For the panoramic video streaming service, this letter proposes a visual perception-based view navigation trick mode (VP-VNTM) that reduces bandwidth requirements by adjusting the quality of transmitting views in accordance with the view navigation velocity without decreasing the user's visual sensitivity. Experiments show that the proposed VP-VNTM reduces bandwidth requirements by more than 44%.

The suffix tree is one of most widely adopted indexes in the application of genome sequence alignment. Although it supports very fast alignment, it has a couple of shortcomings, such as a very long construction time and a very large volume size. Loh et al. [7] proposed a suffix tree construction algorithm with dramatically improved performance; however, the size still remains as a challenging problem. We propose an algorithm by extending the one by Loh et al. to reduce the suffix tree size. As a result of our experiments, our algorithm constructed a suffix tree of approximately 60% of the size within almost the same time period.

The contribution of this paper is two-fold. Firstly, we conduct a large-scale real-world evaluation of the effectiveness of integrating an automatic transliteration system with a machine translation system. A human evaluation is usually preferable to an automatic evaluation, and in the case of this evaluation especially so, since the common machine translation evaluation methods are affected by the length of the translations they are evaluating, often being biassed towards translations in terms of their length rather than the information they convey. We evaluate our transliteration system on data collected in field experiments conducted all over Japan. Our results conclusively show that using a transliteration system can improve machine translation quality when translating unknown words. Our second contribution is to propose a novel Bayesian model for unsupervised bilingual character sequence segmentation of corpora for transliteration. The system is based on a Dirichlet process model trained using Bayesian inference through blocked Gibbs sampling implemented using an efficient forward filtering/backward sampling dynamic programming algorithm. The Bayesian approach is able to overcome the overfitting problem inherent in maximum likelihood training. We demonstrate the effectiveness of our Bayesian segmentation by using it to build a translation model for a phrase-based statistical machine translation (SMT) system trained to perform transliteration by monotonic transduction from character sequence to character sequence. The Bayesian segmentation was used to construct a phrase-table and we compared the quality of this phrase-table to one generated in the usual manner by the state-of-the-art GIZA++ word alignment process used in combination with phrase extraction heuristics from the MOSES statistical machine translation system, by using both to perform transliteration generation within an identical framework. In our experiments on English-Japanese data from the NEWS2010 transliteration generation shared task, we used our technique to bilingually co-segment the training corpus. We then derived a phrase-table from the segmentation from the sample at the final iteration of the training procedure, and the resulting phrase-table was used to directly substitute for the phrase-table extracted by using GIZA++/MOSES. The phrase-table resulting from our Bayesian segmentation model was approximately 30% smaller than that produced by the SMT system's training procedure, and gave an increase in transliteration quality measured in terms of both word accuracy and F-score.

This paper studies the design of Cascade Granular Neural Networks (CGNN) for human-centric systems. In contrast to typical rule-based systems encountered in fuzzy modeling, the proposed method consists of two-phase development for CGNN. First, we construct a Granular Neural Network (GNN) which could be treated as a preliminary design. Next, all modeling discrepancies are compensated by a second GNN with a collection of rules that become attached to the regions of the input space where the error is localized. These granular networks are constructed by building a collection of user-centric information granules through Context-based Fuzzy c-Means (CFCM) clustering. Finally, the experimental results on two examples reveal that the proposed approach shows good performance in comparison with the previous works.

Since the release of human genome sequences, one of the most important research issues is about indexing the genome sequences, and the suffix tree is most widely adopted for that purpose. The traditional suffix tree construction algorithms suffer from severe performance degradation due to the memory bottleneck problem. The recent disk-based algorithms also provide limited performance improvement due to random disk accesses. Moreover, they do not fully utilize the recent CPUs with multiple cores. In this paper, we propose a fast algorithm based on `divide-and-conquer' strategy for indexing the human genome sequences. Our algorithm nearly eliminates random disk accesses by accessing the disk in the unit of contiguous chunks. In addition, our algorithm fully utilizes the multi-core CPUs by dividing the genome sequences into multiple partitions and then assigning each partition to a different core for parallel processing. Experimental results show that our algorithm outperforms the previous fastest DIGEST algorithm by up to 10.5 times.

