CMSoft presents a study on how to use OpenCL to accelerate the extraction of color Haar-like wavelet features from color images. This process involves OpenCL acceleration of the computation of the image integral, generation of regions of sliding window in the target picture and preparing data structures to receive all features.
The Khronos Group announced a new initiative to create an open, royalty-free standard for cross platform acceleration of computer vision applications. In response to requests and proposals from members, Khronos has created a vision working group to develop a hardware acceleration API using the proven Khronos development process and aiming for a first public release within 12 months. Any interested company is welcome to join Khronos to make contributions, influence the direction of the specification and gain early access to draft specifications before public release. The vision working group will commence work during January 2012.
Carlos Sánchez de La Lama announced Portable OpenCL on the LLVM development list. The Portable OpenCL project is self-described as “an open source implementation of the OpenCL standard which can be easily adapted for new targets. One of the goals of the project is improving performance portability of OpenCL programs, avoiding the need for target-dependent manual optimizations. A “native” target is included, which allows running OpenCL kernels on the host (CPU).” The source code is available online.