Wednesday January 16, 2019
Robotics and Inspection
Session Chair:
Juha Röning, University of Oulu (Finland)
8:50 – 10:10 AM
Regency B
8:50IRIACV-450
Laser quadrat and photogrammetry based autonomous coral reef mapping ocean robot, Sidhant Gupta, Thanh Bui, King Lui, and Edmund Lam, The University of Hong Kong (Hong Kong)
9:10IRIACV-451
Multimodal localization for autonomous agents, Robert Relyea, Darshan Ramesh Bhanushali, Abhishek Vashist, Amlan Ganguly, Andres Kwasinski, Michael Kuhl, and Ray Ptucha, Rochester Institute of Technology (United States)
9:30IRIACV-452
Automatic estimation of the position and orientation of the drill to be grasped and manipulated by the disaster response robot based on analyzing depth information, Keishi Nishikawa, Waseda University (Japan)
9:50IRIACV-453
Automated optical inspection for abnormal-shaped packages, Wei Lin, Chang-Tao Hsu, Chi Chang, and Jen-Hui Chuang, National Chiao Tung University (Taiwan)
10:00 AM – 3:30 PM Industry Exhibition
10:10 – 10:40 AM Coffee Break
Machine Vision and Learning
Session Chair:
Juha Röning, University of Oulu (Finland)
10:40 AM – 12:20 PM
Regency B
10:40IRIACV-454
Foreground-aware statistical models for background estimation, Edgar Bernal1, Qun Li2, and Wencheng Wu1; 1University of Rochester and 2Microsoft Corporation (United States)
11:00IRIACV-455
Change detection in Cadastral 3D models and point clouds and its use for improved texturing, Sander Klomp1, Bas Boom2, Thijs van Lankveld2, and Peter De With1; 1Eindhoven University of Technology and 2CycloMedia Technology B.V. (the Netherlands)
11:20IRIACV-456
Study on selection of construction waste using sensor fusion, Masaya Nyumura and Yue Bao, Tokyo City University (Japan)
11:40IRIACV-457
Exploring variants of fully convolutional networks with local and global contexts in semantic segmentation problem, Dong-won Shin, Jun-Yong Park, Chan-Young Sohn, and Yo-Sung Ho, Gwangju Institute of Science and Technology (GIST) (Republic of Korea)
12:00IRIACV-458
ECDNet: Efficient Siamese convolutional network for real-time small object change detection from ground vehicles, Sander Klomp1, Dennis van de Wouw1,2, and Peter De With1; 1Eindhoven University of Technology and 2ViNotion B.V. (the Netherlands)
12:30 – 2:00 PM Lunch
Wednesday Plenary
2:00 – 3:00 PM
Grand Peninsula Ballroom D
Light Fields and Light Stages for Photoreal Movies, Games, and Virtual Reality, Paul Debevec, Senior Scientist, Google (United States)
Paul Debevec will discuss the technology and production processes behind "Welcome to Light Fields", the first downloadable virtual reality experience based on light field capture techniques which allow the visual appearance of an explorable volume of space to be recorded and reprojected photorealistically in VR enabling full 6DOF head movement. The lightfields technique differs from conventional approaches such as 3D modelling and photogrammetry. Debevec will discuss the theory and application of the technique. Debevec will also discuss the Light Stage computational illumination and facial scanning systems which use geodesic spheres of inward-pointing LED lights as have been used to create digital actor effects in movies such as Avatar, Benjamin Button, and Gravity, and have recently been used to create photoreal digital actors based on real people in movies such as Furious 7, Blade Runner: 2049, and Ready Player One. Th lighting reproduction process of light stages allows omnidirectional lighting environments captured from the real world to be accurately reproduced in a studio, and has recently be extended with multispectral capabilities to enable LED lighting to accurately mimic the color rendition properties of daylight, incandescent, and mixed lighting environments. They have also recently used their full-body light stage in conjunction with natural language processing and automultiscopic video projection to record and project interactive conversations with survivors of the World War II Holocaust.
Paul Debevec is a Senior Scientist at Google VR, a member of GoogleVR's Daydream team, and Adjunct Research Professor of Computer Science in the Viterbi School of Engineering at the University of Southern California, working within the Vision and Graphics Laboratory at the USC Institute for Creative Technologies. Debevec's computer graphics research has been recognized with ACM SIGGRAPH's first Significant New Researcher Award in 2001 for "Creative and Innovative Work in the Field of Image-Based Modeling and Rendering", a Scientific and Engineering Academy Award in 2010 for "the design and engineering of the Light Stage capture devices and the image-based facial rendering system developed for character relighting in motion pictures" with Tim Hawkins, John Monos, and Mark Sagar, and the SMPTE Progress Medal in 2017 in recognition of his achievements and ongoing work in pioneering techniques for illuminating computer-generated objects based on measurement of real-world illumination and their effective commercial application in numerous Hollywood films. In 2014, he was profiled in The New Yorker magazine's "Pixel Perfect: The Scientist Behind the Digital Cloning of Actors" article by Margaret Talbot.
3:00 – 3:30 PM Coffee Break
Machine Vision Applications
Session Chair:
Kurt Niel, University of Applied Sciences Upper Austria (Austria)
3:30 – 5:30 PM
Regency B
3:30IRIACV-459
People recognition and position measurement in workplace by fisheye camera, Haike Guan and Makoto Shinnishi, Ricoh Company, Ltd. (Japan)
3:50IRIACV-460
Optical system of industrial camera that achieves both short minimum focusing distance and high resolution, Yoshifumi Sudoh, Ricoh Company, Ltd. (Japan)
4:10IRIACV-461
Investigating camera calibration methods for naturalistic driving studies, Jeffrey Paone1, Thomas Karnowski2, Deniz Aykac2, Regina Ferrell2, Jim Goddard2, and Austin Albright2; 1Colorado School of Mines and 2Oak Ridge National Laboratory (United States)
4:30IRIACV-462
Application of semantic segmentation for an autonomous rail tamping assistance system, Gerald Zauner1, Tobias Mueller2, Andreas Theiss2, Martin Buerger2, and Florian Auer2; 1University of Applied Sciences Upper Austria and 2Plasser & Theurer GmbH (Austria)
4:50IRIACV-463
Hazmat label recognition and localization for rescue robots in disaster scenarios, Raimund Edlinger, Gerald Zauner, Ralph Slabihoud, and Michael Zauner, University of Applied Sciences Upper Austria (Austria)
5:10IRIACV-464
Industrial computer vision in academic education - Is there a need besides so many professional business models supporting ready to go solutions?, Kurt Niel, University of Applied Sciences Upper Austria (Austria)
Intelligent Robotics and Industrial Applications using Computer Vision 2019 Interactive Posters Session
5:30 – 7:00 PM
The Grove
The following works will be presented at the EI 2019 Symposium Interactive Papers Session.
IRIACV-465
Improved 3D scene modeling for image registration in change detection, Sjors van Riel, Dennis van de Wouw, and Peter De With, Eindhoven University of Technology (the Netherlands)
IRIACV-466
Single Shot Appearance Model (SSAM) for multi-target tracking, Mohib Ullah and Faouzi Alaya Cheikh, Norwegian University of Science and Technology (Norway)