This paper presents a novel pedestrian detection method based on the use of a convolutional neural network (CNN) classifier. Our method achieves high accuracy by automatically optimizing the feature representation to the detection task and regularizing the neural network. We evaluate the proposed method on a difficult database containing pedestrians in a city environment with no restrictions on pose, action, background and lighting conditions. The false positive rate (FPR) of the proposed CNN classifier is less than 1/5-th of the FPR of a support vector machine (SVM) classifier using Haar-wavelet features when the detection rate is 90%. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN, confirming the importance of automatically optimized features. The computational demand of the CNN classifier is, however, more than an order of magnitude lower than that of the SVM, irrespective of the type of features used.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pedestrian detection with convolutional neural networks


    Contributors:
    Szarvas, M. (author) / Yoshizawa, A. (author) / Yamamoto, M. (author) / Ogata, J. (author)


    Publication date :

    2005-01-01


    Size :

    1135642 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Pedestrian Detection with Convolutional Neural Networks

    Szarvas, M. / Yoshizawa, A. / Yamamoto, M. et al. | British Library Conference Proceedings | 2005


    Pedestrian Detection with Deep Convolutional Neural Network

    Chen, Xiaogang / Wei, Pengxu / Ke, Wei et al. | British Library Conference Proceedings | 2015


    Real-time Pedestrian Detection Using LIDAR and Convolutional Neural Networks

    Szarvas, M. / Sakai, U. / Ogata, J. | British Library Conference Proceedings | 2006


    Multi‐receptive field graph convolutional neural networks for pedestrian detection

    Shen, Chao / Zhao, Xiangmo / Fan, Xing et al. | Wiley | 2019

    Free access

    Multi-receptive field graph convolutional neural networks for pedestrian detection

    Shen, Chao / Zhao, Xiangmo / Fan, Xing et al. | IET | 2019

    Free access