In this paper, we present a new people counting approach in visual surveillance scenes. The features adopted in previous methods are all extracted at pixel-level or based on local area, which are severely affected by ...
详细信息
Video denoising is highly desirable in many real world applications. It can enhance the perceived quality of video signals, and can also help improve the performance of subsequent processes such as compression, segmen...
详细信息
ISBN:
(纸本)9783642215926;9783642215933
Video denoising is highly desirable in many real world applications. It can enhance the perceived quality of video signals, and can also help improve the performance of subsequent processes such as compression, segmentation, and object recognition. In this paper, we propose a method to enhance existing video denoising algorithms by denoising a video signal from multiple views (front-, top-, and side-views). A fusion scheme is then proposed to optimally combine the denoised videos from multiple views into one. We show that such a conceptually simple and easy-to-use strategy, which we call multiple view fusion (MVF), leads to a computationally efficient algorithm that can significantly improve video denoising results upon state-of-the-art algorithms. The effect is especially strong at high noise levels, where the gain over the best video denoising results reported in the literature, can be as high as 2-3 dB in PSNR. Significant visual quality enhancement is also observed and evidenced by improvement in terms of SSIM evaluations.
The paper presents a method of static graphical pattern identification inspired by human perception. Cooperation of visual cortex regions is thought to play a major role in the perception, that is why in our approach ...
详细信息
ISBN:
(纸本)9783642200427
The paper presents a method of static graphical pattern identification inspired by human perception. Cooperation of visual cortex regions is thought to play a major role in the perception, that is why in our approach this cooperation is modelled by joining algorithms responsible for shape and color processing. In order to obtain more stable set of characteristic points, the SIFT algorithm has been modified. To acquire information about shapes Harris operator and Hough transform are considered. The proposed method achieves about 28% less number of incorrect identification comparing to the results obtained by the classical SIFT algorithm.
The trajectory tracking control problem of internet-based bilateral nonlinear teleoperators with the presence of the symmetric and unsymmetrical time varying communication delay is addressed in this paper. The design ...
详细信息
ISBN:
(纸本)9783642215377;9783642215384
The trajectory tracking control problem of internet-based bilateral nonlinear teleoperators with the presence of the symmetric and unsymmetrical time varying communication delay is addressed in this paper. The design comprises proportional derivative (PD) terms with nonlinear adaptive control terms in order to cope with parametric uncertainty of the master and slave robot dynamics. The master-slave teleoperators are coupled by velocity and delayed position signals. The Lyapunov-Krasovskii-like functional is employed to ensure asymptotic stability of the master-slave closed-loop teleoperator systems under time varying communication delay. The stability condition allows the designer to estimate the control gains in order to achieve desired tracking property of the position and velocity signals for the master and slave systems.
In this paper, we design and implement model-free linear and model-based nonlinear adaptive output feedback method for robot manipulators. The model-free design uses only proportional and derivative (PD) error terms f...
详细信息
ISBN:
(纸本)9783642215377;9783642215384
In this paper, we design and implement model-free linear and model-based nonlinear adaptive output feedback method for robot manipulators. The model-free design uses only proportional and derivative (PD) error terms for trajectory tracking control of nonlinear robot manipulators. The design is very simple in the sense that it does not require a priori knowledge of the system dynamics. The model-based output feedback method combines PD controller terms with nonlinear adaptive term to cope with uncertain parametric uncertainty. The unknown velocity signals for two output feedback method are generated by the output of the model-free linear observer. Using asymptotic analysis, tracking error bounds for both output feedback design are shown to be bounded and their bounds can be made closed to the bound obtained with state feedback design by using small value of observer design parameters. Finally, we experimentally compare both method on a 3-DOF Phantom TM robot manipulator.
We derive mathematically a class of metrics for signals and images, considered as elements of R-N, that are based upon the structural similarity (SSIM) index. The important feature of our construction is that we consi...
