Public transportation is a crucial aspect of pas-senger transportation, with buses playing a vital role in the transportation service. Passenger counting is an essential tool for organizing and managing transportation services. However, manual counting is a tedious and time-consuming task, which is why computer vision algorithms are being utilized to make the process more efficient. In this study, different object detection algorithms combining with object tracking are investigated to compare passenger counting performance. The system employs the EfficientDet algorithm, which has demonstrated balanced performance in terms of speed and accuracy. Our results show that the EfficientDet can accurately count passengers in varying conditions with an accuracy of 94 %.

A hyperspectral (HS) image has high spectral resolution information but low spatial resolution information. To get an HS image of high spatial and spectral resolution (high-spatial HS image), fusion techniques are actively studied, which synthesize an HS image of low spatial and high spectral resolution and a multispectral (MS) image. The techniques can generate a high-spatial HS image by exploiting the high spectral and spatial resolution information of HS and MS images, respectively. However, the methods do not evaluate the edge similarity between generated HS and observed MS images, and do not denoise the MS image. As a result, when an observed MS image is noisy, these methods produce artifacts and spectral distortion. To tackle this problem, we propose a new HS and MS data fusion method using a hybrid spatio-spectral total variation (HSSTV), which is a regularization for HS image restoration. The method not only generates a high-spatial HS image but also denoises a given MS image, so that we obtain a high-spatial HS image even if the observed images are contaminated by noise. In the experiments, we demonstrate the advantages of our method over existing fusion methods and the effectiveness of HSSTV for MS image restoration.

This paper proposes a new mixed noise removal method using a hybrid spatio-spectral total variation (HSSTV) for hy-perspectral (HS) images. HSSTV effectively evaluates spatial and spectral piecewise smoothness and would be a powerful regularization for HS image restoration. Existing mixed noise removal methods evaluate a-priori knowledge of an HS image via multiple regularizations. However, they do not appropriately evaluate spatial piecewise smoothness, resulting in oversmoothing or artifacts. Moreover, parameter settings in existing methods are troublesome tasks because multiple balancing parameters are interdependent. In contrast, thanks to HSSTV, the proposed method can restore a clean HS image while keeping sharp edges and details. In addition, parameter settings in our method are much easier than existing ones because data fidelity is imposed as hard constraints. In the experiments, we demonstrate the advantages of our proposed method over existing regularizations.

Novel virtual turning for stationary VR environments, accomplishing to reorient the gazed view towards the center, is proposed. Prompt reorientation during rapid head motion and blinking performed unnoticeable scene switching that achieved the seamless user experience, especially for the wide-angle turning. Whereas, continuous narrow-angle turning by horizontally rotating the virtual world corresponding to the face orientation achieved enhanced sense of reality. The proposal comprises a hybrid of these two turning schemes. Experiments using simulator sickness and presence questionnaires revealed that our methods achieved comparable or lower sickness scores and higher presence scores than conventional smooth and snap turns.

Stationary subjects exposed to compelling scene movements in virtual reality environments often experience symptoms of visually induced motion sickness (cybersickness). This study specifically focuses on virtual turning and evaluates user experience in the task of searching and collecting objects appeared around the player in the first-person view. Typical conventional control schemes for turning includes the smooth and snap turns. The smooth turn is continuous turning performed by moving a scene in the horizontal direction. In this case, reflexive eye movement occurs even in the absence of physical motion, which often causes eye strain and nausea. The snap turn achieves a prompt direction change by omitting intervening turning, which often damages the sense of reality. To address these negative effects, we propose the novel turning method inspired by the particular human behavior, which achieves to reorient the gazed view towards the center. Prompt reorientation during rapid head motion and blinking performed unnoticeable scene switching that achieved the seamless user experience, especially for the wide-angle turning. Whereas, continuous narrow-angle turning by horizontally rotating the virtual world corresponding to the face orientation achieved enhanced the sense of reality. The proposal comprises a hybrid of these two turning schemes. Experiments using simulator sickness and presence questionnaires revealed that our methods achieved comparable or lower sickness scores and higher presence scores than either of conventional turning schemes.

