Improving the Optical Flow Accuracy Based on the Total Variation of Local-Global method
被引:0
|
作者:
Zhang, Yugui
论文数: 0引用数: 0
h-index: 0
机构:
Beihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R ChinaBeihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R China
Zhang, Yugui
[1
]
Fan, Haonan
论文数: 0引用数: 0
h-index: 0
机构:
Beihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R ChinaBeihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R China
Fan, Haonan
[1
]
Zheng, Jin
论文数: 0引用数: 0
h-index: 0
机构:
Beihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R ChinaBeihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R China
Zheng, Jin
[1
]
Zhang, Chi
论文数: 0引用数: 0
h-index: 0
机构:
Beihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R ChinaBeihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R China
Zhang, Chi
[1
]
机构:
[1] Beihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R China
Optical flow estimation;
Total variation;
Combined local-global;
Median filtering;
SEGMENTATION;
FIELDS;
D O I:
暂无
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
The aim of this paper is to improve the optical flow accuracy for the preservation of flow discontinuities in total variation method. The proposed method is based on the total variation of the local-global method, including the following steps: firstly, the initial optical flow is obtained from the local-global method; secondly, the data item and the smoothing item are designed based on initial optical flow by using the total variation, with the data item involving the brightness constancy and the gradient constancy, and the smoothing item involving exponential function; and finally, the optical flow results from the second step are optimized by using median filtering. The experimental results show that our proposed method could enhance the accuracy and robustness of the optical flow on the Middlebury Dataset and the MPI Sintel Dataset.
机构:
School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha,410114, ChinaSchool of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha,410114, China
Wang, Wei
Li, Xijie
论文数: 0引用数: 0
h-index: 0
机构:
School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha,410114, ChinaSchool of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha,410114, China
Li, Xijie
Wang, Xin
论文数: 0引用数: 0
h-index: 0
机构:
School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha,410114, ChinaSchool of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha,410114, China
机构:
Southwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R ChinaSouthwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R China
Zhou, Yi
Ning, Shuncheng
论文数: 0引用数: 0
h-index: 0
机构:
Southwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R China
Southwest Jiaotong Univ, Key Lab High Speed Railway Engn, Minist Educ, Chengdu, Sichuan, Peoples R ChinaSouthwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R China
Ning, Shuncheng
Huang, Dongchuan
论文数: 0引用数: 0
h-index: 0
机构:
Southwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R ChinaSouthwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R China
Huang, Dongchuan
Li, Yinglei
论文数: 0引用数: 0
h-index: 0
机构:
Hong Kong Polytech Univ, Civil & Environm Engn, Hong Kong, Peoples R ChinaSouthwest Jiaotong Univ, Sch Civil Engn, 999 Xian Rd, Chengdu, Sichuan, Peoples R China