Developer Blog: Deploying Real-time Object Detection Models

This post is the first in a series that shows you how to use Docker for object detection with NVIDIA Transfer Learning Toolkit (TLT). For part 2, see Using the NVIDIA Isaac SDK Object Detection Pipeline with Docker and the NVIDIA Transfer Learning Toolkit.

The modular and easy-to-use perception stack of the NVIDIA Isaac SDK continues to accelerate the development of various mobile robots. Isaac SDK 2020.1 includes support for object detection for robots that must determine the identity and position of objects to perform intelligent operations such as delivering payloads or bin-picking for manufacturing and assembly lines.

One of the difficult aspects of building a reliable perception system is the gathering of diverse, realistically labeled, training data for a specific application. The Isaac SDK approach uses the simulation capabilities of the NVIDIA GPU-powered Isaac Sim to generate photorealistic synthetic datasets and use them for training robust object-detection models.

In this post, we explore how the Isaac SDK can be used to generate synthetic datasets from simulation and then use this data to fine-tune an object detection deep neural network (DNN) using the NVIDIA Transfer Learning Toolkit (TLT). In addition, we show how the Isaac SDK accelerated inference components enable real-time object detection for a factory intralogistics environment.

Read the full blog, Deploying Real-time Object Detection Models with the NVIDIA Isaac SDK and NVIDIA Transfer Learning Toolkit, on the NVIDIA Developer Blog

    Leave a Reply