A novel method is proposed to estimate the 3D relative positions of an articulated body from point correspondences in an uncalibrated monocular image sequence. It is based on a camera perspective model. Unlike previous approaches, our proposed method does not require camera parameters or a manual specification of the 3D pose at the first frame, nor does it require the assumption that at least one predefined segment in every frame is parallel to the image plane. Our work assumes a simpler assumption, for example, the actor stands vertically parallel to the image plane and not all of his/her joints lie on a plane parallel to the image plane in the first frame. Input into our algorithm consists of a topological skeleton model and 2D position data on the joints of a human actor. By geometric constraint of body parts in the skeleton model, 3D relative coordinates of the model are obtained. This reconstruction from 2D to 3D is an ill-posed problem due to non-uniqueness of solutions. Therefore, we introduced a technique based on the concept of multiple hypothesis tracking (MHT) with a motion-smoothness function between consecutive frames to automatically find the optimal solution for this ill-posed problem. Since reconstruction configurations are obtained from our closed-form equation, our technique is very efficient. Very accurate results were attained for both synthesized and real-world image sequences. We also compared our technique with both scaled-orthographic and existing perspective approaches. Our proposed method outperformed other approaches, especially in scenes with strong perspective effects and difficult poses.

In this paper, we propose a spatially adaptive gradient-projection algorithm for the H.264 video coding standard to remove coding artifacts using local statistics. A hybrid method combining a new weighted constrained least squares (WCLS) approach and the projection onto convex sets (POCS) approach is introduced, where weighting components are determined on the basis of the human visual system (HVS) and projection set is defined by the difference between adjacent pixels and the quantization index (QI). A new visual function is defined to determine the weighting matrices controlling the degree of global smoothness, and a projection set is used to obtain a solution satisfying local smoothing constraints, so that the coding artifacts such as blocking and ringing artifacts can be simultaneously removed. The experimental results show the capability and efficiency of the proposed algorithm.

We propose a novel and efficient approach for tracking 2D articulated human body parts. In our approach, the human body is modeled by a graphical model where each part is represented by a node and the relationship between a pair of adjacent parts is indicated by an edge in the graph. Various approaches have been proposed to solve such problems, but efficiency is still a vital problem. We present a new Quick Shift Belief Propagation (QSBP) based approach which benefits from Quick Shift, a simple and efficient mode seeking method, in a part based belief propagation model. The unique aspect of this model is its ability to efficiently discover modes of the underlying marginal probability distribution while preserving the accuracy. This gives QSBP a significant advantage over approaches like Belief Propagation (BP) and Mean Shift Belief Propagation (MSBP). Moreover, we demonstrate the use of QSBP with an action based model; this provides additional advantages of handling self-occlusion and further reducing the search space. We present qualitative and quantitative analysis of the proposed approach with encouraging results.

This paper presents a robust framework of human-computer interaction from the hand gesture vision in the presence of realistic and challenging scenarios. To this end, several novel components are proposed. A hybrid approach is first proposed to automatically infer the beginning position of hand gestures of interest via jointly optimizing the regions given by an offline skin model trained from Gaussian mixture models and a specific hand gesture classifier trained from the Adaboost technique. To consistently track the hand in the context of using kernel based tracking, a semi-supervised feature selection strategy is further presented to choose the feature subspaces which appropriately represent the properties of offline hand skin cues and online foreground-background-classification cues. Taking the histogram of oriented gradients as the descriptor to represent hand gestures, a soft-decision approach is finally proposed for recognizing static hand gestures at the locations where severe ambiguity occurs and hidden Markov model based dynamic gestures are employed for interaction. Experiments on various real video sequences show the superior performance of the proposed components. In addition, the whole framework is applicable to real-time applications on general computing platforms.

