Norimichi Ukita

Nara Institute of Science and Technology, Ikuma, Nara, Japan

Are you Norimichi Ukita?

Claim your profile

Publications (56)15.22 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an approach for human passenger stress reduction while riding a personal mobility autonomous vehicle. The particular vehicle of interest is a robotic autonomous wheelchair which can provide mobility assistance in pedestrian paths. State of the art algorithms for autonomous vehicles mainly focus on collision free path planning and safe control for obstacle avoidance. This work studies comfort factors of the passenger while riding the vehicle. We propose a method for velocity control of the robotic wheelchair based on the concept of " visible-comfort index " to reduce stress from the collision prediction in blind regions. Visible-comfort index is defined as the visible collision area against dynamic obstacles which is free from collision. By using this index, the velocity of the robotic wheelchair is computed. Experimental results based on physiological measurements (heart rate and galvanic skin response) show that the control of the robotic wheelchair using the visible-comfort index decreases stressful situations for passengers.
    Full-text · Conference Paper · Nov 2015
  • Norimichi Ukita · Daniel Kaulen · Carsten Röcker
    [Show abstract] [Hide abstract]
    ABSTRACT: Our goal is to develop a system for coaching human motions (e.g., for rehabilitation and daily health maintenance). This paper focuses on how to coach a user so that his/her motion gets closer to the good template of a target motion. It is important to efficiently advise the user to emulate the crucial features that define the good template. The proposed system (1) automatically mines the crucial features of any kind of motion from a set of motion features and (2) gives the user feedback about how to modify the motion through an intuitive interface. The crucial features are mined by feature sparsification through binary classification between the samples of good and other motions. An interface for motion coaching is designed to give feedback via different channels (e.g., visually, aurally), depending on the type of error. To use the total system, all the user must do is just move and then get feedback on the motion. Following experimental results, open problems for future work are discussed.
    No preview · Chapter · Jan 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a novel framework to estimate the amount of physical activity at a place where people stayed, by utilizing facility information and user's acceleration data. The total amount of physical activities, energy expenditure of a physical activity is a good scale. Our framework provides a physical activity scale based on typical energy expenditure of the activity given by existing researches already. To estimates the energy expenditure, we use typical value of metabolic equivalents to task (MET) which is used as practical scale. Unlike the other studies for monitoring physical activity, we estimate the type of user's activity using facility information which are obtained from road map and land-use/land-cover map. To confirm the feasibility of our approach, we have conducted a long-term experiment on monitoring the activity of elderly people living in less-populated area. As a result, our framework provides good summarization of daily activities of participants.
    No preview · Conference Paper · Oct 2014
  • Edilson De Aguiar · Norimichi Ukita
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new approach to represent and manipulate a mesh-based character animation preserving its time-varying details. Our method first decomposes the input mesh animation into coarse and fine deformation components. A model for the coarse deformations is constructed by an underlying kinematic skeleton structure and blending skinning weights. Thereafter, a non-linear probabilistic model is used to encode the fine time-varying details of the input animation. The user can manipulate the corresponding skeleton-based component of the input, which can be done by any standard animation package, and the final result is generated including its important time-varying details. By converting an input sample animation into our new hybrid representation, we are able to maintain the flexibility of mesh-based methods during animation creation while allowing for practical manipulations using the standard skeleton-based paradigm. We demonstrate the performance of our method by converting and manipulating several mesh animations generated by different performance capture approaches and apply it to represent and manipulate cloth simulation data.
    No preview · Article · Feb 2014 · Computers & Graphics
  • Source
    Norimichi Ukita · Daniel Kaulen · Carsten Röcker
    [Show abstract] [Hide abstract]
    ABSTRACT: The development of a widely applicable automatic motion coaching system requires one to address a lot of issues including motion capturing, motion analysis and comparison, error detection as well as error feed-back. In order to cope with this complexity, most existing approaches focus on a specific motion sequence or exercise. As a first step towards the development of a more generic system, this paper systematically ana-lyzes different error and feedback types. A prototype of a feedback system that addresses multiple modali-ties is presented. The system allows to evaluate the applicability of the proposed feedback techniques for ar-bitrary types of motions in a next step.
