NVIDIA Jetson AGX Thor - RidgeRun Products - Video Stabilization
Overview of RidgeRun Video Stabilization Library
RidgeRun places strong emphasis on comprehensive documentation, especially for complex digital imaging tools such as video stabilization. Proper documentation helps reduce the learning curve and accelerates time-to-market, ensuring developers can focus on innovation rather than setup challenges.
Video Stabilization Library, which represents the company’s most advanced Electronic Image Stabilization (EIS) solution. Key features include:
- Real-time stabilization using accelerometer and gyroscope data from an IMU.
- State-of-the-art algorithms optimized for professional use cases.
- Hardware acceleration through SIMD CPU instructions, OpenCL, and CUDA.
- Cross-platform compatibility: PC, servers, and embedded systems.
This makes it particularly well-suited for drones, robotics, surveillance, and entertainment applications, where stability and low-latency performance are critical.
Examples
RidgeRun's Video Stabilization library provides an example that takes the input of a prerecored video stream alongside the data reported by the sensor. Then it generates the stabilized output video. More details can be found in the wiki.
The example use memory type NVMM and are tested in performance mode using jetson_clocks.sh on NVIDIA Jetson platforms.
Resolutions and Definitions:
- HD: 1920×1080 (WIDTH=1920, HEIGHT=1080)
- 4K: 3840×2160 (WIDTH=3840, HEIGHT=2160)
- BACKEND: CUDA (BACKEND=cuda)
- FOV: 2.4
The filesrc would be the following:
wget "https://drive.usercontent.google.com/download?id=1uW2sg3E2W2UOF9rjDaHG8eJus7m531_4&export=download&authuser=0&confirm=f" -O test-video-reencoded.mp4
The raw gyro data:
wget "https://drive.usercontent.google.com/download?id=1LXjqut2c8YIiJg66vH_UyYSdP664OErw&export=download&authuser=0&confirm=f" -O raw-gyro-data.csv
After the setup execute the script.
rvs-complete-concept -f ./test-video-reencoded.mp4 -g raw-gyro-data.csv -b $BACKEND -w $WIDTH -h $HEIGHT -s $FOV
Thor performance
The performance obtained by this element is plotted in the following table for different resolutions. There you can compare the GPU% and CPU% usage.
| Resolution | CPU (%) | GPU (%) |
|---|---|---|
| HD | 0.00276 | 23.00 |
| 4K | 0.00449 | 25.38 |
Getting Started
To know more about the extension, please refer to the Video Stabilization Library wiki page.
How to Purchase
For direct inquiries, please refer to the contact information available on our Contact page. Alternatively, you may complete and submit the form provided at the same link. We will respond to your request at our earliest opportunity.
Links to RidgeRun Resources and RidgeRun Artificial Intelligence Solutions can be found in the footer below.
ARTIFICIAL INTELLIGENCE
