Back to customer stories

Axelera AI enables Vision AI at the edge with Ultralytics YOLO

Problem

Axelera AI needed an accurate and efficient vision model to showcase what its hardware could do and to help customers build real-time AI applications more easily.

Solution

By adding Ultralytics YOLO models to its Voyager SDK, Axelera AI made it simple for customers to run real-time computer vision solutions on its Metis AI Processing Units (AIPUs) right out of the box.

Axelera AI is a European semiconductor company that builds powerful, energy-efficient AI chips for running computer vision at the edge. For instance, their Metis AI Processing Units (AIPUs) are used in industries like retail, security, and manufacturing.

To make it easier for customers to build and deploy AI applications, Axelera integrated Ultralytics YOLO models into their Voyager SDK, a software platform that streamlines model optimization, deployment, and acceleration on Metis AIPUs, making real-time Vision AI faster, simpler, and more scalable.

Redefining Vision AI hardware acceleration

Founded in 2021 and based in the Netherlands, Axelera AI set out to solve a fundamental problem: traditional AI hardware was built for the cloud, not the edge. To close this gap, the company developed the Metis AIPU. 

It’s a high-performance, low-power chip designed specifically for edge workloads - AI tasks that run locally on devices where speed, privacy, and energy efficiency are critical.

It’s backed by their proprietary Digital In-Memory Compute (D-IMC) technology, which makes it possible for data to be processed directly where it’s stored and dramatically reduces latency and energy use. With a fully integrated software stack and a mission to democratize AI, Axelera is making high-performance AI more accessible.

The challenge of running models on edge AI hardware

To deliver a seamless AI experience at the edge, Axelera AI aimed to provide more than high-performance hardware. Customers also required a simple and reliable way to run real-time computer vision solutions that didn’t involve complicated tools or time-consuming customization. Many existing models were too large, too slow, or not well-suited for resource-constrained environments.

Retail analytics, factory automation, and surveillance systems often rely on fast and accurate visual insights to support operations. However, traditional models and cloud-based solutions typically can’t meet the low latency, energy efficiency, and on-device processing requirements of these edge AI applications.

Axelera began looking for a model suite that was accurate, easy to implement, and able to run efficiently on its Metis AI Processing Units. The right solution would complement its hardware capabilities while simplifying development and speeding up deployment across a broad range of edge AI use cases.

 Accelerated AI inferences at the edge with Ultralytics YOLO

Axelera AI integrated Ultralytics YOLO models into its Voyager SDK to make building and deploying edge AI applications faster, easier, and more scalable. The SDK includes a Model Zoo with ready-to-use YOLO models and automates the full pipeline, covering preprocessing, inference, and post-processing, optimized for Metis AI Processing Units.

Fig 1. Metis AI Processing Unit (AIPU).

This integration lets customers use pre-trained Ultralytics YOLO models out of the box or bring their own, with seamless acceleration on edge hardware. With support for parallel and cascaded model execution, Metis AIPUs enable advanced multi-model setups like pose estimation followed by segmentation. This is ideal for complex tasks in retail, security, and industrial automation.

The combination of real-time computer vision tasks supported by Ultralytics YOLO models and Axelera’s efficient hardware and software stack delivers exceptional performance per watt and per dollar. For customers, this means more accurate results, faster deployment, and a lower barrier to scaling Vision AI at the edge.

Why choose Ultralytics YOLO models?

Axelera AI partnered with Ultralytics to integrate Ultralytics YOLO models into its platform for their exceptional balance of accuracy, speed, and ease of use. With support for multiple Ultralytics YOLO variants, Axelera AI customers can evaluate a wide range of workloads and performance needs on the Metis AIPU.

Through an Ultralytics Enterprise License, Axelera provides access to the full suite of YOLO models for evaluation and development. For commercial deployment, customers are required to obtain their own license directly from Ultralytics via the license form, ensuring compliance and supporting scalable innovation in Vision AI at the edge.

Leveraging Ultralytics YOLO models at scale with Axelera AI’s Voyager SDK

With Ultralytics YOLO models and Axelera AI’s Voyager SDK, users can deploy accurate, low-latency computer vision applications directly on Metis AI Processing Units. Also, having access to multiple YOLO variants allows customers to adjust performance based on the specific needs of their application.

For example, Axelera AI has seen customers test YOLO-powered solutions across a variety of domains like:

  • Retail: Multi-model pipelines combining pose estimation, segmentation, and object detection can be used to support tasks like shrink reduction and inventory tracking. These deployments run efficiently on embedded platforms like the Raspberry Pi 5 paired with the Metis AIPU.