    Full-text · Conference Paper · Jan 2014
  • Norimichi Ukita · Atsushi Nakazawa
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper discusses the usefulness of human body-parts tracking for acquiring subtle cues in social interactions. While many kinds of body-parts tracking algorithms have been proposed, we focus on particle filtering-based tracking using prior models, which have several advantages for researches on social interactions. As a first step for extracting subtle cues from videos of social interaction behaviors, the advantages, disadvantages, and prospective properties of the body-parts tracking using prior models are summarized with actual results.
    No preview · Conference Paper · Dec 2013
  • Norimichi Ukita
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes human motion models of multiple actions for 3D pose tracking. A training pose sequence of each action, such as walking and jogging, is separately recorded by a motion capture system and modeled independently. This independent modeling of action-specific motions allows us 1) to optimize each model in accordance with only its respective motion and 2) to improve the scalability of the models. Unlike existing approaches with similar motion models (e.g. switching dynamical models), our pose tracking method uses the multiple models simultaneously for coping with ambiguous motions. For robust tracking with the multiple models, particle filtering is employed so that particles are distributed simultaneously in the models. Efficient use of the particles can be achieved by locating many particles in the model corresponding to an action that is currently observed. For transferring the particles among the models in quick response to changes in the action, transition paths are synthesized between the different models in order to virtually prepare inter-action motions. Experimental results demonstrate that the proposed models improve accuracy in pose tracking.
    No preview · Article · Jun 2013 · Image and Vision Computing
  • Norimichi UKITA · Kazuki MATSUDA · N. Hagita
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a method for reconstructing accurate 3D surface points. To this end, robust and dense reconstruction with Shape-from-Silhouettes (SfS) and accurate multiview stereo are integrated. Unlike gradual shape shrinking and/or bruteforce large space search by existing space carving approaches, our method obtains 3D points by SfS and stereo independently, and then selects correct ones from them. The point selection is achieved in accordance with spatial consistency and smoothness of 3D point coordinates and normals. The globally optimized points are selected by graph-cuts. Experimental results demonstrate that our method outperforms existing approaches.
    No preview · Conference Paper · Dec 2012
  • Norimichi Ukita · Shigenobu Fujine · Norihiro Hagita
    [Show abstract] [Hide abstract]
    ABSTRACT: We have developed a system with multiple pan-tilt cameras for capturing high-resolution videos of a moving person. This system controls the cameras so that each camera captures the best view of the person (i.e. one of body parts such as the head, torso, and limbs) based on criteria for camera-work optimization. For achieving this optimization in real time, time-consuming pre-processes, which give useful clues for the optimization, are performed in a training stage. Specifically, a target performance (e.g. a dance) is captured to acquire the configuration of the body parts at each frame. In a real capture stage, the system compares an online-reconstructed shape with those in the training data for fast retrieval of the configuration of the body parts. The retrieved configuration is used by an efficient scheme for optimizing a camera work. Experimental results show the camera work optimized in accordance with given criteria. A high-resolution 3D videos produced by the proposed system are also shown as a typical use of high-resolution videos.
    No preview · Conference Paper · Oct 2012
  • Norimichi Ukita · Takeo Kanade
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a multiview method for reconstructing a folded cloth surface on which regularly-textured color patches are printed. These patches provide not only easy pixel-correspondence between multiviews but also the following two new functions. (1) Error recovery: errors in 3D surface reconstruction (e.g. errors in occlusion boundaries and shaded regions) can be recovered based on the spatio-temporal consistency of the patches. (2) Single-view hole filling: patches that are visible only from a single view can be extrapolated from the reconstructed ones based on the regularity of the patches. Using these functions for improving 3D reconstruction also produces the patch configuration on the reconstructed surface, showing how the cloth is deformed from its reference shape. Experimental results demonstrate the above improvements and the accurate patch configurations produced by our method.