Acquiring high-resolution hyperspectral (HS) images is a very challenging task. To this end, hyperspectral pansharpening techniques have been widely studied, which estimate an HS image of high spatial and spectral resolution (high HS image) from a pair of an HS image of high spectral resolution but low spatial resolution (low HS image) and a high spatial resolution panchromatic (PAN) image. However, since these methods do not fully utilize the piecewise-smoothness of spectral information on HS images in estimation, they tend to produce spectral distortion when the low HS image contains noise. To tackle this issue, we propose a new hyperspectral pansharpening method using a spatio-spectral regularization. Our method not only effectively exploits observed information but also properly promotes the spatio-spectral piecewise-smoothness of the resulting high HS image, leading to high quality and robust estimation. The proposed method is reduced to a nonsmooth convex optimization problem, which is efficiently solved by a primal-dual splitting method. Our experiments demonstrate the advantages of our method over existing hyperspectral pansharpening methods.

We propose a new regularization technique, named Hybrid Spatio-Spectral Total Variation (HSSTV), for hyperspectral image (HSI) restoration. Popular regularization techniques for HSIs are total variation functions (TV), and there have been proposed a variety of TVs for HSI restoration. However, they do not fully exploit both spatial and spectral smoothness, which are the underlying properties of HSIs, and/or they result in computationally expensive optimization. Our proposed HSSTV is designed to evaluate the two properties via two types of discrete differences of an HSI, leading to much more effective regularization than existing TVs for HSI restoration. HSSTV is defined with local discrete difference operators and the ℓ1/mixed ℓ1,2norm, so that optimization problems involving it can be efficiently solved by proximal splitting methods, such as the so-called alternating direction method of multipliers. Experimental results illustrate the advantages of HSSTV over state-of-the-art methods.

The frame rate of existing stereo cameras is not enough to track quick hand or finger actions. It also requires lots of computational cost to find correspondence between stereo images to compute distance. The recently commercialized 3D position sensors such as TOF cameras or Leap Motion needs strong illumination to ensure sufficient optical energy for the high frame rate sensing. To overcome these problems, this paper proposes to use a pair of optical-mouse-sensors as a stereo image sensor to measure 3D-velocity and use it to extrapolate 3D position measured by a low-frame-rate stereo camera. It is shown that quick hand actions are tracked under ordinary in-door lighting condition. As 2D velocities are computed inside the optical-mouse-sensors, computation and communication costs are drastically reduced.

This paper presents a simple but effective way of enhancing tactile stimulus by a mechanism with springs to preserve elastic energies charged in a prior energy-charging phase and discharge them to enhance the force to hit a finger in the stimulating phase. With this mechanism, a small and light stimulator attached to the fingertip is developed and demonstrated to generate the tactile feedback strong enough to make people feel as if their fingers collide with a virtual object. It is also shown that the durations of the two phases can be as short as a few milliseconds so that the latency in tactile feedback can be negligible. The performance of the mechanism and the effectiveness of its tactile feedback are evaluated for in-air keypress and swipe operations.

Simulator sickness is an issue in virtual reality environments. In a virtual world, sensory conflict between visual sensation and self-motion perception occurs readily. Contradiction between visual and vestibular sensation is a dominant cause of motion sickness. Vection is a visually evoked illusion of self-motion. Vection occurs when a stationary human experiences locomotor stimulation over a wider area of the field of view, and senses motion when in fact there is none. Strong vection has been associated with simulator sickness. In this poster, the authors present results of a pilot study based on a hypothesis that simulator sickness can be mitigated by passively responding to the body sway. Commercially available air cushions were applied for VR environments. Measurable mitigation of simulator sickness was achieved by physically responding to vection. Allowing body sway encourages moderating the sensory conflict between visual sensation and self-motion perception. Also, the shapes of air cushions on seat backs were found to be an important variable.

