mstiehm-nf/isaac_ros_object_detection

Deep learning model support for object detection including DetectNet

Isaac ROS Object Detection

Hardware-accelerated, deep learned model support for object detection including DetectNet.

Overview

Isaac ROS Object Detection contains an ROS 2 package to perform object detection. isaac_ros_detectnet provides a method for spatial classification using bounding boxes with an input image. Classification is performed by a GPU-accelerated DetectNet model. The output prediction can be used by perception functions to understand the presence and spatial location of an object in an image.

isaac_ros_detectnet is used in a graph of nodes to provide a bounding box detection array with object classes from an input image. A DetectNet model is required to produce the detection array. Input images may need to be cropped and resized to maintain the aspect ratio and match the input resolution of DetectNet; image resolution may be reduced to improve DNN inference performance, which typically scales directly with the number of pixels in the image. isaac_ros_dnn_image_encoder provides a DNN encoder to process the input image into Tensors for the DetectNet model. Prediction results are clustered in the DNN decoder to group multiple detections on the same object. Output is provided as a detection array with object classes.

DNNs have a minimum number of pixels that need to be visible on the object to provide a classification prediction. If a person cannot see the object in the image, it’s unlikely the DNN will. Reducing input resolution to reduce compute may reduce what is detected in the image. For example, a 1920x1080 image containing a distant person occupying 1k pixels (64x16) would have 0.25K pixels (32x8) when downscaled by 1/2 in both X and Y. The DNN may detect the person with the original input image, which provides 1K pixels for the person, and fail to detect the same person in the downscaled resolution, which only provides 0.25K pixels for the person.

Note

DetectNet is similar to other popular object detection models such as YOLOV3, FasterRCNN, and SSD, while being efficient at detecting multiple object classes in large images.

Object detection classifies a rectangle of pixels as containing an object, whereas image segmentation provides more information and uses more compute to produce a classification per pixel. Object detection is used to know if, and where in a 2D image, the object exists. If a 3D spacial understanding or size of an object in pixels is required, use image segmentation.

Isaac ROS NITROS Acceleration

This package is powered by NVIDIA Isaac Transport for ROS (NITROS), which leverages type adaptation and negotiation to optimize message formats and dramatically accelerate communication between participating nodes.

Performance

Sample Graph	Input Size	AGX Orin	Orin NX	Orin Nano 8GB	x86_64 w/ RTX 4060 Ti
DetectNet Object Detection Graph	544p	232 fps 11 ms	105 fps 15 ms	74.2 fps 22 ms	644 fps 5.6 ms

---

Documentation

Please visit the Isaac ROS Documentation to learn how to use this repository.

---

Packages

• isaac_ros_detectnet
  • Quickstart
  • Try More Examples
  • ROS 2 Graph Configuration
  • Troubleshooting
  • API
• isaac_ros_yolov8
  • Quickstart
  • API

Latest

Update 2023-10-18: Adding NITROS YOLOv8 decoder.