Qualcomm introduced FastCV (Fast Computer Vision), a mobile-optimized computer vision (CV) library that includes the most frequently used vision processing functions for use across a wide array of Android mobile devices.
FastCV provides computationally intensive vision processing APIs, with hardware acceleration and better performance on mobile devices. FastCV is designed for efficiency on all ARM-based processors, but is also especially tuned to take advantage of Qualcomm’s Snapdragon processors (Qualcomm S2 and above). That’s because FastCV for Snapdragon can offload processing onto various subsystems within the processor, whereas FastCV for ARM is limited to acceleration on the CPU.
FastCV is the framework at the heart of Qualcomm’s vision-based Augmented Reality (AR) SDK, because AR is much more precise and useful when it’s based on camera input than on location-based estimates.
Qualcomm anticipates that FastCV will be used to build additional frameworks that will allow developers of computer vision apps to build compelling experiences around CV that take advantage of:
Face detection, tracking and recognition
Text recognition and tracking
Depth of field calculations
Developers can already download FastCV SDK and start building new user experiences leveraging camera-based apps.
There are also other developers’ resources for Qualcomm Computer Vision including:
FastCV API – Library of the most frequently used CV functions through the FastCV API.
FastCV Forum – Interact with other developers about how they are using computer vision to enhance their apps.
FastCV only supports Android for now, but Qualcomm plans to make FastCV SDK available to iOS developers in early 2012. You’ll also need to do the development under Windows, as Linux and MacOS are not currently supported.