We propose an efficient image restoration framework based on stochastic optimization. Image restoration usually requires some iterative methods for solving optimization problems that characterize restored images, where the multiplication of the observation matrix Φ ϵ Rm × n and variables has to be computed at each iteration. If an efficient implementation of the multiplication (e.g., using FFT) is unavailable, its computational cost becomes O(MN), which is quite expensive since both N and M are usually large in image restoration. Our method needs to load and apply only a part of the observation matrix of size M/b × N (b: the number of parts), so that the computational cost is only O(MN/b). Moreover, the proposed method accepts various nonsmooth objectives effective for image restoration. Experiments on compressed sensing reconstruction and non-uniform deblurring show the advantage of the proposed method over state-of-the-art proximal optimization methods.

This paper proposes a new land cover mapping algorithm that combines the strengths of random forest (RF) with a Markov random field (MRF) model. The idea is to transform the observed data into the decision domain of weak classifiers inside an RF. Due to how RF are trained, these decisions can be considered to be independent from each others, and therefore the joint probability density function in the decision domain can be both easily and accurately estimated. For a decision vector from RF, and under an MRF model, the optimum land cover map is iteratively searched. The performances of the proposed algorithm were evaluated using a real remote-sensing image, and we found that the resulting land cover maps are more accurate than most traditional classifiers in all sizes of training samples.

When we use a tablet style handheld device such as a smart phone as a part of a virtual really system, its most outstanding future: the touch screen dominating the most area of the front face should be incorporated into the system effectively and beneficially. For example, the visual information displayed on the screen can be merged with the surrounding or background scenes and the intuitive touch operation can be performed in a suitable scenario. However, if the means of the interaction is limited to the touch operation, finger operation on the front screen must be performed even for unsuitable scenarios, and the fingers or hands occluding the visual information disturb our immersive experience. To deal with this situation, we propose a multi-modal interactive tablet that uses its cameras, accelerometer, track ball and pressure sensors implemented on its rear and side for operations ensuring visibility. The pressing and ball-rotating operation on the rear and the side and the tactile feedback generated by voice-coil-based actuators assist and guide the multi-modal interaction. The effectiveness of the multi-modality with the rear and the side operation and the tactile feedback is evaluated by an experiment.

To improve single-handed operation of mobile devices, rear touch panel operation to control commands and facial feature detection to control cursor position are proposed. Operational control is achieved through finger chord gestures on a rear touch panel, and nose movement is used to control cursor movement. Zooming is achieved by detecting the apparent distance between the left and right eyes in conjunction with a finger chord gesture. We have evaluated movement time, error rates, and the throughputs of these techniques in comparison with the conventional single-handed front touch panel thumb operations using Fitts's law. Experiments have been conducted to evaluate two operation modes, selection and zooming, in the form of reciprocal 1-D pointing tasks with 12 participants. For the target selection task, the proposed technique achieved 12% (0.26 s) shorter movement time and 4.7% smaller error rate than the conventional method on average. Especially, for long distance targets, the performance of the conventional method became remarkably inferior due to the limit of reach of the thumb, whereas the proposed technique achieved much less deterioration and obtained expected performance because the cursor could reach anywhere on the display. For the target size adjustment task, the proposed technique achieved 9% (0.22 s) shorter movement time than the conventional method and obtained a comparable error rate of less than 4%. Consequently, we could demonstrate the techniques that make single-handed select and zoom operations available anywhere on a large-sized tablet device with no blockage of the display.

This paper proposes a second-order discrete total generalized variation (TGV) for arbitrary graph signals, which we call the graph TGV (G-TGV). The original TGV was introduced as a natural higher-order extension of the well-known total variation (TV) and is an effective prior for piecewise smooth signals. Similarly, the proposed G-TGV is an extension of the TV for graph signals (G-TV) and inherits the capability of the TGV, such as avoiding staircasing effect. Thus the G-TGV is expected to be a fundamental building block for graph signal processing. We provide its applications to piecewise-smooth graph signal inpainting and 3D mesh smoothing with illustrative experimental results.

