CapnaDSP: SPECTER - System-level Programming Environment and Common Framework for Intelligent Image Processing

Advances in sensor technology combined with high performance embedded processors has
yielded many novel applications and products in recent years, such as self-parking cars, realtime
visualisation for vascular intervention, vehicle tracking, and 3D image reconstruction.
The limiting factor in these designs is generally not in designer inventiveness but in the
underlying performance of the device and effort required to program it. By providing an
open, powerful, and easy to program platform, we address a number of key markets.
The project is targeted at the growing intelligent imaging market where applications are
demanding ever increasing performance with the shift towards higher resolutions, frame rates
and multi-source imaging techniques to improve content value delivered to users. In security,
next generation CCTV can no longer rely on operator-driven, standalone camera platforms but
on context and position-aware assisted operation where individual image feeds are combined
to build up an increased scene awareness, e.g. as a region of interest is expanded in one
camera feed; this needs to be communicated to allow dynamic stitching of multi-source
images to maintain full scene coverage.
Further techniques such as combining image sources from different parts of the radio
frequency spectrum, visible and infra-red, are also needed. For example, merging infra-red
images to increase the quality as the visible light decreases. As local data storage is expensive
and distributing data volumes is prohibitive, smart decisions on duration and retaining of data
is required. While complex in their nature, these techniques rely on a set fundamental
operational blocks to facilitate their implementation which if provided in a modular,
extensible hardware accelerated processing platform, would prove a major selling point over
other options. FPGA hardware acceleration has been applied to high end systems but
widespread market adoption will require a lowering of the barriers to entry for mid-range and
low-volume market segments. It is in providing a generic modular solution that can be quickly
customised and implemented that CapnaDSP sees a strong and rapidly emerging market
opportunity.
We believe that by ultimately making this technology accessible through a COTS platform
with easily configurable plug and play programming tools we can bring a product to market
that has a genuine unique selling point and commercial appeal. This will open up market
segments where FPGA hardware acceleration was not previously viable. Moves from 3 megapixel
CCD devices to CMOS cameras in the 8+ mega-pixel range, with frame rates rising
from 10-30fps to 60fps+, will mean that in a very short space of time the amount of data will
mandate new processing approaches. It is at this point that having demonstrated the merit of
our approach in this project, we will seek to commercialize the output and introduce our plug
and play processing solution to a range of markets.