qbxlvnf11/optical-flow

Optical flow with OpenCV, NvidiaHWOpticalFlow, Machine Learning methods etc.

Description

- Optical Flow

• The pattern of apparent motion of image objects between two consecutive frames caused by the movement of object or camera
• It is 2D vector field where each vector is a displacement vector showing the movement of points from first frame to second
• Details about optical flow: see blog posting in References section below

- Sparse Optical Flow vs Dense Optical Flow

• Sparse optical flow: computing the optical flow using the information about the corner location
• Dense optical flow: computing the optical flow for all the points in the frame

Contents

- Lucas-Kanade method based sparse optical flow with OpenCV

- Farneback method based dense optical flow with OpenCV

- Hardware-accelerated optical flow with NvidiaHWOpticalFlow: soon ...

Datasets

- MPI Sintel dataset

http://sintel.is.tue.mpg.de/downloads

References

- Sparse & dense optical flow

https://learnopencv.com/optical-flow-in-opencv/

https://nanonets.com/blog/optical-flow/

- Optical flow with OpenCV

https://docs.opencv.org/3.4/d4/dee/tutorial_optical_flow.html

- NvidiaHWOpticalFlow

https://docs.opencv.org/3.4/d3/dc1/tutorial_basic_linear_transform.html

Author

- LinkedIn: https://www.linkedin.com/in/taeyong-kong-016bb2154

- Blog URL: https://blog.naver.com/qbxlvnf11

- Email: [email protected], [email protected]