Image Stitching for NVIDIA Jetson - Resources

Image Stitching for NVIDIA®Jetson™
Before Starting
Image Stitching Basics
Stitching Projections
Overview
Stitcher Projector Typical Applications Limitations and known issues
Getting Started
Evaluating the Stitcher Getting the code Building Image Stitching
User Guide
Quick Start Guide Controlling the Stitcher Calibration GStreamer Additional details
Resources
3D bases Panoramic data 360 data
Examples
Basic pipelines Using Gstd Other pipelines
Spherical Video
About Equirectangular Projection Projector Building Projector Stitcher Calibration Tool
Performance
Orin Xavier Nano
Contact Us

Resources

RidgeRun decided to create a collection of videos to help testing and benchmarking the cuda stitcher. The main goal of the dataset is provide recordings for a variability of camera arrays, specifically 3 setups were proposed:

• 360 video of three cameras with fisheye lenses.
• 360 video of two cameras with fisheye lenses.
• Panoramic mosaic of six cameras with rectilinear lenses.

For each setup we designed a camera mount 3D model that was printed with the aid of a 3D printer, used to place the cameras and record the dataset videos. Please Contact us in case you want to try them yourself and make your own recordings.

To record the videos we used IMX477 MIPI cameras attached to the NVIDIA Jetson AGX Orin through the Auvidea J20 adapter.

In the next wiki pages you can find information about:

• 3D bases

• Panoramic data

• 360 data