详细信息
ISBN:
(纸本)9783642215926;9783642215933
We derive mathematically a class of metrics for signals and images, considered as elements of R-N, that are based upon the structural similarity (SSIM) index. The important feature of our construction is that we consider the two terms of the SSIM index, which are normally multiplied together to produce a scalar, as components of an ordered pair. Each of these terms is then used to produce a normalized metric, one of which operates on the means of the signals and the other of which operates on their zero-mean components. We then show that a suitable norm of an ordered pair of metrics defines a metric in R-N.
This paper discusses the advantages of score-level fusion between pattern and minutiae based fingerprint verification algorithms in various operational scenarios. The different scenarios considered are sensor interope...
详细信息
ISBN:
(纸本)9783642215957
This paper discusses the advantages of score-level fusion between pattern and minutiae based fingerprint verification algorithms in various operational scenarios. The different scenarios considered are sensor interoperability, environmental conditions and low quality enrollments. These are commonly encountered in real-life deployments of fingerprint-based biometric systems, specifically for large-scale distributed systems and physical access control. Moreover, the approach for jointly utilizing the conceptually different pattern and minutiae algorithms is based on various well-known score-level fusion techniques with single finger presentations. In contrast to previous studies on multi-matcher score-level fusion for fingerprint verification, where only moderate performance improvement were reported, the results presented here show significant performance gains. The two main contributing factors to these findings are that the two algorithms are conceptually different and the effects of the different operational scenarios. For the latter, improvement in accuracy due to fusion is even more significant in non-ideal and challenging operating conditions.
In this work, intelligent control technique using multiple parameter models is proposed for robust trajectory tracking control for a class of nonlinear systems. The idea is to reduce the controller gains so as to redu...
详细信息
ISBN:
(纸本)9783642215377;9783642215384
In this work, intelligent control technique using multiple parameter models is proposed for robust trajectory tracking control for a class of nonlinear systems. The idea is to reduce the controller gains so as to reduce the control efforts from the single model (SM) certainty equivalence (CE) principle based classical adaptive control approach. The method allows classical adaptive control to be switched into a candidate among the finite set of candidate controllers that best approximates the plant at each instant of time. The Lyapunov function inequality is used to identify a candidate that closely approximates the plant at each instant of time. The design can be employed to achieve good transient tracking performance with smaller values of controller gains in the presence of large scale parametric uncertainties. The proposed design is implemented and evaluated on 3-DOF Phantom Premimum (TM) 1.5 haptic robot device to demonstrate the effectiveness of the theoretical development.
A graph matching approach is proposed to retrieve envelope images from a large image database. First, the graph representation of an envelop image is generated based on the image segmentation results, in which each no...
详细信息
ISBN:
(纸本)9780769545202
A graph matching approach is proposed to retrieve envelope images from a large image database. First, the graph representation of an envelop image is generated based on the image segmentation results, in which each node corresponds to one segmented region. The attributes of nodes and edges in the graph are described by characteristics of the envelope image. Second, a minimum weighted bipartite graph matching method is employed to compute the distance between two graphs. Finally, the whole retrieval system including two principal stages is presented, namely, rough matching and fine matching. The experiments on a database of envelope images captured from real-life mailpieces demonstrate that the proposed method achieves promising results.
In this paper, we propose an efficient sparse feature on-line learning approach for image classification. A large-margin formulation solved by linear programming is adopted to learn sparse features on the max-similari...
详细信息
ISBN:
(纸本)9783642215926;9783642215933
In this paper, we propose an efficient sparse feature on-line learning approach for image classification. A large-margin formulation solved by linear programming is adopted to learn sparse features on the max-similarity based image representation. The margins between the training images and the query images can be directly utilized for classification by the Naive-Bayes or the K Nearest Neighbor category classifier. Balancing between efficiency and classification accuracy is the most attractive characteristic of our approach. Efficiency lies in its on-line sparsity learning algorithm and direct usage of margins, while accuracy depends on the discriminative power of selected sparse features with their weights. We test our approach using much fewer features on Caltech-101 and Scene-15 datasets and our classification results are comparable to the state-of-the-art.
暂无评论