High performance deep learning inference for video analytics

The NVIDIA DeepStream SDK is ideal for developers who are creating and deploying AI-based solutions for video analytics applications at scale, offering a complete framework and all the essential building blocks. It lets you focus on the core deep learning networks and IP you care about, rather than designing an end-to-end solution from scratch.

DeepStream SDK offers the capability to gain rich insights through a heterogeneous concurrent neural network architecture. Developers can leverage multiple neural networks to process each video stream, giving them the flexibility to bring in different deep learning techniques to deliver more intelligent insights. This can include detailed attributes such as a car’s color, type and make. DeepStream’s framework enables developers to build complex application pipelines and to seamlessly deploy them from the edge-to-cloud.

Developers are increasingly turning to AI to process video because it has been shown to deliver significantly better performance than previous approaches for these use cases. Applications of Intelligent Video Analytics (IVA) include understanding consumer behavior in retail, intelligent traffic systems, web content filtering, and ad injection.

DeepStream makes use of:

  • NVIDIA® TensorRT™ and NVIDIA CUDA® for AI and other GPU computing tasks
  • Video CODEC SDK and multimedia APIs for accelerated encode and decode
  • Imaging APIs for capture and processing
  • A graph-based architecture and modular plug-ins to create configurable processing pipelines

DeepStream also comes with sample code and pre-trained deep learning models as examples to perform classification and object detection on video streams.

DeepStream is available for NVIDIA Tesla and Jetson. Download the DeepStream SDK today to get started.