3054 Detecting Pedestrians Using an Advanced Local Binary Pattern Histogram

Recorded Presentations from the meeting are now available. A folder icon represents that recordings are available for at least one presentation in the session.

Purchasing Recording Access: ITS America is now offering the option to purchase whole meeting or track access to the recordings if you were not a full registered attendee of the meeting. You may Purchase Full Meeting Access or you will have the option to purchase just individual track access. If you want to purchase multiple tracks, you will need to browse to a recording in each track to purchase that individual track. Full registered meeting attendees still have free access using their registration credentials. Please email papers@itsa.org if you need your registration credentials sent to you.

Session Number Key:
PL=Plenary Sessions  AM=Annual Meeting Sessions  ES=Executive Sessions
SS=Special Interest Sessions  TS=Technical and Scientific Sessions  IS=Interactive Sessions  PAITS=Pan American ITS Sessions  IBEC=Internatiol Benefit, Evaluation, and Cost Sessions 

*Ceremony and Plenary videos can be found at www.itsworldcongress.org

Monday, October 17, 2011: 4:10 PM
S330G (Orange County Convention Center )
Yunyun Cao , Staff Engineer, Tokyo R&D Center, Panasonic Corporation, Yokohmam City, Japan
Hirofumi Nishimura , Panasonic Corporation
Sugiri Pranata , Panasonic Singapore Laboratories Pte Ltd
Description of Paper:

Fast and simple for implementation, Local binary pattern (LBP), has shown its superiority in texture classification and face recognition, but weak in pedestrian recognition. An enhanced LBP Feature --- Weighted LBP Histogram, is proposed for robust pedestrian detection. In Weighted LBP Histogram, each bin value is calculated by accumulating the weight of each pixel’s LBP code which belongs to this bin, whereas the weight is defined as the Sum of Absolute Difference (SAD) of the centre pixel and its surrounding pixels. The experimental results show its effectiveness on alleviation of noise and enhancement of signal-to-noise ratio. Utilizing the proposed LBP feature, our pedestrian detection system achieves a high performance than the benchmark method HOG on several benchmark datasets.

Full Paper: