TY - GEN
T1 - Saliency map for wide angle fovea vision sensor
AU - Murakami, Rei
AU - Shimizu, Sota
AU - Hasebe, Nobuyuki
AU - Yamazaki, Tatsuya
N1 - Funding Information:
This study was partially supported by JSPS Grants-in-Aid for Scientific Research No. 15K05914 and No. 18K04055. The authors would like sincerely to appreciate Prof. Seiichi Mita, Toyota Institute of Technology for their kind helps. We would like thank all the members of Human Support Intelligent Robotics laboratory and other students and staffs in Department ofDesign and Engineering, Shibaura Institute of Technology.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/26
Y1 - 2018/12/26
N2 - This paper proposes and develops a saliency map suitable for the wide angle fovea (WAF) sensor. The saliency map is well-known as a computational method inspired from the human cognitive vision processing. This bottom-up processing method is often available for finding a target, which should be paid attention to, automatically from the arbitrary scene. However, it is not necessarily sufficient to use the existing saliency sap directly with the W A F sensor. Usually, we utilize the W A F sensor by combining different-level image processing tasks using its high spatial resolution central field of view (FOV) or its wide-angle F O V cooperatively, because the W A F sensor does not provide with a uniform resolution input image. When we apply the saliency map for the input image by the W A F sensor, we need to take into account unique properties of this biologically-inspired special vision sensor. Therefore, we design a novel saliency map model which is more suitable for the W A F sensor. After configuration of this specific saliency map, some verification experiments were implemented to enhance advantages of our proposed saliency map for the W A F sensor, i.e., W A F saliency map.
AB - This paper proposes and develops a saliency map suitable for the wide angle fovea (WAF) sensor. The saliency map is well-known as a computational method inspired from the human cognitive vision processing. This bottom-up processing method is often available for finding a target, which should be paid attention to, automatically from the arbitrary scene. However, it is not necessarily sufficient to use the existing saliency sap directly with the W A F sensor. Usually, we utilize the W A F sensor by combining different-level image processing tasks using its high spatial resolution central field of view (FOV) or its wide-angle F O V cooperatively, because the W A F sensor does not provide with a uniform resolution input image. When we apply the saliency map for the input image by the W A F sensor, we need to take into account unique properties of this biologically-inspired special vision sensor. Therefore, we design a novel saliency map model which is more suitable for the W A F sensor. After configuration of this specific saliency map, some verification experiments were implemented to enhance advantages of our proposed saliency map for the W A F sensor, i.e., W A F saliency map.
KW - Attention shift
KW - Eye movement
KW - High spatial resolution
KW - Reg interest
KW - Saliency map
KW - Staticfea dynamicfeature
KW - Wide anglefovea sensor
KW - Widefield of view
UR - http://www.scopus.com/inward/record.url?scp=85061523578&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061523578&partnerID=8YFLogxK
U2 - 10.1109/IECON.2018.8591050
DO - 10.1109/IECON.2018.8591050
M3 - Conference contribution
AN - SCOPUS:85061523578
T3 - Proceedings: IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society
SP - 5481
EP - 5486
BT - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 44th Annual Conference of the IEEE Industrial Electronics Society, IECON 2018
Y2 - 20 October 2018 through 23 October 2018
ER -