ITE Technical Report
Online ISSN : 2424-1970
Print ISSN : 1342-6893
ISSN-L : 1342-6893
35.23
Showing 1-17 articles out of 17 articles from the selected issue
  • Type: Cover
    Pages Cover1-
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (15K)
  • Type: Index
    Pages Toc1-
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (64K)
  • Type: Bibliography
    Pages Misc1-
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (59K)
  • Akira KROMIYA, Takayuki YAMADA, Toshiyuki IWAI, Masayoshi OIKAWA
    Type: Article
    Session ID: IST2011-33/ME2011-65
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    A device was developed to generate high definition images of road surfaces for use in road surveys. The device mounted a line sensor camera on a vehicle, facing downward with its pickup line parallel to the bumper, and composed images from line images capture every predetermined distance of travel. Using the same image capturing approach as a scanner, the device was able to compose images both during straight travel and when changing lanes, but did not perform well on curves, i.e. right/left turns at intersections. Therefore, two line sensor cameras whose pickup lines crossed each other were mounted facing downward to capture images of the road surface. The new system was able to estimate image trajectory and compose images of the road surface along an undefined travel path.
    Download PDF (887K)
  • Naiki Onishi, Chie Fujiwara, Tomoko Tateyama, Kazutoshi Sakakibara, Ye ...
    Type: Article
    Session ID: IST2011-34/ME2011-66
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    In this paper, we propose the agent-based architecture to simulate fish behaviors for Visual Marine Museum. We introduce immune networks, which enable the agents to behave autonomously in dynamic environment, to the fish controller. Particle swarm optimization techniques are also used to acquire the parameters of immune networks. Through some computational simulations, we examine that appropriate behaviors can be acquired by our proposed systems.
    Download PDF (777K)
  • Nobu TSUCHIYAMA, Takaya YUIZONO, Kazunori MIYATA
    Type: Article
    Session ID: IST2011-35/ME2011-67
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    In the textbook for the junior high school students, a number of vertices and sides are required to understand the platonic solids. However, in the case of platonic solids which have over 12 surfaces, it is difficult to confirm the shape, vertexes and sides. And also in our preliminary survey, we confirmed it is not easy to recognize them using paper models. As a comparative evaluation experiment, we investigated the learning effectiveness of Augmented Reality (AR). The experimental result shows the interactive 3DCG using AR is effective for the learning of platonic solids.
    Download PDF (343K)
  • Yusaku Komamura, Junichi Akita
    Type: Article
    Session ID: IST2011-36/ME2011-68
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    The direction of the user's eye attention, or line of sight, has been widely discussed on its applications for new types of user intafaces, however, currently its applications are restricted in the special purposes, for expensive detection system and difficulty in operation. In addition, Saccade, the very rapid eye motion, has been expected to be an explorer for novel types of user interfaces, however, it is impossible to detect and track Saccade motion using conventional camera system. The authors have been proposed the vision architecture for detecting line of sight includiing saccade. In this paper, we describe the fast real-time eye-tracking system with implemented architecture of vision chip on FPGA with high speed camera, as well as its evaluation.
    Download PDF (806K)
  • Hiroyuki Michi, Hiroshi Ikeoka, Takayuki Hamamoto
    Type: Article
    Session ID: IST2011-37/ME2011-69
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    In this paper, we proposed a depth estimation method by tilted lens optics. Our proposed method uses two input images: one is all-in-focus image, another is ground-in-focus image. The method estimates depth value of each pixel by comparing the amount of blur between the ground-in-focus image and multi-focus images which are synthesized by applying the Gaussian filter on the all-in-focus image. To determine the depth values, the method uses the calibration data of the relation between depth value, pixel position (y coordinate of image) and amount of blur.
    Download PDF (807K)
  • Keiichiro KAGAWA, Shoji Kawahito, Jun TANIDA
    Type: Article
    Session ID: IST2011-38/ME2011-70
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    TOMBO (Thin Observation Module by Bound Optics) is a compact three-dimensional camera, which is composed of a single image sensor and a lens array. Aiming at acquisition of the three-dimensional surface profile of mucosa, we have constructed a prototype composed of a polarized active illumination implemented as a compact projector and a TOMBO with polarizers aligned in parallel or perpendicular to the polarization of the illumination for medical applications.
