Video modification using visual saliency map for guiding humans gaze

Hironori Takimoto; Hitoshi Yamauchi; Yasue Mitsukura; Akihiro Kanagawa

doi:10.1541/ieejeiss.137.144

Video modification using visual saliency map for guiding humans gaze

Hironori Takimoto, Hitoshi Yamauchi, Yasue Mitsukura, Akihiro Kanagawa

Department of System Design Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

It is commonly believed that by drawing humans attention to particular objects, human activity can be effectively facilitated. The aim of this paper is to propose a novel video modification method for directing gaze to specific objects of interest, using a saliency map model based on L^∗a^∗b^∗ color space. First, we compute the saliency map, and modify the L^∗a^∗b^∗ components of each frame based on the obtained saliency map for adjusting saliency value. And then, we repeat this process until the specified objects has become the most salient in each frame. By applying the our attention retargeting method to a video, we can obtain the video in which the specific object shows the highest saliency.

Original language	English
Pages (from-to)	144-151
Number of pages	8
Journal	IEEJ Transactions on Electronics, Information and Systems
Volume	137
Issue number	1
DOIs	https://doi.org/10.1541/ieejeiss.137.144
Publication status	Published - 2017

Keywords

Guiding attention
Object tracking
Visual attention
Visual saliency map

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1541/ieejeiss.137.144

Cite this

@article{54d8a6d28c9845afa4d7f0b1eb2e56b4,

title = "Video modification using visual saliency map for guiding humans gaze",

abstract = "It is commonly believed that by drawing humans attention to particular objects, human activity can be effectively facilitated. The aim of this paper is to propose a novel video modification method for directing gaze to specific objects of interest, using a saliency map model based on L∗a∗b∗ color space. First, we compute the saliency map, and modify the L∗a∗b∗ components of each frame based on the obtained saliency map for adjusting saliency value. And then, we repeat this process until the specified objects has become the most salient in each frame. By applying the our attention retargeting method to a video, we can obtain the video in which the specific object shows the highest saliency.",

keywords = "Guiding attention, Object tracking, Visual attention, Visual saliency map",

author = "Hironori Takimoto and Hitoshi Yamauchi and Yasue Mitsukura and Akihiro Kanagawa",

year = "2017",

doi = "10.1541/ieejeiss.137.144",

language = "English",

volume = "137",

pages = "144--151",

journal = "IEEJ Transactions on Electronics, Information and Systems",

issn = "0385-4221",

publisher = "The Institute of Electrical Engineers of Japan",

number = "1",

}

TY - JOUR

T1 - Video modification using visual saliency map for guiding humans gaze

AU - Takimoto, Hironori

AU - Yamauchi, Hitoshi

AU - Mitsukura, Yasue

AU - Kanagawa, Akihiro

PY - 2017

Y1 - 2017

N2 - It is commonly believed that by drawing humans attention to particular objects, human activity can be effectively facilitated. The aim of this paper is to propose a novel video modification method for directing gaze to specific objects of interest, using a saliency map model based on L∗a∗b∗ color space. First, we compute the saliency map, and modify the L∗a∗b∗ components of each frame based on the obtained saliency map for adjusting saliency value. And then, we repeat this process until the specified objects has become the most salient in each frame. By applying the our attention retargeting method to a video, we can obtain the video in which the specific object shows the highest saliency.

AB - It is commonly believed that by drawing humans attention to particular objects, human activity can be effectively facilitated. The aim of this paper is to propose a novel video modification method for directing gaze to specific objects of interest, using a saliency map model based on L∗a∗b∗ color space. First, we compute the saliency map, and modify the L∗a∗b∗ components of each frame based on the obtained saliency map for adjusting saliency value. And then, we repeat this process until the specified objects has become the most salient in each frame. By applying the our attention retargeting method to a video, we can obtain the video in which the specific object shows the highest saliency.

KW - Guiding attention

KW - Object tracking

KW - Visual attention

KW - Visual saliency map

UR - http://www.scopus.com/inward/record.url?scp=85009366175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009366175&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.137.144

DO - 10.1541/ieejeiss.137.144

M3 - Article

AN - SCOPUS:85009366175

SN - 0385-4221

VL - 137

SP - 144

EP - 151

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

IS - 1

ER -

Video modification using visual saliency map for guiding humans gaze

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this