OpenVL: Developer-Friendly Computer Vision

Contact: Gregor Miller <gregor {at} ece.ubc.ca> ; Sidney Fels <ssfels {at} ece.ubc.ca>

We are very happy to announce the first release of OpenVL! This version provides a high-level interface to image segmentation. Results can be visualised using the included VisionGL library (for testing etc.), or extracted to use for your own applications. The release contains C++ static library binaries for OS X (Xcode/GCC), Windows (Visual Studio 2010) and Linux (GCC), as well as all the necessary headers, and an example application. Download OpenVL here.

Computer vision has a new and important role on the world technological stage with the advent of cheap cameras and high-performance low-power processors. Examples of its application are available throughout industry from simple face detection on compact cameras to advanced articulated modelling such as that on the Microsoft Kinect. However, implementation of a "simple" face detection system requires advanced knowledge of existing algorithms and their parameters, which is beyond the scope of general developers. Our approach is to develop an abstraction of computer vision, much like OpenGL provides an abstraction of computer graphics, allowing appropriately trained users to develop complex solutions without the need to specify particular algorithms or parameters.

The theme of our research within computer vision is access: we would like computer vision to be open and accessible beyond the confines of academia and computer vision experts. While many algorithms are freely and openly available, we do not consider these to be accessible, due to the knowledge and expertise required to effectively apply these to real-world problems. The direction of research we are pursuing is to create a basis from which access to computer vision techniques can be provided without requiring specialist knowledge. This requires an abstraction layer above the sophisticated techniques in vision: our key concept is an abstraction layer through which a description of the problem may be provided rather than requiring the selection of a particular algorithm i.e. we let developers describe what the problem is and have our system interpret the description to work out how to solve it, an approach we term problem-centric.

Publications and Activities

Workshop on User-Centred Computer Vision (UCCV2014), General Chair, Singapore, November 2014
.

Introduction to User-Centred Computer Vision, Gregor Miller, invited presentation at the Workshop on User-Centred Computer Vision (UCCV), Singapore, November 2014

Designing a Segmentation Abstraction for Non-Experts, Gregor Miller and Sidney Fels, invited presentation at the Graphics, Animation and New Media NCE Annual Conference (GRAND), Ottawa, Ontario, Canada, May 2014
.

Task-Based Control of Articulated Human Pose Detection for OpenVL, Georgii Oleinikov, Gregor Miller, James J. Little and Sidney Fels, IEEE Winter Conference on Applications of Computer Vision (WACV), Steamboat Springs, U.S.A., March 2014
  PDF   BibTeX
.

Accelerating OpenVL for Heterogeneous Platforms, Gregor Miller, Dong Ping Zhang and Sidney Fels, invited presentation at the AMD Developer Summit (AMD ADS), San Jose, U.S.A., November 2013

OpenVL as an Abstraction for Computer Vision on CPU, GPU and HSA, Gregor Miller and Sidney Fels, invited exhibit at the AMD Developer Summit (AMD ADS), San Jose, U.S.A., November 2013

The Sci-Fi Living Room: 3D Photography, 3D Displays and Personalised Video, Gregor Miller, invited presentation at the GRAND Digital Wave Workshop (GRAND), Vancouver, Canada, August 2013
.

OpenVL: Abstracting Vision Tasks Using a Segment-Based Language Model, Gregor Miller, Steve Oldridge and Sidney Fels, International Conference on Computer and Robot Vision (CRV), Regina, Saskatchewan, Canada, May 2013
  PDF   BibTeX
.

The Sci-Fi Living Room: 3D Photography, 3D Displays and Personalised Video, Gregor Miller, invited presentation at the University of British Columbia (UBC), Vancouver, Canada, May 2013

OpenVL: An Abstraction for Developer-Friendly Computer Vision, Gregor Miller and Sidney Fels, invited presentation at the Graphics, Animation and New Media NCE Annual Conference (GRAND), Toronto, Ontario, Canada, May 2013
  PDF   BibTeX
.

Workshop on User-Centred Computer Vision (UCCV2013), General Chair, Tampa, Florida, U.S.A., January 2013
.

The State of the Art in Developer-Centred Computer Vision, Gregor Miller, invited presentation at the Workshop on Developer-Centred Computer Vision (DCCV), Daejeon, Korea, November 2012

Workshop on Developer-Centred Computer Vision (DCCV2012), General Chair, Daejeon, Korea, November 2012

A Case for a High-Level Mainstream-Developer Interface to Computer Vision, Gregor Miller and Sidney Fels, invited presentation at the Khronos Vision Working Group (Khronos), Vancouver, B.C., Canada, September 2012

OpenVL: A High-Level Developer Interface to Computer Vision, Gregor Miller and Sidney Fels, invited presentation at the Qualcomm Research (Qualcomm), Santa Clara, California, U.S.A., August 2012

OpenVL: A High-Level Developer Interface to Computer Vision, Gregor Miller and Sidney Fels, invited presentation at the AMD Fusion Developer Summit (AFDS), Bellevue, Washington, U.S.A., June 2012

Towards a General Abstraction Through Sequences of Conceptual Operations, Gregor Miller, Steve Oldridge and Sidney Fels, International Conference on Vision Systems (ICVS), Sophia-Antipolis, France, September 2011
  PDF   BibTeX
.

Towards a Computer Vision Shader Language, Gregor Miller, Steve Oldridge and Sidney Fels, ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques; Posters (SIGGRAPH), Vancouver, British Columbia, Canada, August 2011
  PDF   BibTeX
.

A Conceptual Structure for Computer Vision, Gregor Miller, Sidney Fels and Steve Oldridge, International Conference on Computer and Robot Vision (CRV), St. John's, Newfoundland, Canada, May 2011
  PDF   BibTeX
.

Mapping the Problem Space of Image Registration, Steve Oldridge, Gregor Miller and Sidney Fels, Canadian Conference on Computer and Robot Vision (CRV), St. John's, Newfoundland, Canada, May 2011
  PDF   BibTeX
.

Understanding Image Registration: Towards a Descriptive Language of Computer Vision, Steve Oldridge (supervised by Gregor Miller and Sidney Fels), Ph.D. Thesis, University of British Columbia (UBC), Vancouver, Canada, February 2011
  PDF   BibTeX
.

A User-Oriented Language Model for Face Detection, Daesik Jang, Gregor Miller, Sidney Fels and Steve Oldridge, International Workshop on Person-Oriented Vision (POV), Keauhou, Kailua-Kona, Hawai'i, U.S.A., January 2011
  PDF   BibTeX
.

Classification of Image Registration Problems Using Support Vector Machines, Steve Oldridge, Sidney Fels and Gregor Miller, IEEE Workshop on Applications of Computer Vision (WACV), Keauhou, Kailua-Kona, Hawai'i, U.S.A., January 2011
  PDF   BibTeX
.

IEEE Workshop on Person-Oriented Vision (POV2011), General Chair, Keauhou, Kailua-Kona, U.S.A., January 2011
.

Automatic Classification of Image Registration Problems, Steve Oldridge, Gregor Miller and Sidney Fels, International Conference on Vision Systems (ICVS), Liège, Belgium, October 2009
  PDF   BibTeX
.

Vision Utility Framework: A New Approach To Vision System Development, Amir Afrah (supervised by Gregor Miller and Sidney Fels), Masters Thesis, University of British Columbia (UBC), Vancouver, Canada, January 2009
  PDF   BibTeX
.

Design and Implementation of a "What"-Oriented Open Vision Library, Changsong Shen, Steve Oldridge, Amir Afrah, Gregor Miller and Sidney Fels, invited presentation at the Canadian Conference on Intelligent Systems (IS), Windsor, Canada, May 2008
  PDF   BibTeX