vstabilisercv_web_thumbai.png
vstabilisercv_web_thumbai.png

VStabilizerCv C++ lib. Fast cross-platform video stabilisation library

€4,000.00

VStabilizerCv is 2D and 3D (horizontal offset, vertical offset and rotation) digital video stabilization C++ library.

LICENSE: We sell source code of this library as is, without future updates and technical support according to perpetual non-exclusive royalty-free license. You pay once and can use this library in your software and hardware products without limits. Please read the license agreement before purchasing: LICENSE.

VStabilizerCv is 2D and 3D (horizontal offset, vertical offset and rotation) digital video stabilization C++ library.

LICENSE: We sell source code of this library as is, without future updates and technical support according to perpetual non-exclusive royalty-free license. You pay once and can use this library in your software and hardware products without limits. Please read the license agreement before purchasing: LICENSE.

Overview

VStabiliserCv is a C++ library for fast 2D (X and Y offsets) and 3D (X and Y offsets + rotation) digital video stabilization. It provides two algorithm types selected by the TYPE parameter: 2D translation-only stabilization (horizontal and vertical offset) and 3D translation + rotation stabilization via the Fourier-Mellin transform. The library is designed for camera systems requiring video vibration compensation without any external dependencies — it requires only a C++17 compiler and the CMake build system. The library is written in standard C++17. The stabilization algorithm estimates inter-frame translation by cross-correlation in the frequency domain (FFT); the Fourier-Mellin type additionally estimates rotation on the log-polar magnitude spectrum. A Kalman motion filter separates vibration from intentional camera movement on every axis. It inherits the interface from VStabiliser (source code included, Apache 2.0 license), providing a standardized and interchangeable contract compatible with other VStabiliser-based implementations. The library supports various pixel formats (RGB24, BGR24, GRAY, YUV24, YUYV, UYVY, NV12, NV21, YV12, YU12.

Benchmarks

Per-frame stabilization time microseconds for 2D mode (translation only) and 3D mode (rotation + translation) at 1, 2 and 4 threads — across devices from the RPi Zero 2W to a Core i7. Test video and stabilization results with different library parameters you can check on video.

Demo video

Downloads

Documentation: GO TO DOCUMENTATION
Demo application to check algorithms performance on your video (Widows x64): DOWNLOAD

Simple interface

class VStabiliserCv: public VStabiliser
{
public:

    /// Get string of current VStabiliserCv class version.
    static std::string getVersion();

    /// Init all video stabiliser parameters by params structure.
    bool initVStabiliser(const cr::vstab::VStabiliserParams& params) override;

    /// Set value to parameter with given id.
    bool setParam(cr::vstab::VStabiliserParam id, float value) override;

    /// Get parameter with given id.
    float getParam(cr::vstab::VStabiliserParam id) override;

    /// Get params.
    void getParams(VStabiliserParams& params) override;

    /// Execute command.
    bool executeCommand(VStabiliserCommand id, float value = 0.0f) override;

    /// Stabilise video frame.
    bool stabilise(cr::video::Frame& src, cr::video::Frame& dst) override;

    /// Get offsets: horizontal, vertical and rotation.
    void getOffsets(float& dX, float& dY, float& dA) override;

    /// Decode and execute command.
    bool decodeAndExecuteCommand(uint8_t* data, int size) override;
};