Dynamic estimation of optical flow field using objective functions
作者:
Highlights:
•
摘要
Optical flow (image velocity) fields are computed and interpreted from an image sequence by incorporating knowledge of object kinematics. Linear and quadratic objective functions are defined by considering the kinematics, and the function parameters are estimated simultaneously with the computation of the velocity field by relaxation. The objective functions provide an interpretation of the dynamic scenes and, at the same time, serve as the smoothness constraints. The computation is initially based on measured perpendicular velocity components of contours or region boundaries which, due to the ‘aperture problem’, are theoretically not the true perpendicular velocity components. This difficulty is alleviated by introducing a dynamic procedure for the measurement of the perpendicular components. Experiments on using objective functions for synthetic and real images of translating and rotating objects generated velocity fields that are meaningful and consistent with visual perception.
论文关键词:optical flow,image velocity field,objective function,dynamic estimation,relaxation algorithm,motion analysis
论文评审过程:Available online 10 June 2003.
论文官网地址:https://doi.org/10.1016/0262-8856(89)90029-2