We address the problem of pose estimation in videos. The part detectors play important roles, but traditional template-based detectors (e.g. Histogram of Gradient, HoG) fail at pose estimation due to the high variabil...
详细信息
ISBN:
(纸本)9781479983407
We address the problem of pose estimation in videos. The part detectors play important roles, but traditional template-based detectors (e.g. Histogram of Gradient, HoG) fail at pose estimation due to the high variability in appearance. We present an adaptive representation of appearance and shape for articulated human body. The full representation of human body is based on the flexible mixture-of-parts model. We train a Naive Bayes classifier to obtain a confidence score of estimated pose by the basic mixture model, and based on the confidence we learn an instance-specific appearance model. For between-frame consistency, we design a time-efficient energy function for motion cues instead of complex motion models. We incorporate these models into a framework that allows for efficient inference. Quantitative evaluation of pose estimation conducted on two video datasets demonstrates the effectiveness of the proposed method.
This paper studies the application of H2 optimal control to speed regulator for vector controlled induction motor drives.A mechanical movement model derived from vector control is employed in the *** analytical optima...
详细信息
ISBN:
(纸本)9781479970186
This paper studies the application of H2 optimal control to speed regulator for vector controlled induction motor drives.A mechanical movement model derived from vector control is employed in the *** analytical optimal speed controller is obtained which has a form of PI *** based on MATLAB/Simulink is carried out to verify the control scheme,and the results show that the designed controller has good speed tracking ability for various speed commands and is robust against load torque variations.
In this work, we propose a discriminative tracklets representation for motion pattern extraction from crowded scene. The representation incorporates relative position, velocity, and direction information of tracklet i...
详细信息
ISBN:
(纸本)9781479983407
In this work, we propose a discriminative tracklets representation for motion pattern extraction from crowded scene. The representation incorporates relative position, velocity, and direction information of tracklet into one compact form by shaping it within a rectangle. We adopt deep belief networks to extract low-dimensional features from this representation. It not only reduces the computational complexity for the following clustering, but also achieves more discriminative tracklets representation which is invariant to noises brought by tracking failures. To determine the spatio-temporal distribution of each motion pattern, a robust clustering scheme composed of three clustering procedures is proposed. Comprehensive experiments in multiple datasets validate the effectiveness of our approach.
In this paper, we propose a sampling approach of reference points used for performance metrics of multi-objective evolutionary algorithms. Traditional reference point sampling methods, such as the Das and Dennis metho...
详细信息
ISBN:
(纸本)9781509006243
In this paper, we propose a sampling approach of reference points used for performance metrics of multi-objective evolutionary algorithms. Traditional reference point sampling methods, such as the Das and Dennis method, usually sample the reference points via a set of uniformly distributed weight vectors generated on an ideal hyper-plane in objective space, which however often ignore the geometric shape of a specific Pareto front. Therefore, we propose a novel reference point sampling approach by taking the specific shape of the Pareto optimal front to be tackled into account for measuring the performance of multi-objective evolutionary algorithms. The performance of the proposed reference point sampling method against the other two state-of-the-art sampling methods is tested on six test instances in various conditions, which clearly demonstrate the effectiveness and superiority of the proposed sampling method.
In sentiment analysis, polarity shifting means shifting the polarity of a sentiment clue that expresses emotion, evaluation, etc. Compared with other natural language processing (NLP) tasks, extracting polarity shifti...
In sentiment analysis, polarity shifting means shifting the polarity of a sentiment clue that expresses emotion, evaluation, etc. Compared with other natural language processing (NLP) tasks, extracting polarity shifting patterns from corpora is a challenging one because the methods used to shift polarity are flexible, which often invalidates fully automatic approaches. In this study, which aimed to extract polarity shifting patterns that inverted, attenuated, or canceled polarity, we used a semi-automatic approach based on sequence mining. This approach greatly reduced the cost of human annotating, while covering as many frequent polarity shifting patterns as possible. We tested this approach on different domain corpora and in different settings. Three types of experiments were performed and the experimental results were analyzed, which will be reported in this paper.
