Abstract
Estimating the displacements of intensity patterns between sequential frames is a very well-studied problem, which is usually referred to as optical flow estimation. The first assumption among many of the methods in the field is the brightness constancy during movements of pixels between frames. This assumption is proven to be not true in general, and therefore, the use of photometric invariant constraints has been studied in the past. One other solution can be sought by use of structural descriptors rather than pixels for estimating the optical flow. Unlike sparse feature detection/description techniques and since the problem of optical flow estimation tries to find a dense flow field, a dense structural representation of individual pixels and their neighbors is computed and then used for matching and optical flow estimation. Here, a comparative study is carried out by extending the framework of SIFT-flow to include more dense descriptors, and comprehensive comparisons are given. Overall, the work can be considered as a baseline for stimulating more interest in the use of dense descriptors for optical flow estimation.
Highlights
Optical flow estimation refers to the estimation of displacements of intensity patterns in image sequences [1,2]
Several widely-used databases are available on the web for assessing the performance of optical flow estimation algorithms [3,54]
Inspecting the results, it is shown that dense scale-invariant feature transform (SIFT) is able to capture the structural representations of the objects contained in the sequences in a more robust and reliable way in comparison to the rest, while the performance of the dense Schmid descriptor is the worst
Summary
Optical flow estimation refers to the estimation of displacements of intensity patterns in image sequences [1,2]. As for the data term, one of the basic assumptions is to have constant brightness during movements of pixels This assumption is the outcome of some other assumptions regarding the reflectance properties of the scene, the illumination and the process of image formation in the camera [3,4]. Use of photometric invariant constraints, such as the constancy of the gradient in the work of Brox et al [5], higher order derivatives proposed in [6] and color models with photometric invariant channels [7,8], have been investigated before Another problem arises when having motion discontinuities and occlusions in the underlying flow filed, which can be remedied by the use of non-quadratic penalty functions for data terms and the smoothness term, as proposed by [9,10,11] and many other techniques in recent years
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
