Video Stitching Software for Embedded Systems
Video Stitching for Embedded Systems
Developer guide for RidgeRun video stitching on embedded systems.
What is RidgeRun Video Stitcher?
RidgeRun's Video Stitching for Embedded Systems is a software solution that combines multiple synchronized camera feeds into a single, continuous panoramic or 360° video stream using calibrated image alignment and blending. Designed for NVIDIA Jetson, Qualcomm Dragonwing IQ-9075, and NXP i.MX95, it enables GPU-accelerated, multi-camera video stitching for robotics, autonomous vehicles, surveillance, and 360° camera systems. Built on LibPanorama, the solution supports fisheye and rectilinear camera inputs, integrates with GStreamer pipelines through the rrstitcher and rrglstitcher elements, and provides OpenGL acceleration across supported platforms, with an additional CUDA backend for NVIDIA Jetson.
On the Jetson AGX Orin, benchmarks demonstrate real-time stitching of three 4K video inputs at 30 FPS or higher, depending on the processing backend and system configuration. In a three-camera 1920x1080 OpenGL comparison using rrglstitcher, throughput reached 99 FPS on Jetson AGX Orin (MAXN, dynamic clocks), 57 FPS on Dragonwing IQ9, and 34 FPS on i.MX95. With jetson_clocks enabled, AGX Orin reached 205 FPS in the same three-input configuration.
RidgeRun Video Stitching demonstration.
What's New in RidgeRun Video Stitcher 2.0?
Built on the experience of 20 successful customer product deployments, RidgeRun Video Stitcher 2.0 represents the next generation of our embedded video stitching technology. Following the adoption of Video Stitcher 1.0 on NVIDIA platforms, customer demand for broader hardware compatibility drove the development of version 2.0. This release extends support to Qualcomm and NXP platforms through OpenGL-based acceleration, enabling video stitching across a wider range of embedded systems. At its core, Video Stitcher 2.0 integrates Libpanorama, RidgeRun's specialized image transformation library, to provide a hardware-accelerated foundation for multi-camera video stitching. The result is a more versatile solution built on proven deployment experience and RidgeRun's expertise in embedded image processing.
What is included in this guide?
This guide provides engineering tested steps to build, configure, and integrate RidgeRun's Video Stitching software to create panoramic and 360° video from multiple cameras on NVIDIA Jetson, Qualcomm Dragonwing IQ-9075, and NXP i.MX95. It covers installation and setup, the LibPanorama underlying architecture, CPU and GPU processing backends (OpenGL and CUDA), camera calibration for rectilinear and fisheye lenses, and real-time GStreamer pipeline integration using the rrstitcher and rrglstitcher elements. Developers will also find practical multi-camera stitching examples, troubleshooting guidance, and performance benchmarks comparing frame rates across embedded platforms, input resolutions, camera configurations, and processing backends.
Which embedded platforms are supported?
The LibPanorama-based Stitcher has been tested on:
- NVIDIA Jetson AGX Orin and Jetson Orin Nano: OpenGL and CUDA processing options.
- Qualcomm Dragonwing IQ-9075: OpenGL.
- NXP i.MX95: OpenGL.
OpenGL provides the cross-platform GPU processing path. CUDA is a Jetson-specific backend available with a compatible LibPanorama build; at the time, Video Stitching 2.0 does not support the former 1.0 GstCuda/NVMM integration in the GStreamer elements. See Architecture and Getting Started for backend requirements.
What it can do?
Video Stitching for Embedded Systems is intended for applications where multiple overlapping cameras are used to obtain a wider field of view. RidgeRun Video Stitching takes the calibrated camera views and combines them into a single panoramic output that can be displayed or used by other stages in a video pipeline.
Typical use cases include panoramic video, surveillance, robotics, teleoperation, and autonomous systems. It is a good fit for fixed multi-camera setups where the camera positions are known and can be calibrated beforehand.
Supported capabilities and limitations
Capabilities
- Multi-camera stitching using a predefined camera calibration.
- Standalone C++ API.
- GStreamer integration through the
rrstitcherandrrglstitcherelements. - System, OpenGL, and CUDA processing backends through LibPanorama, depending on the target platform.
- System-memory RGBA processing with
rrstitcher. - Direct OpenGL texture processing using
GstGLMemorywithrrglstitcher. - Automatic panorama dimensions based on the calibration and input resolution.
Limitations
- A valid calibration is required before stitching the camera inputs.
- All GStreamer inputs must use the same resolution and framerate.
- The input order must match the camera indices defined by the calibration.
rrglstitcherrequires GStreamer GL and a LibPanorama build with OpenGL support.- Available GPU backends depend on the capabilities of the target platform.
- Image quality depends on camera overlap, placement, synchronization, and calibration accuracy.
- Memory requirements increase with the input resolution, panorama size, and number of cameras.
Measured performance at a glance
The table shows rounded OpenGL stitching throughput with three synthetic 1920 × 1080 RGBA inputs. rrstitcher uses system-memory input; rrglstitcher uses GstGLMemory input.
| Platform | rrstitcher |
rrglstitcher |
|---|---|---|
| NVIDIA Jetson AGX Orin | 85 FPS | 99 FPS |
| Qualcomm Dragonwing | 49 FPS | 57 FPS |
| NXP i.MX95 | 15 FPS | 34 FPS |
These figures measure stitching throughput, not a complete camera-to-display frame rate. The synthetic benchmark excludes camera capture, decoding, encoding, and display. AGX Orin results were measured in MAXN mode with dynamic clocks. See Performance for the full test configuration, methodology, and results at other resolutions and camera counts.
Related documentation
Image Stitching for NVIDIA Jetson documents the former CUDA/GstCuda Stitcher and provides background on image stitching concepts. Our RidgeRun Video Stitching 2.0: OpenGL Support for Jetson, Dragonwing, and i.MX95 blog post provides a quick overview of RidgeRun's new Video Stitching solution. Visit the RidgeRun Store to learn more about the RidgeRun Video Stitching license.
Contact RidgeRun
For evaluation, integration, licensing, and platform-specific support, see RidgeRun's contact page.