 |
Metaspectral was founded by Migel Tissera and Francis Doumet in 2018.
The first iteration of Metaspectral was named PixelDrive and was created to leverage advances in machine learning for media compression, transmission, and storage in the cloud. In 2019, the company rebranded to Compression.ai and opened its platform to developers through an API to offer managed services. After receiving the title of the “real-life Pied Piper” from NVIDIA, Metaspectral was approached by both the defence and space industries in 2020, which were seeking efficient compression solutions for multispectral and hyperspectral data; and Metaspectral of today was born. Metaspectral today provides technology solutions for multiple government and commercial organizations for real-time analysis of electro-optical data to gain actionable insights. Co-founder Migel earned a PhD from the University of South Australia with his thesis focused on creating faster neural network architecture for real-time edge computing. He also holds a Bachelor’s in Electrical and Mechatronics Engineering from UniSA. Miguel previously developed computer vision software to automate operations for nursing homes, as well as computer vision software to provide proactive maintenance for natural gas wells.
Francis Dourmet has over 10 years of experience building software for Fortune 500 companies. He earned a Master’s in Engineering from Stanford University, and an MBA from the Wharton School of Business. Previously, he served as CEO of Adenda, a company building next-generation messaging tools for mobile operators. He has also held leadership positions with Agilent Technologies (robotics) and co-founded Catapult Design, a non-profit design consultancy providing engineering support to social impact organizations.
Metaspectral delivers the next generation of computer vision software, capable of remotely identifying materials and determining their chemical composition, defects, and other properties otherwise invisible to conventional cameras, as well as humans. It achieves this by leveraging hyperspectral sensors and analysing the sensor data in real-time using artificial intelligence (AI) via its scalable, cloud-based platform. Hyperspectral images include up to 300 unique spectral bands instead of the usual three that conventional colour cameras capture. This results in a tremendous volume of data that Metaspectral’s technology is uniquely designed to handle. Novel data compression algorithms can shuttle hyperspectral data more quickly and completely than other methods, whether from orbit to ground or within terrestrial networks. This information makes it possible for the algorithms to identify the molecular composition and properties of materials remotely using only computer vision.
The software is already deployed in a range of industries including aerospace, defence, agriculture, recycling, manufacturing and more. The technology is planned for deployment on the International Space Station to demonstrate real-time compression, streaming, and analysis of hyperspectral data from Low Earth Orbit (LEO). The company’s client list also includes organisations such as the Canadian Space Agency, Defence Research Development Canada (DRDC), and one of the largest consumer packaging recyclers in Canada.
Metaspectral are looking to connect with organisations in the space and defence industries including the Australian Space Agency, DSTG and defence/space prime contractors.
09 February 2022
Space companies from as far as India and Germany will make their way to South Australia, to be part of the state’s coveted Venture Catalyst Space Program.
Co-founder, CTO
Co-founder, CEO
(08) 8302 7368
The Venture Catalyst Space program is Australia's first incubator program for startups in the space sector.
