Abstract
Complexities of dynamic volumetric imaging challenge the available computer vision techniques on a number of different fronts. This paper examines the relationship between the estimation accuracy and required amount of smoothness for a general solution from a robust statistics perspective. We show that a (surprisingly) small amount of local smoothing is required to satisfy both the necessary and sufficient conditions for accurate optic flow estimation. This notion is called "just enough" smoothing, and its proper implementation has a profound effect on the preservation of local information in processing 3D dynamic scans. To demonstrate the effect of "just enough" smoothing, a robust 3D optic flow method with quantized local smoothing is presented, and the effect of local smoothing on the accuracy of motion estimation in dynamic lung CT images is examined using both synthetic and real image sequences with ground truth.
Highlights
M OTION estimation is one of the most crucial and wellstudied problems of computer vision
Comparison of existing results for calculation of 2D optic flow reveals that for real images with discontinuous flow, the local robust approaches perform as well as global ones and the best available result far [8] is achieved by modeling the local discontinuities using a robust estimator
To investigate the effect of the local smoothing on the accuracy of optic flow we created a sequence of synthetic 3D images having a variety of known motions
Summary
M OTION estimation is one of the most crucial and wellstudied problems of computer vision. The underlying task is very general and has a wide range of applications. In the context of medical imaging, the estimation of motion has received substantial attention. With the advance of 3D dynamic imaging by MR, CT and ultrasound, motion estimation has become important in diagnostics, for instance to assess localized abnormalities in heart wall motion or vessel distensibility, as well as in radiation therapy planning and to compensate for soft tissue motion during image guided interventions. Two distinct approaches to estimation of apparent motion (or optic flow) have emerged. The first approach, described by Horn & Schunck [1], views the estimation as a global optimization problem and attempts to find
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