    Download PDF (916K)
  • Hiroshi Katayama, Danya Sugai, Takayuki Hamamoto
    Type: Article
    Session ID: IST2011-39/ME2011-71
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    In this paper, we propose the high accuracy motion estimation method based on the gradient method using high frame-rate images. In the method, we adopt the spatial gradients with low estimated errors by estimating the motion vectors of the current frame from the motion vectors of the previous frame. It is possible when we apply the high frame-rate images that have the high temporal correlation between motion vectors. Using the spatial gradients, we can improve the accuracy of the motion estimation. In addition, we introduce the refine vector to estimate high accuracy motion between frames apart. We evaluate the proposed method and confirm the effectiveness. Finally, we show the method of increasing spatial resolution using high frame-rate images as an application of the proposed method.
    Download PDF (987K)
  • Yasutomo Kawarazaki, Guifang Duan, Tomoko Tateyama, Neela Sawant, Jame ...
    Type: Article
    Session ID: IST2011-40/ME2011-72
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    An icon (from Greek εικων eikon "image") is a religious work of art, most commonly a painting, from Eastern Christianity and in certain Eastern Catholic churches. For studying the culture behind the icons, it is important to know the similarities and differences between them. This paper propose a method of clustering west Icons using facial shape features. The facial shape is represented by the landmarks of faces. A k-means method is employed for the clustering. The experimental results show that the proposed method can effectively cluster the Icons.
    Download PDF (1066K)
  • Kazuki Taniguchi, Xian-Hua Han, Yutaro Iwamoto, So Sasatani, Motonori ...
    Type: Article
    Session ID: IST2011-41/ME2011-73
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Multi-Frame Super-Resolution is a technique which attempts to reconstruct high-resolution image by fusing a number of low-resolution images. Therein, high-accuracy registration for the input low-resolution image set is required for reconstruction a clear high-resolution image. The conventional registration approaches for Multi-Frame Super-Resolution such as Iterative Back Projection and LK optical flow methods, can obtain accurate parameters for tiny translation or rotation movement between images. However, for large movement especially in rotation, there are still no efficient methods for reconstructing high-resolution image. Therefore, in this paper we proposed a new method using Rotation Invariant Phase Only Correlation, which can estimate large rotation parameter, and then follow the Iterative back Projection method for reconstructing high-resolution image. Experimental results show that the reconstructed high resolution images by our proposed approach are much better than those by interpolation techniques.
    Download PDF (853K)
  • Masaki MIZUNO, Yutaka NAKANO, Toshiyuki YOSHIDA
    Type: Article
    Session ID: IST2011-42/ME2011-74
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Epigenetics stands for a research area in biology which analyzes the phenomenon that cells having an identical DNA show mutually different biological characteristics after a cell division. An analysis for the mechanism requires an identification of the parent-child relationship and an extraction of fluorescent characteristics from each cell over several generations. This paper attempts to realize such an analysis process and improve its accuracy. Experimental results show that the proposed technique is promising by combining it with manual modifications for errors.
    Download PDF (861K)
  • Ken Tsutsuguchi, Mark Duppenthaler, Akira Kojima
    Type: Article
    Session ID: IST2011-43/ME2011-75
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    In this paper, we intruduce our video vectorization method. We first vectorize the initial frame of video using Bezier patches, and then track vertices of patches through video frames. After tracking, we approximate space-time and color volume of each patch as a 4 dimensional Bezier volume. We show an example of applying our method to a video with not occluded subjects.
    Download PDF (864K)
  • Type: Appendix
    Pages App1-
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (100K)
  • Type: Appendix
    Pages App2-
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (100K)
  • Type: Appendix
    Pages App3-
    Published: June 13, 2011
    Released: September 21, 2017
    CONFERENCE PROCEEDINGS FREE ACCESS
    Download PDF (100K)
feedback
Top