gap of renegotiation interval; 2) employing multilayer video encoding with finer granularity; and/or 3) increasing the playback buffer size.     

Square-root Bryson-Frazier smoothing algorithms

Some new square-root algorithms for Bryson-Frazier smoothing formulas are suggested: square-root algorithms and a fast square-root (or so-called Chandrasekhar type) algorithm. The new square-root algorithms use square-root arrays composed of smoothed estimates and their error covariances. These algorithms provide many advantages over the conventional algorithms with respect to systolic array and parallel implementations as well as numerical stability and conditioning. For the case of constant-parameter systems, a fast square-root algorithm is suggested, which requires less computation than others     

Discrete-time fixed-lag smoothing algorithms

Kalman filtering results are applied to yield alternative computationally stable fixed-lag smoothing algorithms including reduced order and minimal order fixed-lag smoothers. The reduced order smoothing algorithms are new and clearly have advantages over the more familiar algorithms. The properties of such fixed-lag smoothers are also studied.     

New square-root smoothing algorithms

This paper presents new square-root smoothing algorithms for the three best-known smoothing formulas: (1) Rauch-Tung-Striebel (RTS) formulas, (2) Desai-Weinert-Yusypchuk (DWY) formulas, called backward RTS formulas, and (3) Mayne-Fraser (MF) formulas, called two-filter formulas. The main feature of the new algorithms is that they use unitary rotations to replace all matrix inversion and backsubstitution steps common in earlier algorithms with unitary operations; this feature enables more efficient systolic array and parallel implementations and leads to algorithms with better numerical stability and conditioning properties     

Fuzzy smoothing algorithms for variable structure systems

A variable structure system (VSS) is a control system implementing different control laws in different regions of the state space divided by a set of boundary manifolds. The control input switches from one control law to another when the state crosses the boundary manifolds. In general, the control input may not be smooth when switching at these boundary manifolds and may excite high frequency dynamics. This paper proposes two fuzzy rule based algorithms for smoothing the control input. The merits of these fuzzy smoothing control algorithms are illustrated by two examples: a semiactive suspension system based on optimal control and a direct drive robot arm under discrete time sliding mode control. The controller design for these two examples is a blend of traditional control theoretic approaches and fuzzy rule based approaches     

Genetic algorithms for video segmentation

The current paper presents a new genetic algorithm (GA)-based method for video segmentation. The proposed method is specifically designed to enhance the computational efficiency and quality of the segmentation results compared to standard GAs. The segmentation is performed by chromosomes that independently evolve using distributed genetic algorithms (DGAs). However, unlike conventional DGAs, the chromosomes are initiated using the segmentation results of the previous frame, instead of random values. Thereafter, only unstable chromosomes corresponding to moving object parts are evolved by crossover and mutation. As such, these mechanisms allow for effective solution space exploration and exploitation, thereby improving the performance of the proposed method in terms of speed and segmentation quality. These advantages were confirmed based on experiments where the proposed method was successfully applied to both synthetic and natural video sequences.     

Wavelet-based VBR video traffic smoothing

In a typical video application, such as video-on-demand, videos are continuously streamed from a video server to a distributed set of receivers. The constant-quality video compression technique commonly used, variable bit rate (VBR) encoding, produces flows with multiple time-scale rate variability, so smoothing the VBR video traffic within an entire distribution tree presents a challenging task. This paper proposes a novel wavelet-based traffic smoothing (WTS) algorithm. Unlike existing algorithms, the WTS algorithm considers traffic smoothing at multiple resolutions. It results in a pruned version of a full tree, which corresponds to the original VBR traffic. Theoretical analysis and numerical evaluation demonstrate that: 1) WTS performs well across several metrics in smoothing bursty traffic and 2) for a video bit stream with N frames, the computational complexity of WTS is O(NlogN).     

Parallel filtering and smoothing algorithms

This paper develops algorithms for filtering and smoothing for parallel computers. Numerical results are presented and implementation details are discussed. In the example it is illustrated that parallel methods have better convergence properties than nonparallel methods for nonlinear problems.     

Recursive algorithms for Bayes smoothing with uncertain observations

Recursive algorithms for the Bayes solution of fixed-interval, fixed-point, and fixed-lag smoothing under uncertain observations are presented. The Bayes smoothing algorithms are obtained for a Markovian system model with Markov uncertainty, a model more general than the one used in linear smoothing algorithms. The Bayes fixed-interval smoothing algorithm is applied to a Gauss-Markov example. The simulation results for this example indicate that the MSE performance of the Bayes smoother is significantly better than that of the linear smoother.     