  • Manufacturing: Customers can use parallel model execution to perform simultaneous tasks, such as defect detection, product classification, and pose estimation, on a single chip to improve throughput and reduce hardware costs.

  • Surveillance: YOLO’s real-time object detection capabilities can be used to analyze 4K and 8K video streams at full resolution, facilitating high-accuracy safety monitoring and situational awareness in critical environments. This is a much better solution than traditional downscaling on high-resolution cameras.

  • Healthcare: Optimized YOLO pipelines can support tumor identification, offering high inference speed and reliable accuracy for on-device medical imaging.

These use cases showcase how Axelera AI’s edge AI hardware and Ultralytics YOLO models empower high-performance, energy-efficient Vision AI innovations across industries.

Driving the next wave of edge AI with Ultralytics YOLO

As Axelera AI continues to focus on expanding access to high-performance edge AI, it’s bringing together powerful hardware and reliable vision models to help customers build smarter, faster applications. 

With Ultralytics YOLO models available through the Voyager SDK and Metis AIPU hardware, users can easily develop and scale real-time computer vision solutions across industries. This collaboration supports a growing community of developers and businesses working to bring AI closer to where data is created, improving efficiency, responsiveness, and innovation at the edge.

Ready to accelerate your edge AI journey? Explore our GitHub repository to see how YOLO models are powering innovations like AI in retail and computer vision in logistics. Get hands-on with our Vision AI tools, learn about licensing options, and discover how you can unlock high-performance, energy-efficient computer vision at the edge.

Our solution to your Industry

View all

Frequently asked questions

What are Ultralytics YOLO models?

Ultralytics YOLO models are computer vision architectures developed to analyze visual data from images and video inputs. These models can be trained for tasks including Object detection, classification, pose estimation, tracking and instance segmentation.Ultralytics YOLO models include:

  • Ultralytics YOLOv5
  • Ultralytics YOLOv8
  • Ultralytics YOLO11

What is the difference between Ultralytics YOLO models?

Ultralytics YOLO11 is the latest version of our Computer Vision models. Just like its previous versions, it supports all computer vision tasks that the Vision AI community has come to love about YOLOv8. The new YOLO11, however, comes with greater performance and accuracy, making it a powerful tool and the perfect ally for real-world industry challenges.

Which Ultralytics YOLO model should I choose for my project?

The model you choose to use depends on your specific project requirements. It's key to take into account factors like performance, accuracy, and deployment needs. Here's a quick overview:

  • Some of Ultralytics YOLOv8's key features:
  1. Maturity and Stability: YOLOv8 is a proven, stable framework with extensive documentation and compatibility with earlier YOLO versions, making it ideal for integrating into existing workflows.
  2. Ease of Use: With its beginner-friendly setup and straightforward installation, YOLOv8 is perfect for teams of all skill levels.
  3. Cost-Effectiveness: It requires fewer computational resources, making it a great option for budget-conscious projects.
  • Some of Ultralytics YOLO11's key features:
  1. Higher Accuracy: YOLO11 outperforms YOLOv8 in benchmarks, achieving better accuracy with fewer parameters.
  2. Advanced Features: It supports cutting-edge tasks like pose estimation, object tracking, and oriented bounding boxes (OBB), offering unmatched versatility.
  3. Real-Time Efficiency: Optimized for real-time applications, YOLO11 delivers faster inference times and excels on edge devices and latency-sensitive tasks.
  4. Adaptability: With broad hardware compatibility, YOLO11 is well-suited for deployment across edge devices, cloud platforms, and NVIDIA GPUs

What license do i need?

Ultralytics YOLO repositories, such as YOLOv5 and YOLO11, are distributed under the AGPL-3.0 License by default. This OSI-approved license is designed for students, researchers, and enthusiasts, promoting open collaboration and requiring that any software using AGPL-3.0 components also be open-sourced. While this ensures transparency and fosters innovation, it may not align with commercial use cases.
If your project involves embedding Ultralytics software and AI models into commercial products or services and you wish to bypass the open-source requirements of AGPL-3.0, an Enterprise License is ideal.

Benefits of the Enterprise License include:

  • Commercial Flexibility: Modify and embed Ultralytics YOLO source code and models into proprietary products without adhering to the AGPL-3.0 requirement to open-source your project.
  • Proprietary Development: Gain full freedom to develop and distribute commercial applications that include Ultralytics YOLO code and models.

To ensure seamless integration and avoid AGPL-3.0 constraints, request an Ultralytics Enterprise License using the form provided. Our team will assist you in tailoring the license to your specific needs.

Power up with Ultralytics YOLO

Get advanced AI vision for your projects. Find the right license for your goals today.

Explore licensing options
Link copied to clipboard