    No preview · Article · Aug 2012 · Computer Vision and Image Understanding
  • Edilson de Aguiar · Norimichi Ukita
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new approach to represent and manipulate a mesh-based character animation preserving its time-varying details. Our method first decomposes the input mesh animation into coarse and fine deformation components. A model for the coarse deformations is constructed by an underlying kinematic skeleton structure and blending skinning weights. Thereafter, a non-linear probabilistic model is used to encode the fine time-varying details of the input animation. The user can manipulate the corresponding skeleton-based component of the input, which can be done by any standard animation package, and the final result is generated including its important time-varying details. By converting an input sample animation into our new hybrid representation, we are able to maintain the flexibility of mesh-based methods during animation creation while allowing for practical manipulations using the standard skeleton-based paradigm. We demonstrate the performance of our method by converting and editing several mesh animations generated by different performance capture approaches.
    No preview · Conference Paper · Aug 2012
  • Source
    Kazuki Matsuda · Norimichi Ukita
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a method for reconstructing a smooth and accurate 3D surface. Recent machine vision techniques can reconstruct accurate 3D points and normals of an object. The reconstructed point cloud is used for generating its 3D surface by surface reconstruction. The more accurate the point cloud, the more correct the surface becomes. For improving the surface, how to integrate the advantages of existing techniques for point reconstruction is proposed. Specifically, robust and dense reconstruction with Shape-from-Silhouettes (SfS) and accurate stereo reconstruction are integrated. Unlike gradual shape shrinking by space carving, our method obtains 3D points by SfS and stereo independently and accepts the correct points reconstructed. Experimental results show the improvement by our method.
    Preview · Article · Jul 2012 · IEICE Transactions on Information and Systems
  • N. Ukita
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes contour-based features for articulated pose estimation. Most of recent methods are designed using tree-structured models with appearance evaluation only within the region of each part. While these models allow us to speed up global optimization in localizing the whole parts, useful appearance cues between neighboring parts are missing. Our work focuses on how to evaluate parts connectivity using contour cues. Unlike previous works, we locally evaluate parts connectivity only along the orientation between neighboring parts within where they overlap. This adaptive localization of the features is required for suppressing bad effects due to nuisance edges such as those of background clutter and clothing textures, as well as for reducing computational cost. Discriminative training of the contour features improves estimation accuracy more. Experimental results verify the effectiveness of our contour-based features.
    No preview · Conference Paper · Jun 2012
  • Norimichi Ukita · Takeo Kanade
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a unified model for human motion prior with multiple actions. Our model is generated from sample pose sequences of the multiple actions, each of which is recorded from real human motion. The sample sequences are connected to each other by synthesizing a variety of possible transitions among the different actions. For kinematically-realistic transitions, our model integrates nonlinear probabilistic latent modeling of the samples and interpolation-based synthesis of the transition paths. While naive interpolation makes unexpected poses, our model rejects them (1) by searching for smooth and short transition paths by employing the good properties of the observation and latent spaces and (2) by avoiding using samples that unexpectedly synthesize the nonsmooth interpolation. The effectiveness of the model is demonstrated with real data and its application to human pose tracking.
    No preview · Article · Apr 2012 · Computer Vision and Image Understanding
  • Source
    Norimichi Ukita · Kunihito Terashita · Masatsugu Kidode
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a method for calibrating the topology of distributed pan-tilt cameras (i.e. the structure of routes among and within FOVs) and its probabilistic model. To observe as many objects as possible for as long as possible, pan-tilt control is an important issue in automatic calibration as well as in tracking. In a calibration period, each camera should be controlled towards an object that goes through an unreliable route whose topology is not calibrated yet. This camera control allows us to efficiently establish the topology model. After the topology model is established, the camera should be directed towards the route with the biggest possibility of object observation. We propose a camera control framework based on the mixture of the reliability of the estimated routes and the probability of object observation. This framework is applicable both to camera calibration and object tracking by adjusting weight variables. Experiments demonstrate the efficiency of our camera control scheme for establishing the camera topology model and tracking objects as long as possible.
    Preview · Article · Feb 2012 · IEICE Transactions on Information and Systems
  • Source
    Michiro Hirai · Norimichi Ukita · Masatsugu Kidode
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a real-time method for estimating the pose of a human body using its 3D volume obtained from synchronized videos. The method achieves pose estimation by pose regression from its 3D volume. While the 3D volume allows us to estimate the pose robustly against self occlusions, 3D volume analysis requires a large amount of computational cost. We propose fast and stable volume tracking with efficient volume representation in a low dimensional dynamical model. Experimental results demonstrated that pose estimation of a body with a significantly deformable clothing could run at around 60 fps.
