Learn how AI-based video analytics applications using DeepStream SDK 2.0 for Tesla can transform video into valuable insights for smart cities. Our latest version offers a modular plugin architecture and a scalable framework for application development. It comes with the most frequently used plugins for multi-stream decoding/encoding, scaling, color space conversion, tracking, and multi-stage inference. It also utilizes the newest TensorRT and CUDA tools for the highest throughput and channel density.
Developers can leverage the DeepStream SDK for Tesla to deploy IVA at scale to focus on core deep learning development, while offering the best system level software optimization and performance.
By watching this webinar replay, you'll learn how to:
- Build modular and scalable frameworks for multi-stream, multi-DNN video analytics
- Use TensorRT to optimize deep learning inference at runtime for low latency and high throughput
- Utilize included sample code and pre-trained models for image classification, understanding, categorization and filtering.