Fast and Accurate Real Time Pedestrian Detection Using Convolutional Neural Network

Hayder Albehadili; Laith Alzubaidi; Jabbar Rashed; Murtadha Al-Imam; Haider A. Alwzwazy

doi:10.25212/lfu.qzj.2.2.29

Authors

Hayder Albehadili Department of Software , Kadhum College for Islamic Science University, Iraq
Laith Alzubaidi Department of Systems and Applications, University of Information Technology & Communications Baghdad, Iraq
Jabbar Rashed Department of Electrical Engineering , Engineering College, University of Misan- Iraq
Murtadha Al-Imam Department of Software , Kadhum College for Islamic Science University, Iraq
Haider A. Alwzwazy Department of Mathematics, Mathematics College, University of Misan- Iraq

DOI:

https://doi.org/10.25212/lfu.qzj.2.2.29

Keywords:

Convolutional Neural Network, Pedestrian Detection, Multiscale input images

Abstract

Recently, pedestrian detection has become an important problem of interest. Our work primarily depends on robust and fast deep neural network architectures. This paper used very efficient and recent methods for pedestrian detection. Recently, pedestrian detection has become an important problem of interest. This paper suggests robust convolutional neural network models to solve this problem. We primarily evaluate accuracy and speed. Our work primarily depends on robust and fast deep neural network architectures; substantial changes to those models achieve results that are competitive with prior state-of-the-art methods. As a result, we outperformed all the prior state-of-the-art pedestrian detection methods. We also overtook other models that use extra information during testing and training. All experiments used three pedestrian detection challenge benchmarks: Caltech-USA, INRIA, and ETH.

Downloads

Download data is not yet available.

References

[1] P. Doll´ar, C. Wojek, B. Schiele, and P. Perona. Pedestrian detection: an evaluation of the state of the art. TPAMI, 34(4):743–761, 2012.

[2] P. Sermanet, K. Kavukcuoglu, S. C. Pedestrian, and Y. Le-Cun.Pedestrian detection with unsupervised multi-stage feature learning.CVPR, 2013.

[3] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection.In CVPR, 2005. 1, 2, 5, 7

[4] O. Tuzel, F. Porikli, and P. Meer. Pedestrian detection via classifcation on riemannian manifolds. IEEE Trans. PAMI, 30(10):1713–1727, Oct. 2008. 1, 2

[5] C. Mikolajczyk, C. Schmid, and A. Zisserman. Human detection based on a probabilistic assembly of robust part detectors. In ECCV, 2004.

[6] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part based models. In PAMI 2010. 1

[7] P. Dollar, Z. Tu, P. Perona, and S. Belongie, “Integral Channel Features” Proc. British Machine Vision Conf., 2009.

[ 8] M. Bertozzi, A. Broggi, M. Del Rose, M. Felisa, A. Rakotomamonjy and F. Suard “A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classifier” Proceedings of the 2007 IEEE Intelligent Transportation Systems Conference Seattle, WA, USA, Sept. 30 - Oct. 3, 2007

[ 9] Reecha P. Yadav, Vinuchackravarthy, Sunita P. Ugale “Implementation of Robust HOG-SVM based Pedestrian Classification” International Journal of Computer Applications (0975 – 8887) Volume 114 – No. 19, March 2015

[10] JiaolongXu, David Vazquez, Sebastian Ramos, Antonio M. Lopez , and Daniel Ponsa “Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers” CVPR 2013

[11] [1] J.Gall and V.Lempitsky. Class-specific hough forests for object detection. In CVPR, 2009.

[ 12] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks.In NIPS 2012: Neural Information Processing Systems. 1

[ 13] P. Luo, Y. Tian, X. Wang, and X. Tang. Switchable deep network for pedestrian detection.In CVPR, 2014. 2, 5

[14] 61. Yin, X.C., Yin, X., Huang, K.: Robust text detection in natural scene images. CoRR abs/1301.2628 (2013)

[15] Min Lin, Qiang Chen, and Shuicheng Yan “Network In Network” arXiv 1312.4400v3,4 Mar 2014

[16] Dan Cires¸an, Ueli Meier and JurgenSchmidhuber, “Multi-column Deep Neural Networks for Image Classification” CVPR 2012

[17] JulienMairal, PiotrKoniusz, ZaidHarchaoui, and CordeliaSchmid, “Convolutional Kernel Networks” arXiv 14 Nov 2014 .

[ 18] Ross Girshick Jeff Donahue Trevor Darrell Jitendra Malik “Rich feature hierarchies for accurate object detection and semantic segmentation” arXiv:1311.2524v5 [cs.CV] 22 Oct 2014

[19] Kaiming, He and Xiangyu, Zhang and Shaoqing, Ren and Jian Sun “Spatial pyramid pooling in deep convolutional networks for visual recognition” European Conference on Computer Vision, 2014

[20] Jan Hosang Mohamed Omran Rodrigo BenensonBerntSchiele, “Taking a Deeper Look at Pedestrians” arXiv:1501.05790v1 [cs.CV] 23 Jan 2015

[ 21] S. Paisitkriangkrai, C. Shen, and A. van den Hengel. Strengthening the effectiveness of pedestrian detection with spatially pooled features.In ECCV, 2014. 1, 2, 4, 7

[ 22] Rodrigo Benenson Mohamed Omran Jan HosangBerntSchiele, “Ten Years of Pedestrian Detection,What Have We Learned?”

[23] W. Ouyang and X. Wang.Joint deep learning for pedestrian detection.In ICCV, 2013. 2, 4, 5

[24] Hiroshi Fukui Takayoshi Yamashita, Yuji Yamauchi, Hironobu Fujiyoshi, Hiroshi Murase2 “Pedestrian Detection Based on Deep Convolutional Neural Network with Ensemble Inference Network”

[25] Xiaogang Chen, Pengxu Wei, Wei Ke, Qixiang Ye, Jianbin Jiao “Pedestrian Detection with Deep Convolutional Neural Network”

[26] X. Zeng, W. Ouyang, and X. Wang.Multi-stage contextual deep learning for pedestrian detection.In ICCV, 2013. 2

[27] Ross Girshick, “Fast R-CNN “arXiv preprint arXiv:1504.08083, 2015

Y. Jia, “Caffe: An open source convolutional architecture for fast feature embedding,” http://caffe.berkeleyvision.org/, 2013.