An interactive support system for image quality enhancement to adjust display equipments according to the user's own subjectivity is developed. Interactive support system for image quality enhancement enable the parameters based on user's preference to be derived by only selecting user's preference images without adjusting image quality parameters directly. In the interactive support system for image quality enhancement, the more the number of parameters is, the more effective this system is. In this paper, lightness, color and sharpness are used as the image quality parameters and the images are enhanced by increasing the number of parameters. Shape of tone curve is controlled by two image quality adjustment parameters for lightness enhancement. Images are enhanced using two image quality adjustment parameters for color enhancement. The two parameters are controlled in L* a* b* color space. Degree and coarseness of image sharpness enhancement are adjusted by controlling a radius of mask of smoothing filter and weight of adding. To confirm the effectiveness of the proposed method, the image quality and derivation time of the proposed method are compared with a manual adjustment method.

Color percept is a subjective experience and, in general, it is impossible for other people to tell someone's color percept. The present study demonstrated that the simple image-classification analysis of brain activity obtained by a functional magnetic resonance imaging (fMRI) technique enables to tell which of four colors the subject is looking at. Our results also imply that color information is coded by the responses of hue-selective neurons in human brain, not by the combinations of red-green and blue-yellow hue components.

This paper investigates the relationship between averaged SAR (Specific Absorption Rate) over 10 g mass and temperature elevation in Japanese numerical anatomical models when devices are mounted on the body. Simplifying the radiation source as a half-wavelength dipole, the generated electrical field and SAR are calculated using the FDTD (Finite-Difference Time-Domain) method. Then the bio-heat equation is solved to obtain the temperature elevation due to the SAR derived using the FDTD method as heat source. Frequencies used in the study are 900 MHz and 1950 MHz, which are used for mobile phones. In addition, 3500 MHz is considered because this frequency is reserved for IMT-Advanced (International Mobile Telecommunication-Advanced System). Computational results obtained herein show that the 10 g-average SAR and the temperature elevation are not proportional to frequency. In addition, it is clear that those at 3500 MHz are lower than that at 1950 MHz even though the frequency is higher. It is the point to be stressed here is that good correlation between the 10 g-average SAR and the temperature elevation is observed even for the body-worn device.

We address the problem of perceived age estimation from face images, and propose a new semi-supervised approach involving two novel aspects. The first novelty is an efficient active learning strategy for reducing the cost of labeling face samples. Given a large number of unlabeled face samples, we reveal the cluster structure of the data and propose to label cluster-representative samples for covering as many clusters as possible. This simple sampling strategy allows us to boost the performance of a manifold-based semi-supervised learning method only with a relatively small number of labeled samples. The second contribution is to take the heterogeneous characteristics of human age perception into account. It is rare to misjudge the age of a 5-year-old child as 15 years old, but the age of a 35-year-old person is often misjudged as 45 years old. Thus, magnitude of the error is different depending on subjects' age. We carried out a large-scale questionnaire survey for quantifying human age perception characteristics, and propose to utilize the quantified characteristics in the framework of weighted regression. Consequently, our proposed method is expressed in the form of weighted least-squares with a manifold regularizer, which is scalable to massive datasets. Through real-world age estimation experiments, we demonstrate the usefulness of the proposed method.

In this paper, a human detection method is developed. An appearance based detector and a motion based detector are proposed respectively. A multi scale block histogram of template feature (MB-HOT) is used to detect human by the appearance. It integrates the gray value information and the gradient value information, and represents the relationship of three blocks. Experiment on INRIA dataset shows that this feature is more discriminative than other features, such as histogram of orientation gradient (HOG). A motion based feature is also proposed to capture the relative motion of human body. This feature is calculated in optical flow domain and experimental result in our dataset shows that this feature outperforms other motion based features. The detection responses obtained by two features are combined to reduce the false detection. Graphic process unit (GPU) based implementation is proposed to accelerate the calculation of two features, and make it suitable for real time applications.

