conferences

Tweet Follow @compvision

Online presentations from the Seventh Annual IEEE Embedded Computer Vision Workshop (ECVW 2011) are now available on Computer Vision Central. The event was held on June 20, 2011 in Colorado Springs, in conjunction with CVPR. The presentations can be accessed from the links below.

Next year's workshop on embedded vision, ECVW 2012, will be announced later this year.

Keynote:

What’s Next in Embedded Vision: Today and Future Technologies,
Mike Piacentino (SRI International Sarnoff, USA)

Embedded Stereo Vision

• Near real-time Fast Bilateral Stereo on the GPU, Stefano Mattoccia, Marco Viti, Florian Ries (University of Bologna, Italy)
• Stereo and IMU Assisted Visual Odometry on an OMAP3530 for Small Robots, Steven Goldberg, Larry Matthies (Indelible Systems, USA)
• An optimized Silicon Retina Stereo Matching Algorithm using Time-Space Correlation, Christoph Sulzbachner, Christian Zinner, Juergen Kogler (AIT Austrian Institute of Technology)
• Event-Driven Stereo Vision for Fall Detection, Ahmed Nabil Belbachir, Stephan Schraml, Aneta Nowakowska (AIT Austrian Institute of Technology)

Mobile Computer Vision

• Low-Power and Efficient Ambient Assistive Care System for Elders, Kofi Appiah, Andrew Hunter, Chrisopher Waltham (University of Lincoln, UK)
• Energy-efficient Foreground Object Detection on Embedded Smart Cameras by Hardware-level Operations, Mauricio Casares, Paolo Santinelli, Senem Velipasalar, Andrea Patri, Rita Cucchiara (University of Nebraska, USA)
• Rapid Reconstruction of Small Objects on Mobile Phones, Andreas Hartl, Lukas Gruber, Clemens Arth, Stefan Hauswlesner, Dieter Schmalstieg Graz Technical University, Austria)
• Fast Block Based Local Motion Estimation for Video Stabilization, Giovanni Puglisi, Sebastiano Battiato (Università di Catania, Italy)
• Ego-Motion Compensated Face Detection on a Mobile Device, Bjorn Scheuermann, Arne Ehlers, Hamon Riazy, Florian Baumann, Bodo Rosenhahn (Leibniz University, Germany)

NVIDIA Tutorial Session
Tutorial: Introduction to Mobile Computer Vision Development with NVIDIA Tegra, Joe Stam, (NVIDIA, USA)

Poster Session: Applications

• Real-Time License Plate Localisation on FPGA, Xiaojun Zhai, Faycal Bensaali, Soodamani Ramalingam (University of Hertfordshire, UK)
• A Real-Time Embedded Solution for Skew Correction in Banknote Analysis, Adnan Rashid, Andrea Prati, Rita Cucchiara (University of Modena, Italy)
• Energy-Optimized Mapping of Application to Smartphone Platform – A Case Study of Mobile Face Recognition, Yi-Chu Wang, Kwang-Ting Cheng (University of California, USA)
• Robust Airlight Estimation for Haze Removal from a Single Image, Matteo Pedone, Janne Heikkilä (University of Oulu, Finland)
• Embedded neuromorphic vision for humanoid robots, Chiara Bartolozzi, Francesco Rea, Michael Hofstaetter, Daniel B. Fasnacht, Charles Clercq, Giorgio Metta, Giacomo Indiveri (Italian Institute of Technology)
• Photorealistic 3D Face Modeling on a Smartphone, Won Beom Lee, Man Hee Lee, In Kyu Park (Inha University, Republic of Korea)
• Embedded Vision Alliance,Jeff Bier, Jeremy Giddings, Shehrzad Qureshi (BDTI, USA)

