Real time optical flow estimation for images with large displacements

Abstract

Optical flow is defined as the pattern of apparent motion of objects in a image sequence. Optical flow has many applications: control of automatic taking off and landing of an autonomous aircraft, video compression, noise suppression, motion compensation and many more. There are different methods to estimate the optical flow. Variational models are the most frequently used methods to estimate the optical flow. These methods states an energy model to estimate the optical flow and frequently linealizations are used. Theses linearizations causes that the optical flow estimation fails if the motion presents displacements larger than the size of the objects. Optical flow methods generally implies large execution time to be estimated. In this work is presented a method that incorporate, to the classical optical flow's Horn-Schunk method, exhaustive matchings. These exhaustive matchings improve the estimation to handle large displacements. The method was implemented in a Intel i7, 3.5 GHz, GPU GeForce NVidia GTX 980 Ti and also a standard web-cam. Using images of 320 240 pixels the implementation reaches 6 images per second, which means that it is able to run in real time.

Optical flow is defined as the pattern of apparent motion of objects in a image sequence. Optical flow has many applications: control of automatic taking off and landing of an autonomous aircraft, video compression, noise suppression, motion compensation and many more. There are different methods to estimate the optical flow. Variational models are the most frequently used methods to estimate the optical flow. These methods states an energy model to estimate the optical flow and frequently linealizations are used. Theses linearizations causes that the optical flow estimation fails if the motion presents displacements larger than the size of the objects. Optical flow methods generally implies large execution time to be estimated. In this work is presented a method that incorporate, to the classical optical flow's Horn-Schunk method, exhaustive matchings. These exhaustive matchings improve the estimation to handle large displacements. The method was implemented in a Intel i7, 3.5 GHz, GPU GeForce NVidia GTX 980 Ti and also a standard web-cam. Using images of 320 240 pixels the implementation reaches 6 images per second, which means that it is able to run in real time.