This paper proposes an improved non-dominated sorting genetic algorithm(NSGA2)-DNSGA2, with the aim of preserving diversity of obtained optimal solution and avoiding the original NSGA2 algorithm falling into local opt...
详细信息
ISBN:
(纸本)9781467374439
This paper proposes an improved non-dominated sorting genetic algorithm(NSGA2)-DNSGA2, with the aim of preserving diversity of obtained optimal solution and avoiding the original NSGA2 algorithm falling into local optimal. The proposed DNSGA2 algorithm which introduces a differential mutation operator to replace the original polynomial mutation because the method of differential local search is helpful to the uniformity of Pareto optimal solution set. The performance of the proposed DNSGA2, NSGA2 and W-LRCD-NSGA2(Based on left-right crowding distance non-dominated sorting genetic algorithm) are compared via four benchmark functions. Simulation results indicate that the diversity and uniformity of Pareto optimal solution obtained by DNSGA2 are better than the other two algorithms.
In this paper, the problem of control algorithm design for a class of nonlinear two-input and two-output (TITO) networked controlsystems (NCSs) with non-Gaussian random time delays is investigated, where a general no...
详细信息
In this paper, the problem of control algorithm design for a class of nonlinear two-input and two-output (TITO) networked controlsystems (NCSs) with non-Gaussian random time delays is investigated, where a general non-linear auto-regressive moving average with exogenous model is used to describe the plant. Due to the non-Gaussian random time delays involved in the systems, it is insufficient to obtain a satisfactory optimal control algorithm by only controlling the expected value of the tracking errors. The Renyi entropies of the tracking errors and control inputs are adopted to characterize the randomness of the closed-loop system. The formulations of the probability density functions (PDFs) of the tracking errors and control inputs are deduced. By minimizing the new performance index, a recursive optimal control algorithm is obtained. Furthermore, the local stability condition of the closed-loop systems is established. Finally, the simulation results are presented to illustrate the effectiveness of the proposed method.
Vehicular crowdsensing has attracted lots of attentions due to its low cost and timeliness for urban sensing applications such as traffic estimation and environment monitoring. It is of great importance for a vehicula...
详细信息
ISBN:
(纸本)9781509002443
Vehicular crowdsensing has attracted lots of attentions due to its low cost and timeliness for urban sensing applications such as traffic estimation and environment monitoring. It is of great importance for a vehicular crowdsensing system to recruit a limited number of vehicles to achieve a maximum sensing coverage. It is challenging due to the unpredictable behaviors of vehicles. In this paper, an efficient vehicle recruiting scheme is proposed by minimizing the vehicle's trajectory. To simplify the recruiting scheme design, a heuristic algorithm is firstly proposed. Then considering the dynamics of vehicles in the real world, a dynamic threshold based online algorithm is presented. We evaluate the performance of the proposed algorithms through estimating the Urban Heat Island of Shanghai, China in the real word data. The results demonstrate that the proposed algorithms outperform existing algorithms by reducing more than 50% of vehicles needed and improving the estimation accuracy.
The operation of splicing on words was introduced by Tom Head while proposing a theoretical model of DNA recombination. Subsequent investigations on splicing on linear and circular strings of symbols have resulted in ...
详细信息
This paper presents a use of multi-core DSP TMS320C6678 for the squinted-looking synthetic aperture radars (SARs) real-time signal processing method. This paper first briefly introduces the squinted-looking SAR algori...
详细信息
ISBN:
(纸本)9781849199940
This paper presents a use of multi-core DSP TMS320C6678 for the squinted-looking synthetic aperture radars (SARs) real-time signal processing method. This paper first briefly introduces the squinted-looking SAR algorithm and analyzes the signal processing by use of spectral analysis (SPECAN). Then, according to the requirement of squinted-looking SAR real-time imaging system, the high performance TI multi-core DSP TMS320C6678 is used for realizing the imaging algorithm through the virtual single-node technology for data transmission and interaction and the parallel approach to data processing. Finally, the flight experiment is carried out and the results show that the virtual processing method meets the requirements of the real-time imaging based on the multi-core DSP hardware platform effectively.
暂无评论