Performance evaluation of iterative geometric fitting algorithms

The convergence performance of typical numerical schemes for geometric fitting for computer vision applications is compared. First, the problem and the associated KCR lower bound are stated. Then, three well-known fitting algorithms are described: FNS, HEIV, and renormalization. To these, we add a special variant of Gauss-Newton iterations. For initialization of iterations, random choice, least squares, and Taubin's method are tested. Simulation is conducted for fundamental matrix computation and ellipse fitting, which reveals different characteristics of each method.     

Performance evaluation of PCA-based spike sorting algorithms

Deciphering the electrical activity of individual neurons from multi-unit noisy recordings is critical for understanding complex neural systems. A widely used spike sorting algorithm is being evaluated for single-electrode nerve trunk recordings. The algorithm is based on principal component analysis (PCA) for spike feature extraction. In the neuroscience literature it is generally assumed that the use of the first two or most commonly three principal components is sufficient. We estimate the optimum PCA-based feature space by evaluating the algorithm's performance on simulated series of action potentials. A number of modifications are made to the open source nev2lkit software to enable systematic investigation of the parameter space. We introduce a new metric to define clustering error considering over-clustering more favorable than under-clustering as proposed by experimentalists for our data. Both the program patch and the metric are available online. Correlated and white Gaussian noise processes are superimposed to account for biological and artificial jitter in the recordings. We report that the employment of more than three principal components is in general beneficial for all noise cases considered. Finally, we apply our results to experimental data and verify that the sorting process with four principal components is in agreement with a panel of electrophysiology experts.     

Performance evaluation of artificial intelligence algorithms for virtual network embedding

Network virtualization is not only regarded as a promising technology to create an ecosystem for cloud computing applications, but also considered a promising technology for the future Internet. One of the most important issues in network virtualization is the virtual network embedding (VNE) problem, which deals with the embedding of virtual network (VN) requests in an underlying physical (substrate network) infrastructure. When both the node and link constraints are considered, the VN embedding problem is NP-hard, even in an offline situation. Some Artificial Intelligence (AI) techniques have been applied to the VNE algorithm design and displayed their abilities. This paper aims to compare the computational effectiveness and efficiency of different AI techniques for handling the cost-aware VNE problem. We first propose two kinds of VNE algorithms, based on Ant Colony Optimization and genetic algorithm. Then we carry out extensive simulations to compare the proposed VNE algorithms with the existing AI-based VNE algorithms in terms of the VN Acceptance Ratio, the long-term revenue of the service provider, and the VN embedding cost.     

Fast techniques for the optimal smoothing of stored video

Work-ahead smoothing is a technique whereby a server, transmitting stored compressed video to a client, utilizes client buffer space to reduce the rate variability of the transmitted stream. The technique requires the server to compute a schedule of transfer under the constraints that the client buffer neither overflows nor underflows. Recent work established an optimal off-line algorithm (which minimizes peak, variance and rate variability of the transmitted stream) under the assumptions of fixed client buffer size, known worst case network jitter, and strict playback of the client video. In this paper, we examine the practical considerations of heterogeneous and dynamically variable client buffer sizes, variable worst case network jitter estimates, and client interactivity. These conditions require on-line computation of the optimal transfer schedule. We focus on techniques for reducing on-line computation time. Specifically, (i) we present an algorithm for precomputing and storing the optimal schedules for all possible client buffer sizes in a compact manner; (ii) we show that it is theoretically possible to precompute and store compactly the optimal schedules for all possible estimates of worst case network jitter; (iii) in the context of playback resumption after client interactivity, we show convergence of the recomputed schedule with the original schedule, implying greatly reduced on-line computation time; and (iv) we propose and empirically evaluate an “approximation scheme” that produces a schedule close to optimal but takes much less computation time.     

基于多模态信息的视频描述算法

为了挖掘视频中不同的模态信息,提出一种基于多模态信息的视频描述算法。在基本的编码解码器网络基础上,更加关注视频多模态信息和高级语义属性。在编码器阶段,提取视频的静态特征、光流特征和视频段特征,同时设计语义属性检测网络得到视频高级语义特征。为了避免解码器阶段的曝光偏差和训练损失与评价准则不统一的问题,采用基于强化学习的训练算法直接将客观评价准则作为优化目标来训练模型。所提出的算法在公开视频描述数据集MSVD上取得了很好的实验效果。     

Performance evaluation of vector implementations of combinatorial algorithms

We study the performance and the use of vector computers for the solution of combinatorial optimization problems, particularly dynamic programming and shortest path problems. A general model for performance evaluation and vector implementations for the problems described above are studied. These implementations were done on a CRAY-1 vector computer and the computational results obtained show (i) the adequacy of the performance evaluation model and (ii) very important gains concerning computing times, showing that vector computers will be of great importance in the field of combinatorial optimization.