ImageFlex 2.0 speeds development of autonomous vehicles
Abaco Systems has announced Release 2.0 of its ImageFlex image processing and visualisation toolkit at this week’s GPU Technology Conference (GTC).
ImageFlex leverages the power of GPU technology to provide an easy-to-use application processor interface (API) framework to speed and simplify the development, optimisation and maintenance of advanced artificial intelligence (AI) applications, says Abaco Systems, especially those targeted at autonomous vehicles.
ImageFlex enables developers of image/video processing and visualisation applications on graphic processor units (GPUs) to be more productive by hiding the complexity of the underlying software layers, while maintaining high performance, explains Abaco Systems. By providing an OpenGL abstraction layer (no OpenGL experience is required) it can reduce the number of lines of code required by a factor of five. According to Abaco, this radically reduces the effort and time needed to create, test and maintain the application. This means faster time-to-market as well as lower development cost, adds Abaco Systems.
New features for ImageFlex Release 2.0 include tools and reference examples enabling AI-based applications to be deployed on Abaco’s Nvidia-based GPU products. There is also the provision of a reference target tracking example – a core building block for tracking applications and high quality, GPU-optimised image stabilisation.
ImageFlex is complementary to Abaco’s Nvidia GPU-based GVC1000 and GVC2000 hardware platforms, which use the Nvidia Jetson supercomputer on a module for AI computing at the edge. Degraded Visual Environment (DVE), 360° situational awareness, helmet mount sight processing, target identification and tracking and other EO/IR processing applications can therefore be developed. It is portable across a range of graphics processing architectures and operating systems, and is potentially safety certifiable, adds Abaco Systems.
The ImageFlex API provides for a range of image processing operations from simple image transformations through to more complex lens distortion correction and image morphing. It includes optimised, high quality image fusion, stabilistion, tracking and distortion correction algorithms, as well as a comprehensive set of reference application examples that provide core software building blocks. ImageFlex also provides tools and reference examples demonstrating how to integrate with sensors and deploy AI-based applications such as object detection and recognition.
ImageFlex provides an image fusion function that can fuse image data from multiple sources of different resolutions. The algorithm adaptively adjusts to pull through the regions of highest contrast in each source to a produce a fused result, enabling an observer or processing stage to act on the combined information of the sources.