Poster Session: Technologies

• An Optimized Vision Library Approach for Embedded Systems, Goksel Dedeoglu, Branislav Kisacanin, Darnell Moore, Vinay Sharma, Andrew Miller (Texas Instruments Inc.)
• A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning, Gøril M. Breivik, Jens T. Thielemann, Asbjørn Berge, Øystein Skotheim, Trine Kirkhus (SINTEF, Norway)
• Fast Boosting Trees for Classification, Pose Detection, and Boundary Detection on a GPU, Neil Birkbeck, Michal Sofka, S. Kevin Zhou (University of Alberta, Canada)
• Acceleration of an Improved Retinex Algorithm, Yuan-Kai Wang, Wen-Bin Huang (Taiwan)
• FPGA Implementation of Naive Bayes Classifier for Visual Object Recognition, Hongying Meng, Kofi Appiah, Andrew Hunter, Patrick Dickinson (University of Lincoln, UK)
• Efficient reconfigurable entropy coder for embedded multi-standards video adaptation, Nicolas Marques, Hassan Rabah, Eric Dabellani, Serge Weber (Nancy University)
• Implementation and evaluation of FAST corner detection on the massively parallel embedded processor MX-G, Yushi Moko, Yoshihiro Watanabe, Takashi Komuro, Masatoshi Ishikawa, Masami Nakajima, Kazutami Arimoto (University of Tokyo, Japan)

Invited Talks: Hardware Adaptation

• NeuFlow: A Runtime Reconfigurable Dataflow Processor for Vision, Yann LeCun (part 1), Clément Farabet (part 2), (New York University, USA) [Co-authors: Berin Martini, Benoit Corda, Polina, Akselrod, Eugenio Culurciello]
• Adapting algorithms for hardware implementation, Donald Bailey (Massey University, New Zealand)
• Accelerating Neuromorphic Vision on FPGAs, Vijaykrishnan Narayanan (Pennslyvania State University, USA) [Co-authors: Sungho Park, Srinidhi Kestur, Kevin Irick]
• Embedded Face and Biometric Technologies for National and Border Security, Brian Lovell (University of Queensland, Australia) [Co-authors: Abbas Bigdeli, Sandra Mau]
• Pedestrian Detection using GPU-accelerated Multiple Cue Computation, Csaba Beleznai, (AIT Austrian Institute of Technology) [Co-authors: David Schreiber, Michael Rauter]

College undergraduates and high schoolers are now offered new oppotunities to learn about computer vision through a series of summer programs. This year, five separate programs are offered:

• The National Science Foundation’s REU (Research Experience for Undergraduates)
• Research Experience for Teachers supplement;
• Scholarships in Science, Technology, Engineering and Mathematics (S-STEM) and
• Computational Science Training for Undergraduates in the Mathematical Sciences (CSUMS),
• Army Research Office’s Apprenticeship program.

A press release from University of Central Florida (UCF) describes one of these summer programs to expose high school students to computer vision.

In addition, Montclair State University offers a REU program in image processing and computer vision. The program is led by Prof Stefan Robila. More information is available at the iMagine website.

Video presentations for the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2011 are now available at http://techtalks.tv/cvpr/2011. The event was held on June 20-25, 2011 in Colorado Springs. The online video presentations are available only to registered CVPR attendees. The video presentations offer a new medium to review the latest research and developments in computer vision.

The Seventh IEEE Embedded Computer Vision Workshop (ECVW) was recently held at Colorado Springs, in conjunction with CVPR 2011. According to the general chair, Dr. Nabil Belbachir, this year’s program had the highest number of presentations, including posters from both academia and industry. Over a hundred people attended and participated in the long ten-hour program, which also included a lunch tutorial by NVIDIA.

Two papers were selected for the best paper award:

• Near real-time Fast Bilateral Stereo on the GPU, Stefano Mattoccia, Marco Viti, Florian Ries University of Bologna, Italy)
• Energy-Optimized Mapping of Application to Smartphone Platform – A Case Study of Mobile Face Recognition, Yi-Chu Wang, Kwang-Ting Cheng (University of California, USA) -- pictured below

Please visit the ECVW website for more updates and details about the workshop.

In a recent Google research blog, the company listed a number of papers appearing at CVPR 2011 that show how involved it is in computer vision research. The article noted that many of Google's products such as Image Search, YouTube, Street View, Picasa, and Goggles are powered by computer vision algorithms. Among the CVPR 2011 papers highlighted as technologies that have made it into Google products are:

• Google Earth Facade Shadow Removal by Mei Han, Vivek Kwatra, and Shengyang Dai
• Tag Suggest for YouTube by George Toderici and Mehmet Emre Sargin
• Video Stabilization on YouTube Editor by Matthias Grundmann, Vivek Kwatra, and Irfan Essa

Computer Vision Central has previously reported on one of the papers above,"Auto-Directed Video Stabilization with Robust L1 Optimal Camera Paths", about technology that is now available publicly at http://youtube.com/editor.