The front face of the tablet style smartphone or computer is dominated by a touch screen. As a finger operation on the touch screen disturbs its visibility, it is assumed a finger touches the screen instantly. Under such restriction, use of the rear surface of the tablet for tactile display is promising as the fingers constantly touch the back face and feel the tactile information. In our presentation, various tactile feedback mechanisms implemented on the back face are demonstrated and the latency of the feedback and its effect on the usability are evaluated for different communication means to control actuators such as wireless LAN, Bluetooth and audio signals. It is shown that the audio signal is promising to generate quick tactile feedback.

The front surface of the tablet style smartphone or computer is dominated by a touch screen. As a finger operation on the touch screen disturbs its visibility, it is assumed a finger touches the screen instantly. Under such restriction, use of the rear surface of the tablet for tactile display is promising as the fingers holding the tablet constantly touch it and feel the feedback steadily. In this paper, a slim design of tactile feedback mechanism that can be easily installed on the back of existing tablets is given and its mechanical performance regarding electricity consumption, latency and force is evaluated. Human capability in perceiving the tactile information on the display is also evaluated.

This paper addresses the problem of flood detection from the cloud-contaminated MODIS time-series data. Although MODIS data can provide almost daily coverage over the large area with the medium resolution. The use of MODIS data for flood mapping in the tropical regions is a challenging task due to the cloud contamination. Since the floods usually occur in the connected regions over a certain period of time, we employed the Markov random field model to characterize this property. For our experiments, the classification accuracy of flooded and non-flooded areas can be significantly increased by incorporating the MRF model.

In this demo session, we demonstrate two of our original tactile feedback devices and provide user experiences of their performance. The devices, with a combined use of a tablet computer, are used to constitute a kind of communication robot which has a rotating wheel or an actuated stage to give tactile feedback to the user's fingers while the user is performing a gesture operation on the touch panel. The devices are designed to give comfortable tactile feedback with very smooth movement actuated by eccentric rotation of a ball bearing. Although a low-cost servo motor for a hobby is used to rotate the eccentric shaft of the bearing, it is demonstrated to be effective in representing depth and hardness of the virtual surface by synchronizing the movement of the touch panel surface with the finger movement and the pressure detected by the touch panel.

We describe the prototype of an image retrieval system used for mobile guide applications. It allows users to send image queries of urban scenes using camera phones. The system uses a database of views of scenes to determine the poses of query views provided by the users. Information is then mapped onto the query views. Our approach is based on a fully affine invariant descriptor, coined PRIUS, which can identify corresponding building facades across widely separated views despite the highly repetitive nature of the man-made environments. The system is substantiated by experiments that show that our approach outperforms the state-of-the-art approaches such as SIFT (scale-invariant feature transform) and MSER (maximally stable external regions) in image retrieval. © 2012 Wiley Periodicals, Inc.

This paper introduces a mouse with a tactile display that generates tactile feedback for multi-modal user interface. The control system to generate tactile feedback imitates the biological nervous system that has multiple feedback loops for quick and flexible reaction against sensory inputs. The control system, inspired by the biological system, has double feedback loops, one for the local feedback performed within the mouse for quick and fixed reaction and the other for the global feedback performed through the communication with an external computer for slow and flexible reaction. The conflicting demands of quickness and flexibility can be satisfied by combining these two feedback loops. The control system is applied to the multi-modal user interface that uses tactile information in addition to the auditory information to assist visually handicapped people to operate a web browser that uses the tactile information to guide cursor operation.

In this paper, we present a neural-network learning scheme for face reconstruction. This scheme, which we called the smooth projected polygon representation neural network (SPPRNN), is able to successively refine the polygon's vertices parameter of an initial 3D shape based on depth-maps of several calibrated images taken from multiple views. The depth-maps, which are obtained by deploying the Tsai-Shah shape-from-shading (SFS) algorithm, can be considered as partial 3D shapes of the face to be reconstructed. The reconstruction is finalized by mapping the texture of face images to the initial 3D shape. There are three interesting issues investigated in this paper concerning the effectiveness of this scheme. First, how effective the SFS provides partial 3D shapes compared to if we simply used 2D images. Secondly, how essential a smooth projected polygonal model is in order to approximate the face structure and enhance the convergence rate of this scheme. Thirdly, how an appropriate initial 3D shape should be selected and used in order to improve model resolution and learning stability. By carefully addressing these three issues, it was shown from our experiment that a compact and realistic 3D model of a human (mannequin) face could be obtained.

