For the implementation of a VAT application / service in the real world, remote administration and control of the applications is essential. DeepStream SDK can run on any cloud and at the edge, making it a powerful SDK to handle IoT requirements such as effective two-way messaging between the edge and the cloud, security, smart recording, and over-the-air AI model update.
With two-way messaging between the edge and the cloud, you can add greater control for use cases, such as remote triggers for event recording, changing operational parameters and application settings, or requesting system logs.
The smart logging feature in the DeepStream app allows you to save valuable disk space at the edge with selective burning that enables faster searching. You can use cloud-to-edge messaging to quickly trigger recording from the cloud.
Hassle-free wireless update (OTA) for the entire application or individual AI models from any cloud registry to continuously improve accuracy without downtime.
For secure communication of IoT devices, DeepStream provides two-way TLS authentication based on SSL certificates and encrypted communication based on public key authentication.
DeepStream offers an interface for IoT integration with Kafka, MQTT and AMQP and turnkey integration with AWS IoT and Microsoft Azure IoT.
You can build high-performance DeepStream cloud-native applications with NVIDIA NGC containers. Using DeepStream, you can scale-out and manage containerized applications with Kubernetes and Helm Charts.
POWERFUL AND FLEXIBLE SDK
A unified SDK suitable for a multitude of use cases in a wide set of industries.
Duplicate blocks and columns to add more features.
Understand rich, multimodal sensor data at the edge.
Deploy AI services in cloud-native containers and orchestrate with Kubernetes.
Managed AI services.
Train with the Transfer Learning Toolkit and use DeepStream to increase flow density.