AI-driven and scalable

The Herd

The Herd is a set of AI-powered algorithms designed to facilitate various data analyses. It comprises three elements – data pre-processing, data analysis algorithms and post-processing techniques.

Discover

Key applications

Earth Observation and Remote Sensing

‍

Provides efficient processing for multi- and hyperspectral data, improving satellite imagery with tasks like semantic segmentation, object detection, classification, and super resolution reconstruction.

‍

Satellite Telemetry Analysis

‍

Enables real-time monitoring and analysis of satellite telemetry data, ensuring more efficient signal processing and anomaly detection.

‍

_‍

Onboarding AI Models

‍

Facilitates the deployment of AI models directly on satellite hardware, with robust verification processes ensuring reliability in performing tasks like image analysis and object detection during the mission.

‍

Case study

Use cases

Our experience with the company has been nothing short of amazing. Their innovative solutions have revolutionized our space missions.

John Doe

CEO, XYZ Corp

Working with the company has been a game-changer for us. Their cutting-edge technology has significantly improved our mission outcomes.

Jane Smith

CTO, ABC Inc

The company's expertise and dedication are unmatched. They have exceeded our expectations in every way.

Mike Johnson

COO, DEF Corp

We are extremely satisfied with the company's services. Their solutions have greatly improved our mission efficiency.

Sarah Williams

CFO, GHI Inc

GENESIS (1&2)

Transforming Agriculture with Satellite-Driven Soil Monitoring Solutions

The project addresses traditional soil monitoring challenges by developing satellite-based solutions using hyperspectral imaging and machine learning algorithms for soil composition analysis.

GENESIS project aims to enable continuous monitoring of soil parameters through the Intuition-1 satellite platform, offering potential for large-scale data collection without ground sampling requirements.

The proposed system is designed to provide insights for agricultural management through space-based soil analysis, supporting more precise and sustainable farming practices.

‍

QZ Solutions

2021-2023

European Space Agency

Φsat-2

AI-Enhanced 6U CubeSat for Multispectral Earth Observation

The Φsat-2 mission demonstrates advanced AI capabilities in Earth observation through a 6U satellite equipped with a multispectral instrument, launched in August 2024.

KP Labs developed a CNN-based algorithm for automatic cloud detection, optimizing data transmission by filtering out cloud-covered images before downlink.

The project implemented 8-bit quantization to ensure algorithm efficiency within CubeSat hardware limitations while maintaining effective real-time image processing capabilities.

‍

Open Cosmos

2021-2024

European Space Agency

From design to deployment

Tailored solutions for onboard processing

We design and deploy AI models specifically for space missions, ensuring they are robust, efficient, and tailored to the unique challenges of operating in space.

Step 1: Design and Implementation of AI Models

‍

Each space mission is unique. AI models are designed using cutting-edge techniques to push the limits of current capabilities in satellite data processing. Solutions are crafted specifically to meet the needs of individual missions, ensuring optimal performance.

Step 2: Onboarding AI Models to Edge Devices

‍

Onboarding AI models to edge devices, such as AI-enabled satellites, is critical for their practical utility. This process may involve model quantization or more advanced techniques like knowledge distillation and optimization, depending on the target hardware, ensuring maximum efficiency.

Step 3: Verification and Validation of AI Models

‍

Reliability is essential. Quantitative, qualitative, and statistical verification and validation processes are used to ensure models perform effectively in harsh space environments, such as sensor noise and corruption, providing robust, reliable performance throughout the mission.

Scientific research

Publications

Explore our list of resources for valuable insights and information.

Understanding the value of hyperspectral image super-resolution from Prisma data

Artificial Intelligence

Details

Hyperspectral image pansharpening: the Prisma case study

Artificial Intelligence

Details

Multitemporal and multispectral data fusion for super-resolution of Sentinel-2 images

Artificial Intelligence

Details

All Publications

Contact

Let's talk

Thank you for your message! We will contact you shortly.

Something went wrong while submitting the form, please try again later.