This paper presents a novel filter to keep from over-smoothing the edges and corners and rectify the outliers in the flow field after each incremental computation step, which plays a key role during the process of estimating flow field. This filter works according to the spatial-temporal derivatives distance of the input image and velocity field distance, whose principle is more reasonable in filtering mechanism for optical flow than other existing nonlinear filters. Moreover, we regard the spatial-temporal derivatives as new powerful descriptions of different motion layers or regions and give a detailed explanation. Experimental results show that our proposed method achieves better performance.
Kaihong SHI
Tsinghua University
Zongqing LU
Tsinghua University
Qingyun SHE
Tsinghua University
Fei ZHOU
Tsinghua University
Qingmin LIAO
Tsinghua University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kaihong SHI, Zongqing LU, Qingyun SHE, Fei ZHOU, Qingmin LIAO, "Optical Flow Estimation Combining Spatial-Temporal Derivatives Based Nonlinear Filtering" in IEICE TRANSACTIONS on Information,
vol. E97-D, no. 9, pp. 2559-2562, September 2014, doi: 10.1587/transinf.2014EDL8030.
Abstract: This paper presents a novel filter to keep from over-smoothing the edges and corners and rectify the outliers in the flow field after each incremental computation step, which plays a key role during the process of estimating flow field. This filter works according to the spatial-temporal derivatives distance of the input image and velocity field distance, whose principle is more reasonable in filtering mechanism for optical flow than other existing nonlinear filters. Moreover, we regard the spatial-temporal derivatives as new powerful descriptions of different motion layers or regions and give a detailed explanation. Experimental results show that our proposed method achieves better performance.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8030/_p
Copy
@ARTICLE{e97-d_9_2559,
author={Kaihong SHI, Zongqing LU, Qingyun SHE, Fei ZHOU, Qingmin LIAO, },
journal={IEICE TRANSACTIONS on Information},
title={Optical Flow Estimation Combining Spatial-Temporal Derivatives Based Nonlinear Filtering},
year={2014},
volume={E97-D},
number={9},
pages={2559-2562},
abstract={This paper presents a novel filter to keep from over-smoothing the edges and corners and rectify the outliers in the flow field after each incremental computation step, which plays a key role during the process of estimating flow field. This filter works according to the spatial-temporal derivatives distance of the input image and velocity field distance, whose principle is more reasonable in filtering mechanism for optical flow than other existing nonlinear filters. Moreover, we regard the spatial-temporal derivatives as new powerful descriptions of different motion layers or regions and give a detailed explanation. Experimental results show that our proposed method achieves better performance.},
keywords={},
doi={10.1587/transinf.2014EDL8030},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Optical Flow Estimation Combining Spatial-Temporal Derivatives Based Nonlinear Filtering
T2 - IEICE TRANSACTIONS on Information
SP - 2559
EP - 2562
AU - Kaihong SHI
AU - Zongqing LU
AU - Qingyun SHE
AU - Fei ZHOU
AU - Qingmin LIAO
PY - 2014
DO - 10.1587/transinf.2014EDL8030
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2014
AB - This paper presents a novel filter to keep from over-smoothing the edges and corners and rectify the outliers in the flow field after each incremental computation step, which plays a key role during the process of estimating flow field. This filter works according to the spatial-temporal derivatives distance of the input image and velocity field distance, whose principle is more reasonable in filtering mechanism for optical flow than other existing nonlinear filters. Moreover, we regard the spatial-temporal derivatives as new powerful descriptions of different motion layers or regions and give a detailed explanation. Experimental results show that our proposed method achieves better performance.
ER -