Scene Flow Estimation Based on Adaptive Anisotropic Total Variation Flow-Driven Method

Xuezhi Xiang; Rongfang Zhang; Mingliang Zhai; Deguang Xiao; Erwei Bai

doi:10.1155/2018/4908273

Back

Scene Flow Estimation Based on Adaptive Anisotropic Total Variation Flow-Driven Method

Journal article

Open access

Peer reviewed

Scene Flow Estimation Based on Adaptive Anisotropic Total Variation Flow-Driven Method

Xuezhi Xiang, Rongfang Zhang, Mingliang Zhai, Deguang Xiao and Erwei Bai

Mathematical problems in engineering, Vol.2018, pp.1-10

01/01/2018

DOI: 10.1155/2018/4908273

Files and links (1)

url

https://doi.org/10.1155/2018/4908273View

Published (Version of record) Open Access

Abstract

Scene flow estimation based on disparity and optical flow is a challenging task. We present a novel method based on adaptive anisotropic total variation flow-driven method for scene flow estimation from a calibrated stereo image sequence. The basic idea is that diffusion of flow field in different directions has different rates, which can be used to calculate total variation and anisotropic diffusion automatically. Brightness consistency and gradient consistency constraint are employed to establish the data term, and adaptive anisotropic flow-driven penalty constraint is employed to establish the smoothness term. Similar to the optical flow estimation, there are also large displacement problems in the estimation of the scene flow, which is solved by introducing a hierarchical computing optimization. The proposed method is verified by using the synthetic dataset and the real scene image sequences. The experimental results show the effectiveness of the proposed algorithm.

Details

Title: Subtitle: Scene Flow Estimation Based on Adaptive Anisotropic Total Variation Flow-Driven Method
Creators: Xuezhi Xiang - Harbin Engineering University
Rongfang Zhang - Harbin Engineering University
Mingliang Zhai - Harbin Engineering University
Deguang Xiao - Harbin Engineering University
Erwei Bai - Harbin Engineering University
Contributors: Francesco Marotti de Sciarra (Editor)
Resource Type: Journal article
Publication Details: Mathematical problems in engineering, Vol.2018, pp.1-10
DOI: 10.1155/2018/4908273
ISSN: 1024-123X
eISSN: 1563-5147
Publisher: Hindawi
Grant note: LC201426 / Natural Science Foundation of Heilongjiang Province 61401113 / National Natural Science Foundation of China
Language: English
Date published: 01/01/2018
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984573939802771

Metrics

4 Record Views