Skip to main content
placeholder image

Reduced training of convolutional neural networks for pedestrian detection

Conference Paper


Download full-text (Open Access)

Abstract


  • Pedestrian detection is a vision task with many practical applications in video surveillance, road safety, autonomous driving and military. However, it is much more difficult compared to the detection of other visual objects, because of the tremendous variations in the inner region as well as the outer shape of the pedestrian pattern. In this paper, we propose a pedestrian detection approach that uses convolutional neural network (CNN) to differentiate pedestrian and non-pedestrian patterns. Among several advantages, the CNN integrates feature extraction and classification into one single, fully adaptive structure. It can extract two-dimensional features at increasing scales, and it is relatively tolerant to geometric, local distortions in the image. Although the CNN has good generalization performance, training CNN classifier is time-comsuming. Therefore, we present an efficient training

    approach for CNN. Through the experiments, we show that it is possible to design networks in a fraction of time taken by the standard learning approach.

Publication Date


  • 2009

Citation


  • Hoang Nguyen, G., Phung, S. & Bouzerdoum, A. (2009). Reduced training of convolutional neural networks for pedestrian detection. In H. Huynh, D. Tien & G. Shi (Eds.), International Conference on Information Technology and Applications (pp. 61-66). Hanoi, Vietnam: ICITA.

Scopus Eid


  • 2-s2.0-77953986372

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1807&context=infopapers

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/793

Has Global Citation Frequency


Start Page


  • 61

End Page


  • 66

Place Of Publication


  • Hanoi, Vietnam

Abstract


  • Pedestrian detection is a vision task with many practical applications in video surveillance, road safety, autonomous driving and military. However, it is much more difficult compared to the detection of other visual objects, because of the tremendous variations in the inner region as well as the outer shape of the pedestrian pattern. In this paper, we propose a pedestrian detection approach that uses convolutional neural network (CNN) to differentiate pedestrian and non-pedestrian patterns. Among several advantages, the CNN integrates feature extraction and classification into one single, fully adaptive structure. It can extract two-dimensional features at increasing scales, and it is relatively tolerant to geometric, local distortions in the image. Although the CNN has good generalization performance, training CNN classifier is time-comsuming. Therefore, we present an efficient training

    approach for CNN. Through the experiments, we show that it is possible to design networks in a fraction of time taken by the standard learning approach.

Publication Date


  • 2009

Citation


  • Hoang Nguyen, G., Phung, S. & Bouzerdoum, A. (2009). Reduced training of convolutional neural networks for pedestrian detection. In H. Huynh, D. Tien & G. Shi (Eds.), International Conference on Information Technology and Applications (pp. 61-66). Hanoi, Vietnam: ICITA.

Scopus Eid


  • 2-s2.0-77953986372

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1807&context=infopapers

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/793

Has Global Citation Frequency


Start Page


  • 61

End Page


  • 66

Place Of Publication


  • Hanoi, Vietnam