Object Scene Flow with Temporal Consistency

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00308347" target="_blank" >RIV/68407700:21230/17:00308347 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Object Scene Flow with Temporal Consistency

Original language description

In this paper, we propose several improvements of the Object Scene Flow (OSF) algorithm [14]. The OSF does not use the scene flow estimated in previous frame nor the object labels and their corresponding object motion information. The goal of this paper is to use this information in order to produce temporarily consistent output throughout the whole video sequence. We evaluate the progress on the KITTI’15 multiframe dataset. We show that propagating the labels and the corresponding motion information using the estimated flow reduces the false negative rate (missed cars). Together with two further proposed improvements the overall reduction of false negative is 42%. The proposed improvements also reduce EPE on the KITTI’15 scene flow from 10.63% to 9.65%.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2017

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 22nd Computer Vision Winter Workshop

ISBN

978-3-200-04969-7

ISSN

—

e-ISSN

—

Number of pages

9

Pages from-to

—

Publisher name

Pattern Recognition & Image Processing Group, Vienna University of Technology

Place of publication

Wien

Event location

Retz

Event date

Feb 6, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—