    Preview · Conference Paper · Sep 2010
  • Norimichi Ukita · Akira Makino · Masatsugu Kidode
    [Show abstract] [Hide abstract]
    ABSTRACT: In this research, we focus on how to track a target region that lies next to similar regions (e.g. a forearm and an upper arm) in zoom-in images. Many previous tracking methods express the target region (i.e. a part in a human body) with a single model such as an ellipse, a rectangle, and a deformable closed region. With the single model, however, it is difficult to track the target region in zoom-in images without confusing it and its neighboring similar regions (e.g. ``a forearm and an upper arm'' and ``a small region in a torso and its neighboring regions'') because they might have the same texture patterns and do not have the detectable border between them. In our method, a group of feature points in a target region is extracted and tracked as the model of the target. Small differences between the neighboring regions can be verified by focusing only on the feature points. In addition, (1) the stability of tracking is improved using particle filtering and (2) tracking robust to occlusions is realized by removing unreliable points using random sampling. Experimental results demonstrate the effectiveness of our method even when occlusions occur.
    No preview · Article · Jul 2010 · IEICE Transactions on Information and Systems
  • Norimichi Ukita · Michiro Hirai · Masatsugu Kidode
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a method for estimating the pose of a human body using its approximate 3D volume (visual hull) obtained in real time from synchronized videos. Our method can cope with loose-fitting clothing, which hides the human body and produces non-rigid motions and critical reconstruction errors, as well as tight-fitting clothing. To follow the shape variations robustly against erratic motions and the ambiguity between a reconstructed body shape and its pose, the probabilistic dynamical model of human volumes is learned from training temporal volumes refined by error correction. The dynamical model of a body pose (joint angles) is also learned with its corresponding volume. By comparing the volume model with an input visual hull and regressing its pose from the pose model, pose estimation can be realized. In our method, this is improved by double volume comparison: 1) comparison in a low-dimensional latent space with probabilistic volume models and 2) comparison in an observation volume space using geometric constrains between a real volume and a visual hull. Comparative experiments demonstrate the effectiveness of our method faster than existing methods.
    No preview · Conference Paper · Nov 2009
  • Source
    N. Ukita · K. Terashita · M. Kidode
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a method for calibrating the topology of distributed pan tilt cameras (i.e., the structure of routes among FOVs) and its probabilistic model, which is useful for multi-object tracking in a wide area. To observe objects as long and many as possible, pan tilt control is an important issue in automatic calibration as well as in tracking. If only one object is observed by a camera and its neighboring cameras, the camera should point towards this object both in the calibration and tracking periods. However, if there are multiple objects, in the calibration period, the camera should be controlled towards an object that goes through an unreliable route in which a sufficient number of object detection results have not been observed. This control allows us to efficiently establish the reliable topology model. After the reliable topology model is established, on the other hand, the camera should be directed towards the route with the biggest possibility of object observation. We therefore propose a camera control framework based on the mixture of the reliability of the estimated routes and the probability of object observation. This framework is applicable both to camera calibration and object tracking by adjusting weight variables. Experiments demonstrate the efficiency of our camera control scheme for establishing the camera topology model and tracking objects as long as possible.
    Preview · Conference Paper · Oct 2009
  • Source
    Norimichi Ukita · Shohei Kawata · Masatsugu Kidode
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a free-viewpoint imaging method that can be used in a complicated scene such as an office room by using sparsely located cameras. In our method, a free-viewpoint image is generated from multiple image patches obtained by dividing observed images. The quality of the generated image strongly depends on how to divide the observed images. In an incorrect patch in the generated image, the images projected from different cameras differ significantly. With this property, the incorrect patches can be detected. These patches are then re-divided. We demonstrated the effectiveness of our method by generating free-viewpoint images from the real images observed by the cameras in an office room.
    Preview · Conference Paper · Jan 2009