We propose a novel learning strategy called Global-Local Motion Pattern Classification (GLMPC) to localize pedestrian-like motion patterns in videos. Instead of modeling such patterns as a single class that alone can lead to high intra-class variability, three meaningful partitions are considered - left, right and frontal motion. An AdaBoost classifier based on the most discriminative eigenflow weak classifiers is learnt for each of these subsets separately. Furthermore, a linear three-class SVM classifier is trained to estimate the global motion direction. To detect pedestrians in a given image sequence, the candidate optical flow sub-windows are tested by estimating the global motion direction followed by feeding to the matched AdaBoost classifier. The comparison with two baseline algorithms including the degenerate case of a single motion class shows an improvement of 37% in false positive rate.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pedestrian Detection Using Global-Local Motion Patterns


    Contributors:
    Yagi, Yasushi (editor) / Kang, Sing Bing (editor) / Kweon, In So (editor) / Zha, Hongbin (editor) / Goel, Dhiraj (author) / Chen, Tsuhan (author)

    Conference:

    Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007


    Published in:

    Computer Vision – ACCV 2007 ; Chapter : 20 ; 220-229


    Publication date :

    2007-01-01


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Can appearance patterns improve pedestrian detection?

    Ohn-Bar, Eshed / Trivedi, Mohan M. | IEEE | 2015


    Predictive Modeling of Pedestrian Motion Patterns with Bayesian Nonparametrics

    Chen, Yufan / Liu, Miao / Liu, Shih-Yuan et al. | AIAA | 2016


    Pedestrian Detection via Periodic Motion Analysis

    Ran, Y. / Weiss, I. / Zheng, Q. et al. | British Library Online Contents | 2007


    Pedestrian detection from non-smooth motion

    Kilicarslan, Mehmet / Zheng, Jiang Yu / Algarni, Aied | IEEE | 2015