Video Stabilization for Embedded Systems - Video Stabilization Basics
 |
| Video Stabilization for Embedded Systems |
|---|
|
| Video Stabilization Basics |
| Getting Started |
| User Guide |
| Examples |
| GStreamer plug-in |
|
Installing the plug-in |
| Contact Us |
RidgeRun's Video Stabilization for Embedded Systems is a software library that aims to provide efficient video stabilization solutions for resource constrained systems. The library uses different hardware units available in the platform to ensure real-time performance on a variety of small platforms.
Stages
Motion estimation
This stage leverages the motion estimation in H264 encoding to take advantage of hardware accelerated H264 encoding found in many SoCs.
Motion compensation
This stage applies a low pass filter with zero DC delay to reduce as much as possible the latency added by traditional low pass filters.
Image warping
This stage applies the final transformation to the image by taking advantage of hardware acceleration provided by OpenGL and running on the GPU.
Real-time in embedded systems
From these, the first and the last stages are known to be very resource intensive. For the motion estimation, we make use of the HW accelerated H.264 encoder and extract the motion vectors. Most modern platforms, even though small, are capable of encoding at 30fps. These motion vectors are aggregated to estimate the overall camera movement.
The camera movement is then smoothed out to eliminate undesired perturbations. This motion correction is applied to the original image by using OpenGL, which again may operate in real-time in the mentioned platforms.