The purpose of this study is to establish a whole-body averaged specific absorption rate (WB-SAR) estimation method using the power absorbed by humans; a cylindrical-external field scanning technique is used to measure the radiated RF (radio-frequency) power. This technique is adopted with the goal of simplifying the estimation of the exposure dosimetry of humans who have different postures and/or sizes. In this paper, to validate the proposed measurement method, we subject numerical human phantom models and cylindrical scanning conditions to FDTD analysis. We design a radiation system that uses a dielectric lens to achieve plane-wave irradiation of tested human phantoms in order to develop an experimental WB-SAR measurement system for UHF far-field exposure condition. In addition, we use a constructed SAR measurement system to confirm absorbed power estimations of simple geometrical phantoms and so estimate measurement error of the measurement system. Finally, we discuss the measurement results of WB-SARs for male adult and child human phantom models.

In this letter, we propose a novel approach to human activity recognition. We present a class of features that are robust to the tilt of the attached sensor module and a state transition model suitable for HMM-based activity recognition. In addition, postprocessing techniques are applied to stabilize the recognition results. The proposed approach shows significant improvements in recognition experiments over a variety of human activity DB.

Detecting emergency situation is very important to a surveillance system for people like elderly live alone. A vision-based emergency response system with a paramedic mobile robot is presented in this paper. The proposed system is consisted of a vision-based emergency detection system and a mobile robot as a paramedic. A vision-based emergency detection system detects emergency by tracking people and detecting their actions from image sequences acquired by single surveillance camera. In order to recognize human actions, interest regions are segmented from the background using blob extraction method and tracked continuously using generic model. Then a MHI (Motion History Image) for a tracked person is constructed by silhouette information of region blobs and model actions. Emergency situation is finally detected by applying these information to neural network. When an emergency is detected, a mobile robot can help to diagnose the status of the person in the situation. To send the mobile robot to the proper position, we implement mobile robot navigation algorithm based on the distance between the person and a mobile robot. We validate our system by showing emergency detection rate and emergency response demonstration using the mobile robot.

In this paper, we propose a novel feature named histogram of template (HOT) for human detection in still images. For every pixel of an image, various templates are defined, each of which contains the pixel itself and two of its neighboring pixels. If the texture and gradient values of the three pixels satisfy a pre-defined formula, the central pixel is regarded to meet the corresponding template for this formula. Histograms of pixels meeting various templates are calculated for a set of formulas, and combined to be the feature for detection. Compared to the other features, the proposed feature takes texture as well as the gradient information into consideration. Besides, it reflects the relationship between 3 pixels, instead of focusing on only one. Experiments for human detection are performed on INRIA dataset, which shows the proposed HOT feature is more discriminative than histogram of orientated gradient (HOG) feature, under the same training method.

Electrostatic discharge (ESD) events due to metal objects electrified with low voltages give a fatal electromagnetic interference to high-tech information equipment. In order to elucidate the mechanism, with a 6-GHz digital oscilloscope, we previously measured the discharge current due to collision of a hand-held metal piece from a charged human body, and gave a current calculation model. In this study, based on the calculation model, a method was presented for deriving a gap potential gradient from the measured discharge current. Measurements of the discharge currents were made for charge voltages from 200 V to 1000 V. The corresponding potential gradients were estimated, which were validated in comparison with an empirical formula based on the Paschen's law together with other researcher's experimental results.

Continuous pen pressure can be used to operate multi-state widgets such as menus in pen based user interfaces. The number of levels into which the pen pressure space is divided determines the number of states in the multi-state widgets. To increase the optimal number of divisions of the pen pressure space and achieve greater pen pressure usability, we propose a new discretization method which divides the pen pressure space according to a personal pen pressure use profile. We present here four variations of the method: discretization according to personal/aggregation pen pressure use profile with/without visual feedback of uniform level widths and the traditional even discretization method. Two experiments were conducted respectively to investigate pen pressure use profile and to comparatively evaluate the performance of these methods. Results indicate that the subjects performed fastest and with the fewest errors when the pen pressure space was divided according to personal profile with visual feedback of uniform level widths (PU) and performed worst when the pen pressure space was divided evenly. With PU method, the optimal number of divisions of the pen pressure space was 8. Visual feedback of uniform level widths enhanced performance of uneven discretization. The findings of this study have implications for human-oriented pen pressure use in pen pressure based user interface designs.