KP Labs sp. z.o.o
KP Labs is a NewSpace company based in Poland. We support deep space exploration with enhanced spacecraft autonomy, technologies including hyperspectral imaging instruments and high-efficiency Data Processing Units.
Our key solutions:
- Zebra X1 - is a lightweight hyperspectral camera that can capture images in a wavelength of 470 to 900 nanometres and record 150 channels with a rate of 65 frames per second.
- Leopard - is a CubeSat standard-compliant Data Processing Unit which enables mission designers to apply AI solutions in space. It was designed to support capturing, managing and processing of data in orbit. Leopard redefines the current approach to remote sensing. Instead of sending huge unprocessed sets of data to ground stations, Leopard uses Deep Neural Networks to process data on-board and therefore only sends the most important and valuable insights to the ground. By reducing the time and cost of data transfer and processing, it enables you to focus on a rapid response to any detected phenomena. Leopard DPU is a part of Intuition-1 mission, which is a satellite equipped with a hyperspectral optical instrument and an on-board computer allowing for advanced data processing through convolutional neural networks to perform Earth observation.
We also work on fields related to:
- Electronics and optics design for space and BSP applications.
- Creation of artificial intelligence and machine learning methods.
KP Labs is a software development spin-off established in 2016 by a group of experienced engineers and scientists from the Silesian University of Technology who saw future business potential in applying machine learning algorithms to solve real-life problems.
The team of over 40 FTE (full-time equivalent) have gained experience while working for IT companies beforehand, mainly in medical imaging and computer vision fields. These projects encompassed, among others, increasing the diagnostic efficiency of dynamic-contrast enhanced imaging in oncology, as well as improving the analysis and information extraction from angiography and CT images in cardiac applications.
KP Labs also has experience in computer vision fields, segmentation of hyperspectral images and creating and implementing algorithms for satellite imagery analysis. The company successfully completed an EU funded project aimed to deliver an innovative video surveillance system which would contain detection algorithms utilizing stereo vision and machine learning to properly assign detected objects to appropriate classes, e.g. people, cars, and lorries. KP Labs received ESA funding for HyperNet project, which focused on the design and implementation of an extensive framework for experimental validation of hyperspectral deep learning segmentation algorithms.
Together with our partners and the Warsaw University of Technology we gaine. d experience in PW-Sat2 project (https://pw-sat.pl/en/home-page/). We supported the construction of the satellite by providing software and hardware solutions.
Succeses and awadrs
Our latest achievements, prizes and publications:
- Falcon 9 with PW-Sat2 CubeSat onboard successfully launched from Vandenberg Air Force Base - our team cooperated with PW-Sat2 with our partners.
- Publications about our Intuition-1 space mission in The Economist and SpaceNews periodicals: https://www.economist.com/science-and-technology/2019/06/13/using-ai-to-speed-up-the-processing-of-space-images, https://spacenews.com/polish-space-startup-selects-clyde-space-as-subcontractor-for-earth-observation-satellite-project/
- We are a member of Nvidia Inception Program.
- Deep Flow team qualified to participate in The Copernicus Accelerator Bootcamp 2018 and SpaceUP BSA program.
- Deep Flow team won the first Copernicus Hackathon in Poland - an international event financed by the European Commission, organized in 20 European cities.
- Our scientists actively participate in conferences. Especially in such event as Phi-week, INTERGEO Expo and Conference, IEEE Geoscience and Remote Sensing (GRSS) Symposium, ACIIDS 2019 and many others.
- In 2019 KP Labs Sp. z o.o. was one of 40 companies in Poland which received the title of Research and Development Centre in the field of electronics and space technology. Status of the R&D centre will allow us to develop R&D competence and support our partners in the field of professional research services.
Experience in Big Science projects
We have the following experience in Big Science projects:
- In May 2019 we completed the European Space Agency (ESA) commissioned project HYPERNET - “HYPER-spectral image segmentation using deep neural NETworks Hyperspectral satellite imaging (HSI)”. Within the project, we delivered cutting-edge algorithms to pre-process, augment, visualize, and precisely segment HSI.
- In March 2019 we completed the ESA commissioned project AMMER - “Automated Method for Measuring Eutrophication of Inland Water Using Remote Sensing.” AMMER helps monitor inland reservoir water quality thanks to a fully remote evaluation of phytoplankton concentration. Within this project, KP Labs developed cutting-edge algorithms which enabled detection of the concentration of phytoplankton.
Potential for cooperation
As an R&D Centre, we can support our partners in the field of professional research services. Our goal is to strengthen innovation through the creation of unique space technologies and products. The researches’ activities will mainly focus on the development of the onboard processing unit, autonomy and communication with satellites.
We are highly skilled in segmentation of hyperspectral images, computer vision solutions, creating and implementing algorithms for satellite imagery analysis, creating deep neural networks and heuristic algorithms, supporting satellite construction and providing software and hardware solutions.