Adaptive window search using semantic texton forests for real-time object detection

Yuki Ono; Abdul Raziz Junaidi; Tadahiro Kuroda

doi:10.1109/ICIP.2013.6738678

Adaptive window search using semantic texton forests for real-time object detection

Yuki Ono, Abdul Raziz Junaidi, Tadahiro Kuroda

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

1 Citation (Scopus)

Abstract

We propose a new window search method to realize real-time object detection. Our method generates windows adaptively for objects' shapes and scales to detect various size objects. It also achieves real-time window search by using fast estimation of object's location based on existence probability of an object. Experiment results demonstrate that the proposed method reduces the number of windows drastically compared with exhaustive search. Furthermore, our method reduces the processing time while maintaining recall compared with the state-of-the art method when the numbers of searched windows are same in Pascal VOC 2007 dataset.

Original language	English
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages	3293-3296
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2013.6738678
Publication status	Published - 2013 Dec 1
Event	2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia Duration: 2013 Sept 15 → 2013 Sept 18

Publication series

Name	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

Other

Other	2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/Territory	Australia
City	Melbourne, VIC
Period	13/9/15 → 13/9/18

Keywords

adaptive window search
object detection
object map
real-time

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIP.2013.6738678

Cite this

Ono, Y., Junaidi, A. R., & Kuroda, T. (2013). Adaptive window search using semantic texton forests for real-time object detection. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings (pp. 3293-3296). Article 6738678 (2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings). https://doi.org/10.1109/ICIP.2013.6738678

Adaptive window search using semantic texton forests for real-time object detection. / Ono, Yuki; Junaidi, Abdul Raziz; Kuroda, Tadahiro.
2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 3293-3296 6738678 (2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings).

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

Ono, Y, Junaidi, AR & Kuroda, T 2013, Adaptive window search using semantic texton forests for real-time object detection. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738678, 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, pp. 3293-3296, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, Australia, 13/9/15. https://doi.org/10.1109/ICIP.2013.6738678

@inproceedings{67e00667d3234445a2fc3527f60d442e,

title = "Adaptive window search using semantic texton forests for real-time object detection",

abstract = "We propose a new window search method to realize real-time object detection. Our method generates windows adaptively for objects' shapes and scales to detect various size objects. It also achieves real-time window search by using fast estimation of object's location based on existence probability of an object. Experiment results demonstrate that the proposed method reduces the number of windows drastically compared with exhaustive search. Furthermore, our method reduces the processing time while maintaining recall compared with the state-of-the art method when the numbers of searched windows are same in Pascal VOC 2007 dataset.",

keywords = "adaptive window search, object detection, object map, real-time",

author = "Yuki Ono and Junaidi, {Abdul Raziz} and Tadahiro Kuroda",

year = "2013",

month = dec,

day = "1",

doi = "10.1109/ICIP.2013.6738678",

language = "English",

isbn = "9781479923410",

series = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

pages = "3293--3296",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

note = "2013 20th IEEE International Conference on Image Processing, ICIP 2013 ; Conference date: 15-09-2013 Through 18-09-2013",

}

TY - GEN

T1 - Adaptive window search using semantic texton forests for real-time object detection

AU - Ono, Yuki

AU - Junaidi, Abdul Raziz

AU - Kuroda, Tadahiro

PY - 2013/12/1

Y1 - 2013/12/1

N2 - We propose a new window search method to realize real-time object detection. Our method generates windows adaptively for objects' shapes and scales to detect various size objects. It also achieves real-time window search by using fast estimation of object's location based on existence probability of an object. Experiment results demonstrate that the proposed method reduces the number of windows drastically compared with exhaustive search. Furthermore, our method reduces the processing time while maintaining recall compared with the state-of-the art method when the numbers of searched windows are same in Pascal VOC 2007 dataset.

AB - We propose a new window search method to realize real-time object detection. Our method generates windows adaptively for objects' shapes and scales to detect various size objects. It also achieves real-time window search by using fast estimation of object's location based on existence probability of an object. Experiment results demonstrate that the proposed method reduces the number of windows drastically compared with exhaustive search. Furthermore, our method reduces the processing time while maintaining recall compared with the state-of-the art method when the numbers of searched windows are same in Pascal VOC 2007 dataset.

KW - adaptive window search

KW - object detection

KW - object map

KW - real-time

UR - http://www.scopus.com/inward/record.url?scp=84897766573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897766573&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738678

DO - 10.1109/ICIP.2013.6738678

M3 - Conference contribution

AN - SCOPUS:84897766573

SN - 9781479923410

T3 - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

SP - 3293

EP - 3296

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

Adaptive window search using semantic texton forests for real-time object detection

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this