id: 05981003
dt: a
an: 05981003
au: Ma, Yingdong; Chen, Xiankai; Chen, George
ti: Pedestrian detection and tracking using HOG and Oriented LBP features.
so: Altman, Erik (ed.) et al., Network and parallel computing. 8th IFIP
    international conference, NPC 2011, Changsha, China, October 21‒23,
    2011. Proceedings. Berlin: Springer (ISBN 978-3-642-24402-5/pbk).
    Lecture Notes in Computer Science 6985, 176-184 (2011).
py: 2011
pu: Berlin: Springer
la: EN
cc: 
ut: pedestrian detection; support vector machine; oriented local binary
    pattern; histograms of oriented gradient
ci: 
li: doi:10.1007/978-3-642-24403-2_15
ab: Summary: During the last decade, various successful human detection methods
    have been developed. However, most of these methods focus on finding
    powerful features or classifiers to obtain high detection rate. In this
    work we introduce a pedestrian detection and tracking system to extract
    and track human objectives using an on board monocular camera. The
    system is composed of three stages. A pedestrian detector, which is
    based on the non-overlap HOG feature and an Oriented LBP feature, is
    applied to find possible locations of humans. Then an object validation
    step verifies detection results and rejects false positives by using a
    temporal coherence condition. Finally, Kalman filtering is used to
    track detected pedestrians. For a $320 \times 240$ image, the
    implementation of the proposed system runs at about 14 frames/second,
    while maintaining an human detection rate similar to existing methods.
rv: