This HD ANPR internationalisation project will develop unique computer vision and digital IP camera control algorithms together with innovative hardware design to take a UK-based approach to ANPR into new international markets. There are a number of major barriers to internationalisation for current ANPR suppliers, resulting in considerably less than the >95% read accuracy required by the market. Our intention is to develop the technology to provide: • A 4K IP camera solution to give >95% routine accuracy in regions where number plate forms, formats and location on vehicles are not as well regulated as they are in the UK and where motif recognition is also required e.g. province/vehicle class/cargo identifiers. • A system operating preferentially in visible light and employing novel LED Beam Shaping IR illumination when visible light is not available. • Coverage of complex lane configurations with fewer cameras enabling bidirectional traffic to be monitored by one camera, particularly in regions where only rear plates are mandatory. • An HD ANPR System specification ("cook-book") and configuration tools to allow easy system integration from off-the-shelf products by 4Sight-approved region integrators, made possible by unique HD ANPR software capable of using the latest IP camera technology. • Easy installation by CCTV installers i.e. non ANPR experts. The key benefits are: • Enable a new range of high accuracy surveillance products and services to be created and deployed by third party vendors e.g. automated car park payment, hazardous materials tracking and location identification. • Reduce the cost of deployment and maintenance. The key deliverable of this Project is the evaluation of the new set of computer vision and IP camera control algorithms through a series of prototypes that demonstrate the feasibility of remote product integration and installation via regional integrators and which achieve the required market leading performance.

The High Resolution Visible Light (HR-VL) Capable Automatic Number Plate Recognition (ANPR) Internationalisation Project will research new image processing and HD Digital CCTV camera control algorithms required to take a novel UK-based approach for ANPR into new international markets. Number plate forms, formats and location on vehicles in the UK and Europe are well constrained. This is not the case in many other parts of the World. For example, in the USA, the background format for a number plate can consist of images, variable colouring, etc. This makes ANPR considerably more difficult. The key areas of research/innovation will be: a) Internationalisation – to enable the image processing algorithms to handle non-UK number plates. This requires processing a wide range of fonts/character sets (with additional interest in Arabic, Cyrillic & Chinese), processing of plate backgrounds while compensating for typical defects on the number plate surface; b) Plug-and-play – making installation as simple as possible and removing the need for other than the actual installation visit to require user attendance. This requires new control software for the CCTV camera as a necessary precursor to internationalisation. Successful research into, and deployment of, new algorithms will: a) Enable new international markets in North America, Asia and the Middle East to become available; b) Reduce the cost of deployment and maintenance. Self-configuring HD Digital CCTV cameras enable a deployment to use fewer cameras to cover each road configuration; c) Enable a new range of surveillance products and services to be created and deployed by third party vendors. This includes automated car park payment, hazardous materials tracking and moving traffic violations. The key deliverable of this nine-month Proof-of-Concept Project is the evaluation of the new set of image science and HD CCTV camera control algorithms through their deployment and evaluation in a demonstrator.