Title:
SUBJECT DETECTION DEVICE
Document Type and Number:
WIPO Patent Application WO/2014/084218
Kind Code:
A1
Abstract:
The present invention relates to a subject detection device. A subject identification unit is an identifier in which a feature data group representing an image feature amount is the input and information indicating whether or not a subject (crossing pedestrian) is present is the output, the identifier being generated by machine learning. The identifier produces a feature data group from an image of at least one subregion (82) (non-masked region (102)) selected according to the type of subject from a plurality of subregions (82) constituting each of the learning sample images used for machine learning, and inputs the feature data group.
Inventors:
YAGI YASUSHI (JP)
MAKIHARA YASUSHI (JP)
HUA CHUN SHENG (JP)
MIYAGAWA KEISUKE (JP)
IWASAKI SHUN (JP)
MAKIHARA YASUSHI (JP)
HUA CHUN SHENG (JP)
MIYAGAWA KEISUKE (JP)
IWASAKI SHUN (JP)
Application Number:
PCT/JP2013/081808
Publication Date:
June 05, 2014
Filing Date:
November 26, 2013
Export Citation:
Assignee:
UNIV OSAKA (JP)
International Classes:
G06T7/00; G08G1/16; H04N7/18
Domestic Patent References:
WO2012124000A1 | 2012-09-20 | |||
WO2011161924A1 | 2011-12-29 |
Foreign References:
JP2012185684A | 2012-09-27 | |||
JP2011165170A | 2011-08-25 |
Other References:
HIDEFUMI YOSHIDA ET AL.: "A study on a method for stable pedestrian detection against pose changes with generative learning", IEICE TECHNICAL REPORT, vol. 111, no. 49, 12 May 2011 (2011-05-12), pages 127 - 132
Attorney, Agent or Firm:
CHIBA Yoshihiro et al. (JP)
Takehiro Chiba (JP)
Takehiro Chiba (JP)
Download PDF: