Fast and efficient processing of hyperspectral images

Opportunity for

• Food safety companies delivering imaging products and services
• Companies interested in or using remote sensing technologies to develop or deliver products and services
• Security companies delivering imaging products and services
• Companies using platforms (drones / robotics) using hyperspectral cameras

Opportunity description

Industry challenge: Hyperspectral imaging is a different way of collecting photographic information. It is much more powerful than traditional photography, and provides significantly more information than can be seen with the naked eye. Hidden details can be found, and material properties can be discovered. Hyperspectral data can provide information to enable and accelerate the automation of tasks such as in the detection of crop disease, forensic applications and differentiating between different materials.

While hyperspectral cameras are now widely available, the software currently available to analyse the images is not efficient and restricts widespread adoption.

Current opportunity: The CSIRO has developed software to rapidly process hyperspectral images. The benefits associated with using this software includes increased accuracy of analysis (for example, by removing effects due to lighting and surface reflection on objects), and the reduction in constraints at the time of capture (for example, aerial imaging could be conducted at a wider variety of times of the day due to lighting compensation and ground-based use can be achieved more practically). An important feature of the software is the ability to perform tasks such as material indexing without the need to calibrate for lighting.

Hyperspectral imaging can provide more flexible and better results in applications such as food inspection, (fruit sorting or inspecting for microorganisms, fat vs meat content), agriculture (early detection of diseases in plants before they are visible, automated crop identification and health monitoring), and security (face detection allowing more flexible lighting and the ability to more quickly identify skin variants, accurate object tracking, etc).

An application programming interface (API) is available for developers to integrate hyperspectral processing into an application, or to build an application that makes use of the features of the software. The software suits ground based platforms or satellite imagery (if pre-calibrated). See scyllarus website for demonstration of the technology.