Considerations about saliency map from Wide Angle Fovea image

Tatsuya Yamazaki; Nobuyuki Hasebe; Sota Shimizu

doi:10.1109/ISIE.2017.8001438

Considerations about saliency map from Wide Angle Fovea image

Tatsuya Yamazaki, Nobuyuki Hasebe, Sota Shimizu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Wide Angle Fovea (WAF) sensor acquires images having both high resolution and wide angle simultaneously. Such an image is quite applicable for multi-purpose use of the single vision sensor. When the WAF sensor is equipped on a planetary exploring rover, it influences intuitively to the basic design and model of the rover which needs to be autonomous strongly. In this paper, the authors pay attention to difference between the saliency maps generated from the WAF image and the pinhole lens image. Thus, we compared and discussed the performance of our proposed object detection method between the WAF lens and the pinhole lens by taking into consideration characteristcs of the WAF image, i.e., non-uniform resolution throughout the entire field of view (FOV) and higher distortion in more peripheral FOV.

Original language	English
Title of host publication	Proceedings - 2017 IEEE International Symposium on Industrial Electronics, ISIE 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1330-1335
Number of pages	6
ISBN (Electronic)	9781509014125
DOIs	https://doi.org/10.1109/ISIE.2017.8001438
Publication status	Published - 2017 Aug 3
Externally published	Yes
Event	26th IEEE International Symposium on Industrial Electronics, ISIE 2017 - Edinburgh, Scotland, United Kingdom Duration: 2017 Jun 18 → 2017 Jun 21

Other

Other	26th IEEE International Symposium on Industrial Electronics, ISIE 2017
Country	United Kingdom
City	Edinburgh, Scotland
Period	17/6/18 → 17/6/21

Keywords

Autonomos control
Biologically-inspired information processing
Machine intelligence
Saliency map
Wide angle fovea sensor

ASJC Scopus subject areas

Electrical and Electronic Engineering
Control and Systems Engineering

Access to Document

10.1109/ISIE.2017.8001438

Fingerprint Dive into the research topics of 'Considerations about saliency map from Wide Angle Fovea image'. Together they form a unique fingerprint.

Cite this

Considerations about saliency map from Wide Angle Fovea image. / Yamazaki, Tatsuya; Hasebe, Nobuyuki; Shimizu, Sota.

Proceedings - 2017 IEEE International Symposium on Industrial Electronics, ISIE 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1330-1335 8001438.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yamazaki, T, Hasebe, N & Shimizu, S 2017, Considerations about saliency map from Wide Angle Fovea image. in Proceedings - 2017 IEEE International Symposium on Industrial Electronics, ISIE 2017., 8001438, Institute of Electrical and Electronics Engineers Inc., pp. 1330-1335, 26th IEEE International Symposium on Industrial Electronics, ISIE 2017, Edinburgh, Scotland, United Kingdom, 17/6/18. https://doi.org/10.1109/ISIE.2017.8001438

@inproceedings{e082d9672ce34b5587f81946deb087b3,

title = "Considerations about saliency map from Wide Angle Fovea image",

abstract = "Wide Angle Fovea (WAF) sensor acquires images having both high resolution and wide angle simultaneously. Such an image is quite applicable for multi-purpose use of the single vision sensor. When the WAF sensor is equipped on a planetary exploring rover, it influences intuitively to the basic design and model of the rover which needs to be autonomous strongly. In this paper, the authors pay attention to difference between the saliency maps generated from the WAF image and the pinhole lens image. Thus, we compared and discussed the performance of our proposed object detection method between the WAF lens and the pinhole lens by taking into consideration characteristcs of the WAF image, i.e., non-uniform resolution throughout the entire field of view (FOV) and higher distortion in more peripheral FOV.",

keywords = "Autonomos control, Biologically-inspired information processing, Machine intelligence, Saliency map, Wide angle fovea sensor",

author = "Tatsuya Yamazaki and Nobuyuki Hasebe and Sota Shimizu",

year = "2017",

month = aug,

day = "3",

doi = "10.1109/ISIE.2017.8001438",

language = "English",

pages = "1330--1335",

booktitle = "Proceedings - 2017 IEEE International Symposium on Industrial Electronics, ISIE 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "26th IEEE International Symposium on Industrial Electronics, ISIE 2017 ; Conference date: 18-06-2017 Through 21-06-2017",

}

TY - GEN

T1 - Considerations about saliency map from Wide Angle Fovea image

AU - Yamazaki, Tatsuya

AU - Hasebe, Nobuyuki

AU - Shimizu, Sota

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Wide Angle Fovea (WAF) sensor acquires images having both high resolution and wide angle simultaneously. Such an image is quite applicable for multi-purpose use of the single vision sensor. When the WAF sensor is equipped on a planetary exploring rover, it influences intuitively to the basic design and model of the rover which needs to be autonomous strongly. In this paper, the authors pay attention to difference between the saliency maps generated from the WAF image and the pinhole lens image. Thus, we compared and discussed the performance of our proposed object detection method between the WAF lens and the pinhole lens by taking into consideration characteristcs of the WAF image, i.e., non-uniform resolution throughout the entire field of view (FOV) and higher distortion in more peripheral FOV.

AB - Wide Angle Fovea (WAF) sensor acquires images having both high resolution and wide angle simultaneously. Such an image is quite applicable for multi-purpose use of the single vision sensor. When the WAF sensor is equipped on a planetary exploring rover, it influences intuitively to the basic design and model of the rover which needs to be autonomous strongly. In this paper, the authors pay attention to difference between the saliency maps generated from the WAF image and the pinhole lens image. Thus, we compared and discussed the performance of our proposed object detection method between the WAF lens and the pinhole lens by taking into consideration characteristcs of the WAF image, i.e., non-uniform resolution throughout the entire field of view (FOV) and higher distortion in more peripheral FOV.

KW - Autonomos control

KW - Biologically-inspired information processing

KW - Machine intelligence

KW - Saliency map

KW - Wide angle fovea sensor

UR - http://www.scopus.com/inward/record.url?scp=85029895024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029895024&partnerID=8YFLogxK

U2 - 10.1109/ISIE.2017.8001438

DO - 10.1109/ISIE.2017.8001438

M3 - Conference contribution

AN - SCOPUS:85029895024

SP - 1330

EP - 1335

BT - Proceedings - 2017 IEEE International Symposium on Industrial Electronics, ISIE 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th IEEE International Symposium on Industrial Electronics, ISIE 2017

Y2 - 18 June 2017 through 21 June 2017

ER -