Image-To-Class distance is first proposed in Naive- Bayes Nearest-Neighbor. NBNN is a feature-based image classifier, and can achieve impressive classification accuracy. However, the performance of NBNN relies heavily...
详细信息
ISBN:
(纸本)9781457701221
Image-To-Class distance is first proposed in Naive- Bayes Nearest-Neighbor. NBNN is a feature-based image classifier, and can achieve impressive classification accuracy. However, the performance of NBNN relies heavily on the large number of training samples. If using small number of training samples, the performance will degrade. The goal of this paper is to address this issue. The main contribution of this paper is that we propose a robust Image-to-Class distance by local learning. We define the patch-to-class distance as the distance between the input patch to its nearest neighbor in one class, which is reconstructed in the local manifold space;and then our image-toclass distance is the sum of patch-to-class distance. Furthermore, we take advantage of large-margin metric learning framework to obtain a proper Mahalanobis metric for each class. We evaluate the proposed method on four benchmark datasets: Caltech, Corel, Scene13, and Graz. The results show that our defined Image-To-Class Distance is more robust than NBNN and Optimal-NBNN, and by combining with the learned metric for each class, our method can achieve significant improvement over previous reported results on these datasets.
Recently, Independent Component Analysis based foreground detection has been proposed for indoor surveillance applications where the foreground tends to move slowly or remain still. Yet such a method often causes disc...
详细信息
ISBN:
(纸本)9781457701221
Recently, Independent Component Analysis based foreground detection has been proposed for indoor surveillance applications where the foreground tends to move slowly or remain still. Yet such a method often causes discrete segmented foreground objects. In this paper, we propose a novel foreground detection method named Contextual Constrained Independent Component Analysis (CCICA) to tackle this problem. In our method, the contextual constraints are explicitly added to the optimization objective function, which indicate the similarity relationship among neighboring pixels. In this way, the obtained de-mixing matrix can produce the complete foreground compared with the previous ICA model. In addition, our method performs robust to the indoor illumination changes and features a high processing speed. Two sets of image sequences involving room lights switching on/of and door opening/closing are tested. The experimental results clearly demonstrate an improvement over the basic ICA model and the image difference method.
Background modeling is a fundamental yet challenging issue in video surveillance. Traditional methods usually adopt single feature type to solve the problem, while the performance is usually unsatisfactory when handli...
详细信息
ISBN:
(纸本)9781457701221
Background modeling is a fundamental yet challenging issue in video surveillance. Traditional methods usually adopt single feature type to solve the problem, while the performance is usually unsatisfactory when handling complex scenes. In this paper, we propose a multi-scale framework, which combines both texture and intensity feature, to achieve a robust and accurate solution. Our contributions are three folds: first, we provide a multi-scale analysis for the issue;second, for texture feature we propose a novel texture operator named Scale-invariant Centersymmetric Local Ternary Pattern, and a corresponding Pattern Adaptive Kernel Density Estimation technique for its probability estimation;third, we design a Simplified Gaussian Mixture Models for intensity feature. Our method is tested on several complex real world videos with illumination variation, soft shadows and dynamic backgrounds. The experimental results clearly demonstrate that our method is superior to the previous methods.
Modern power grid is a typical multi-level complex giant system. The conventional analytical methods based on reductionism can't provide sufficient guidance for its operation and management. complex system theory,...
详细信息
This paper presents a novel parallel system for Rail Transit based on ACP approach (Artificial systems, Computational experiments, Parallel execution), which is proposed to address issues on safety, efficiency and rel...
详细信息
ISBN:
(纸本)9781467313971
This paper presents a novel parallel system for Rail Transit based on ACP approach (Artificial systems, Computational experiments, Parallel execution), which is proposed to address issues on safety, efficiency and reliability of their operation and optimization. Firstly, the construction of dynamic, overall and real Artificial Rail Transit systems and their demonstration are provided. Then, based on these systems, the platform, content and analysis of computational experiments and comprehensive evaluation system are researched. Finally, parallel control and management of the actual systems via parallel execution can be achieved. By Parallel Rail Transit systems, a set of recommendations and strategies of railway can be formed, which would improve the overall functionality of the trail transit system.
This paper proposes a novel budget model based on differential game to deal with budget allocation in competitive search advertisements under a finite time horizon, with consideration of budget constraints. We extend ...
详细信息
This paper proposes a novel budget model based on differential game to deal with budget allocation in competitive search advertisements under a finite time horizon, with consideration of budget constraints. We extend the advertising response function with the dynamical advertising effort u and quality score q to fit search advertising scenarios. We also discuss Nash equilibriums of our model, and study some desirable properties of two kinds of equilibriums in the case with budget constraints: "budget-stable" open-loop Nash equilibrium (BS-OLNE) and "budget-unstable" open-loop Nash equilibrium (BUS-OLNE). We have evaluated our budget model and identified properties with computational experiments. Experimental results show that budget strategies with dynamical advertising elasticity are superior to those with fixed one and our findings on OLNEs are helpful for advertisers to make budget decisions.
The far-field intensity is detected from far-field image to estimate the piston distance between two gratings. The image processing algorithm includes projections along the horizontal and vertical directions, search f...
详细信息
Polarity shifting has been a challenge to automatic sentiment classification. In this paper, we create a corpus which consists of polarity-shifted sentences in various kinds of product reviews. In the corpus, both the...
详细信息
As an efficient business process execution language which supports web services, BPEL4WS is widely supported by the academic and the industrial circles. According to the shortcomings such as number of computer terms, ...
详细信息
In this work, we took the analysis of neural interactions change in M1 of a monkey during the adaptation process for it to complete reach-to-grasp tasks with external perturbation across days. BN model was applied to ...
详细信息
暂无评论