For accurate region extraction, region-based active contour models (ACM) have been proposed. Compared with ordinary ACM, they require heavier loads of initial settings and further processing time. Considering these problems, for effective and efficient extraction, we propose a new region-based ACM. In the proposed method, first, users draw an initial curve in an object. Along this curve, definite length scanlines are set perpendicular to the initial curve and across the object contour. Depending on the image properties around scanlines, the scanlines are separated into several groups and each group is divided into two subregions (object and background regions). Scanline grouping and group dividing are iterated until the image properties are sufficiently uniform in each subregion. Through this clustering, a region along an object contour is segmented into subregions of uniform image properties, and consequently the image properties in a necessary and sufficient area are introduced into the extraction process effectively.

In this article, we present a technique to improve the generalization ability of multilayer neural networks. The proposed method introduces linear constraints on weight representation based on the invariance natures of training targets. We propose a learning method that introduces effective linear constraints into an error function as a penalty term. Furthermore, introduction of such constraints leads to reduction of the VC dimension of neural networks. We show bounds on the VC dimension of the neural networks with such constraints. Finally, we demonstrate the effectiveness of the proposed method by some experiments.

In this article, we propose an object tracking method using a neural network which represents the shape of an object based on the object's color information. We previously proposed a specific form of multiple-layered neural network which has a suitable structure to represent an object's shape. This network (shape representation network, SRN) originally was developed to deal with black and white images but it is extended for color images in this article. SRN is capable of representing objects of various kinds of shape and color with an arbitrary degree of blurring. Its learning capability enables automatic model construction for various shapes including their color information. To perform object tracking with color information, we introduce Mahalanobis distance in color space and improve the tracking performance. Some experiments are performed to evaluate the performance of the proposed method using real image sequences.

Proposes an object tracking method using the shape representation network (SRN) which represents an object's shape with the arbitrary degree of blurring. The SRN is a feedforward neural network composed of several edge description units each of which describes an edge shape with a blurring parameter, and one combining unit which represents various kinds of object's shape with a blurring parameter. In the first frame, the SRN is trained by minimizing squared errors between the frame and the template represented by the SRN. From the second frame, object is tracked by affine transformation of the template created in the initial frame. Originally, the blurring parameter has been held fixed to a constant value during the object tracking processes, however when an object has large movements between frames, this method can not keep tracking the object precisely through the whole image sequences. To solve this problem, we introduced a coarse-to-fine approach into the template matching process by changing the blurring degree of a template. The coarse-to-fine approach improves the tracking performance of the SRN, when a target moves rapidly and there is a large difference in object postures between adjacent frames.

A framework to represent target shapes and extract them from distorted images is proposed and its potential is demonstrated by some basic computer simulations. The proposed system consists of an array of cells. Each of the cells contains a neural network describing a template shape and a set of parameters for the affine transformation of the template shape. During the template shape learning phase, the connection weights of the neural network are trained so that an approximation is obtained for the template shape. In the shape matching phase, an additional layer which stores a set of affine parameters is used. With the rest of the connection weights fixed, the affine parameters are updated by a backpropagation-based algorithm so that the best shape matching is obtained. It is confirmed that the neural network is effective for shape representation and the cellular neural network locates target shapes with accurate poses in sample images.

This paper describes an adaptive filter construction technique and a spectrum estimation technique which uses a model for the variations of speech characteristics. The filter construction technique is applied to the adaptive analysis for the spectrum estimation technique. These techniques are the bases for the speaker independent vowel recognition which is tolerant of the variations of the speech features. Although the model is simple and efficient for the calculation, it is experimentally shown that the model yields well approximated spectra for the varied vowel parts in CV syllables and for the speaker dependent variations of isolated vowels.