New AI Vision Solution Kit with Cloud Connectivity

Basler is expanding its portfolio with embedded vision systems that feature cloud connectivity. This provides developers with an efficient solution for rapid prototyping for AI-based IoT applications.

Fully integrated: The new AI Vision Solution Kit with Cloud Connectivity

With the new AI Vision Solution Kit, Basler now offers a fully integrated development kit with cloud connectivity. It allows to test AI-based IoT applications on an optimized vision system and access cloud services. The cloud connectivity makes it easy to load or train neural networks, for example. The AI Vision Solution Kit reduces the complexity and need for expert knowledge of embedded hardware and software technology significantly. The system thus offers developers a new and efficient approach for rapid prototyping.

Cloud based ML applications made easy

Fully integrated embedded vision system
Prototyping of ML-based application examples
Simplified use of cloud-specific tools
Optimized image processing on the Edge Device
Defined interface for transferring metadata to the cloud
Supports and shortens the actual product development
Long-term availability of all components

Hardware

NEW Basler dart BCON for MIPI camera with a resolution of 13 MP
Processing: Due to its particularly powerful GPU, NVIDIA's Jetson Nano enables simplified handling of complex AI tasks

Find all product details here

Embedded Vision Kit	Camera module	Resolution	Processor	Interface
daA4200-30mci-JNANO-NVDK-AIA	daA4200-30mci	13 MP	NVIDIA Jetson Nano	BCON for MIPI

Our answer to the challenge of combining hard- and software components for new IoT vision systems

The Internet of Things (IoT) and the many options for product enhancement that it provides are no longer a new phenomenon. Yet, developers still face significant challenges when designing and implementing new, vision based IoT tasks such as detecting objects or people.

First, they need to define all the components required for the system:

1. Data acquisition: A data stream of images, generated by a camera;

2. Data processing: Powerful hardware to process image data;

3. Data analytics: A machine learning algorithm needed to perform the inference and

4. Connectivity: Ability to use cloud services and send meta data to the cloud (data storage, analytics).

Next, all these parts must fit together and operate seamlessly. Again, this requires extensive expert knowledge. With its new AI Vision Solution Kit, Basler enables developers to move directly into developing their IoT vision system: all the necessary hardware and software components are integrated into a ready-to-use prototyping kit.

The AI Vision Solution Kit is Basler’s answer to the challenge of combining hard- and software components when prototyping new IoT vision systems.

How It Works: The Functionality of the AI Vision Solution Kit with Cloud Connectivity

Targeted towards data scientists and field application engineers, the AI Vision Solution Kit is an embedded vision system for easy prototyping of IoT vision solutions. Its integrated hard- and software design comprises Basler’s newly developed IoT software architecture: Basler Container Management and Cloud Connector. They allow the easy deployment of optimized ML learning models and access to cloud services.

There are two options for machine learning models used on the system: developers can choose either Basler’s ML models or upload their own ML models.

1. Basler’s ML models are pre-trained ML models for object detection and people detection. These Basler ML models are optimized for the SoC and the generated image data: they work together seamlessly.

2. If developers use their own ML models, they can use the functionalities of AWS SageMaker and AWS SageMaker Neo to train, optimize and deploy them.

In the next step, the compiled ML model available in the Basler cloud is deployed on the kit using container management and AWS SageMaker.

As well, camera parameters can be adjusted using the camera configuration tool. pylon operates and configures the camera, which is a 13 MP Basler dart with BCON for MIPI interface. In this way, image quality can be adjusted and assured. This is important as the quality of the ML inference on the kit depends not only on the training of the model, but also on the quality of the acquired data from the camera and on the power of the processing unit. After the inference is done on the kit, the resulting meta data is sent to the AWS cloud and stored using AWS IoT Core.

With the AI Vision Solution Kit, prototyping of IoT vision solutions based on embedded technology is taken to the next level. Basler also supports its customers beyond the prototyping stage and develops customized solutions based on its flexible toolbox approach of hard- and software components.