Instructor-Led Workshop
Deep Learning for Intelligent Video Analytics

This workshop teaches you how to build object detection and tracking models to analyze data from large-scale video streams using NVIDIA DeepStream technology. You’ll access hands-on tasks to build, train, and deploy deep learning models to analyze parking lot camera feeds of a hardware-accelerated traffic management system. At the end of the workshop, you’ll have access to additional resources to design and deploy intelligent video analytics (IVA) applications on your own.

Learning Objectives


By participating in this workshop, you’ll:
  • Understand data normalization, annotation, and metadata formatting in IVA applications
  • Wrangle video data and perform raw data ingestion into underlying models
  • Deploy deep learning models for accurate and effective object detection and tracking applications
  • Accelerate the development of IVA applications by using the DeepStream framework

Download workshop datasheet (PDF 291 KB)

Workshop Outline

Introduction
(15 mins)
  • Meet the instructor.
  • Create an account at courses.nvidia.com/join
Object Detection for Intelligent Video Analytics (IVA)
(120 mins)
  • Learn the fundamentals of object detection methods in IVA applications, as well as preliminaries of raw data processing and metadata formatting.
  • Get hands-on experience with the Object Detection API.
  • Learn how to measure accuracy and performance of the models using intersection over union (IoU) metrics.
Break (60 mins)
Using Transfer Learning and Multiple-ObjectTracking Techniques in IVA
(120 mins)
  • Get familiar with the nuances of fine-tuning an IVA application and learn about the implications of modeling.
  • Measure and visualize model performance.
  • Understand how object detectors can be bootstrapped into your IVA application.
Break (15 mins)
Deploying the Application Using NVIDIA DeepStream
(120 mins)
  • Learn to deploy the video analytics models into a ready-to-use video processing pipeline using DeepStream.
  • Understand the fundamentals of creating robust smart city applications.
  • Learn how to easily plug in multiple inference models, and explore methods for visualizing the inference data.
Final Review
(15 mins)
  • Review key learnings and wrap up questions.
  • Complete the assessment to earn a certificate.
  • Take the workshop survey.
 

Workshop Details

Duration: 8 hours

Price: Contact us for pricing.  

Prerequisites:

  • Experience with deep neural networks (specifically variations of convolutional neural networks)
  • Intermediate-level experience with C and Python

Technologies: TensorFlow, DeepStream 3.0

Certificate: Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.

Hardware Requirements: Desktop or laptop computer capable of running the latest version of Chrome or Firefox. Each participant will be provided with dedicated access to a fully configured, GPU-accelerated server in the cloud.

Languages: English, Korean, Traditional Chinese

Questions?