The Khronos Group, an open consortium of leading hardware and software companies, has released the OpenVX 1.2 specification for cross-platform acceleration of computer vision applications and libraries, which comes with new functionality including neural network acceleration, feature detection, image classification, and conditional graph processing.
Three new extensions released alongside the graphic-based OpenVX 1.2 API enable the import and export of verified, optimized graphs, 16-bit image operations, and neural network inferencing acceleration. Updates include:
- The import/export extension enables a user to "compile" a graph offline, save or "export" it, and then at run-time efficiently "import" and execute it.
- The 16-bit extension provides signed 16-bit image data support for most image operations.
- The neural network extension introduces OpenVX graph nodes corresponding to common neural network operation layers, e.g. convolution, deconvolution, activation, normalization, pooling, and softmax, to enable the expression and low-power acceleration of neural network-based algorithms such as object detection and recognition.
Additionally, OpenVX 1.2 significantly expands the OpenVX vision operator and graph framework capabilities, including:
- Feature detection for object detection and recognition
- Classification operations for detection and recognition of objects based on a set of features
- Enhanced range of image processing operations
- Conditional execution of nodes for significantly expanded control and flexibility in expressing complex operations in an OpenVX graph
Furthermore, OpenVX SC 1,1, a modification of OpenVX 1.1 specification targeted at safety critical systems, was released to assist in the efficient system certification to meet the stringent requirements of markets such as advanced driver assistance systems (ADAS), autonomous vehicles and medical and process-control applications. This modification leverages the import/export extension to define a run-time-only "deployment feature set." Developers can use a complete set of graph construction features and development tools to implement the application, and then verify, compile, and export the verified graph in a binary format. Then, according to Khronos, the restricted "deployment" implementation executes on the target hardware by reading the binary format and executing the pre-compiled graphs.
"Computer vision applications are becoming increasingly important to a variety of scientific and consumer fields," said Greg Stoner, senior director, Radeon Open Compute, Radeon Technologies Group, AMD.
"AMD applauds The Khronos Group’s efforts on the OpenVX specification to accelerate these workloads, and offers continued support for open, royalty-free standards like OpenVX, which when used with AMD’s free, open-source deep learning library, MIOpen, creates a rich foundation for accelerating machine intelligence implementations."
View more information on OpenVX.
Learn more: search the Vision Systems Design Buyer's Guide for companies, new products, press releases, and videos