Related news on Computer Vision Central

• YouTube launches video stabilization and 3D tools

The CVPR 2011 organizing committee has announced this year's best paper award recipients:

• Longuet-Higgins Prize
  Rapid Object Detection using a Boosted Cascade of Simple Features,
  Paul A. Viola, Michael J. Jones.
  Sponsored by Microsoft
• Best Paper
  Real-time Human Pose Recognition in Parts from Single Depth Images,
  Jamie Shotton, Andrew FItzgibbon, Mat Cook, Toby Sharp, Mark Finocchio, Richard Moore, Alex Kipman, Andrew Blake.
  Sponsored by Google
• Best Paper Honorable Mention
  Discrete-Continuous Optimization for Large-scale Structure from Motion,
  David Crandall, Andrew Owens, Noah Snavely, Daniel Huttenlocher
  Sponsored by Google
• Best Student Paper
  Recognition Using Visual Phrases,
  Ali Farhadi, Mohammad Amin Sadeghi
  Sponsored by United Technologies Research Center
• Best Student Paper Honorable Mention Separating Reflective and Fluorescent Components of An Image,
  Cherry Zhang, Imari Sato.
  Sponsored by Springer

Congratulations to this year's winners!

NVIDIA announced that it is sponsoring a contest soliciting research proposals using the next generation Tegra processor development kit. The announcement was made during the NVIDIA tutorial that was held during the 2011 Embedded Computer Vision Workshop (ECVW). Conference attendees can also visit the NVIDIA exhibitor booth at CVPR 2011 to see the Tegra (project Kal-el) development kit in action. Project proposals can be submitted at research.nvidia.com/cvpr11. Here are some details from the website:

• We are looking for partners that want to work on innovative research projects once the developer boards for the Project Kal-El, the next generation of Tegra, become available.
• We welcome you to provide research proposals. Selected proposals will be supported by donations of developer boards that have back-facing stereo camera, front facing single camera, tablet-size touch display, quad-core ARM (with Neon) CPU, and a powerful OpenGL ES 2.0 GPU. The boards have also prototype versions of FCam and OpenCV.
• We don't know yet when the boards will be available, but expect to have them during the summer of 2011. We also don't know how many we will have available for donation, but expect at least a couple of dozen.

At the 2011 Embedded Computer Vision Workshop (ECVW), Joe Stam (NVIDIA) presented their integrated Android development platform with integrated OpenCV functions. The effort is done jointly with Willow Garage and Itseez. This level of integration would help support the growth of embedded vision applications on smart camera hardware platforms such as the Project Kal-el (next gen Tegra processor) that will be released later in 2011. In addition, Dr. Kari Pulli (NVIDIA) described the new effort to port FCam API into the Tegra platform, providing a more structured access to the camera for computational photography and other applications.

The Seventh Embedded Computer Vision Workshop will be held Monday, June 20, 2011. See the ECVW webpage for complete details on the workshop, including keynotes and invited speakers.

If you are attending CVPR, you can register for the NVIDIA Tutorial. This tutorial provides an overview of the Tegra processor, the Android OS development environment, the NVIDIA hardware development kit, software libraries relevant to computer vision, and demos. No prior mobile development experience is needed, and by the end of the session, you will be ready to start your own mobile vision applications.

The Fifth ACM/IEEE International Conference on Distributed Smart Cameras (ICSDC 2011) is now accepting proposals for the demo session. Researchers and industry-based developers are invited to demonstrate and present their latest results. Written material can be submitted as a two-page demo paper that will be published. Furthermore, ICDSC 2011 will feature a PhD Forum where students present and defend their research topics and receive feedback from an academic jury. Two-page PhD Forum submissions will be published as well. The deadline for submission is June 19, 2011.

More information is available in the ICDSC 2011 website.