Narrow directional steerable filters in motion estimation

Alexiadis, Dimitrios S.; Sergiadis, George D.

doi:10.1016/j.cviu.2007.07.002

Cited by 11 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…..I 0 denote the interpolation coefficients [10]. Based on the definition (9), it can be shown that the same interpolation formula holds for the filter replicas, namely…”

Section: Directional Filters and Filter "Replicas"mentioning

confidence: 99%

“…In [10], a complete framework for the construction of 3D steerable filters and their application to flow estimation can be found. In this work, we adapt and extend the relevant theory, towards the construction and use of filters for joint motion-disparity estimation.…”

Section: Steerable 3d Filters For Joint Motion-disparity Estimationmentioning

confidence: 99%

“…The "donut mechanism" [10,40] has been effectively applied in the 2D optical flow problem. It enables the fast calculation of an energy functional, known as the "max-steering" distribution, which describes the spectral energy distribution along (near) the motion planes.…”

Section: Definition Of Appropriate Energy Functionsmentioning

confidence: 99%

“…The problem of disparity estimation has been extensively studied during the last few decades [6,7]. Similarly, 2D motion (optical flow) estimation from monocular image sequences has been largely studied [6,[8][9][10]. However, most of the existing approaches treat depth and motion independently of each other.…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, in this paper, the joint estimation problem is formulated in the frequency-domain, and a steerable filter-based [10,11] approach is proposed. The motivation behind this direction of work was that early experimental studies have shown that the biological visual mechanisms can be modelled based on the spatiotemporal frequency-domain or filter-based considerations, for both the perception of depth [12,13] and the perception of motion [14,15].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Frequency-Domain Joint Motion and Disparity Estimation Using Steerable Filters

2018

View full text Add to dashboard Cite

Abstract:In this paper, the problem of joint disparity and motion estimation from stereo image sequences is formulated in the spatiotemporal frequency domain, and a novel steerable filter-based approach is proposed. Our rationale behind coupling the two problems is that according to experimental evidence in the literature, the biological visual mechanisms for depth and motion are not independent of each other. Furthermore, our motivation to study the problem in the frequency domain and search for a filter-based solution is based on the fact that, according to early experimental studies, the biological visual mechanisms can be modelled based on frequency-domain or filter-based considerations, for both the perception of depth and the perception of motion. The proposed framework constitutes the first attempt to solve the joint estimation problem through a filter-based solution, based on frequency-domain considerations. Thus, the presented ideas provide a new direction of work and could be the basis for further developments. From an algorithmic point of view, we additionally extend state-of-the-art ideas from the disparity estimation literature to handle the joint disparity-motion estimation problem and formulate an algorithm that is evaluated through a number of experimental results. Comparisons with state-of-the-art-methods demonstrate the accuracy of the proposed approach.

show abstract

“…..I 0 denote the interpolation coefficients [10]. Based on the definition (9), it can be shown that the same interpolation formula holds for the filter replicas, namely…”

Section: Directional Filters and Filter "Replicas"mentioning

confidence: 99%

Section: Steerable 3d Filters For Joint Motion-disparity Estimationmentioning

confidence: 99%

Section: Definition Of Appropriate Energy Functionsmentioning

confidence: 99%