Pedestrian Detection in Visual Images Using Combination of HOG and HOM Features

  • Kok Wei Chee
  • Soo Siang TeohEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 547)


The ability to detect pedestrian is an important feature in autonomous driving vehicle and advanced driver assistance system (ADAS). The detection can be very challenging due to the complex scene and bad visibility on the road. In addition, it is difficult to achieve high accuracy and good speed performance at the same time due to more processing power is required to increase the accuracy. To address this constraint, we propose a framework to detect pedestrian through fusion of image gradient and magnitude properties and the process is speed up with integral image implementation. Both image gradient and magnitude properties were extracted using Histogram of Oriented Gradient (HOG) and Histogram of Magnitude (HOM) features. From the experiment results, we showed that the combination of HOG and HOM features can achieve 99.0% accuracy compared to HOG (98.6%) or HOM (95.5%) features when they are used independently.


Pedestrian detection Feature extraction Pattern recognition Driver assistance system 



This research was supported by Universiti Sains Malaysia Research University Grant (RUI) under project no.1001/PELECT/8014053.


  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
  2. 2.
    Cao, Y., Pranata, S., Yasugi, M., Niu, N., Nishimura, N.: Stagged multi-scale LBP for pedestrian detection. In: 19th IEEE International Conference on Image Processing, pp. 449–452 (2012)Google Scholar
  3. 3.
    Elmikaty, M., Stathaki, T., Kimber, P., Giannarou, S.: A novel two-level shape descriptor for pedestrian detection. In: Sensor Signal Processing for Defence (SSPD 2012), pp. 1–5 (2012)Google Scholar
  4. 4.
    Sun, W., Zhu, S., Cheng, Y.: Pedestrian detection via fusing LBP and GSS features. In: 36th Chinese Control Conference (CCC), Dalian, pp. 11072–11076 (2017)Google Scholar
  5. 5.
    Das, A.J., Saikia, N.: Pedestrian detection using dense LDB descriptor combined with HOG. In: International Conference on Information Technology (InCITe), Noida, pp. 299–304 (2016)Google Scholar
  6. 6.
    Cao, Y., Pang, J., Li, X.: Pedestrian detection inspired by appearance constancy and shape symmetry. IEEE Trans. Image Process. 25(12), 5538–5551 (2016)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Huang, C., Huang, J.: A Fast HOG Descriptor Using Lookup Table and Integral Image. CoRR, abs/1703.06256 (2017)Google Scholar
  8. 8.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, pp. I-511–I-518 (2001)Google Scholar
  9. 9.
    Lai, C.Q., Teoh, S.S.: An efficient method of HOG feature extraction using selective histogram bin and PCA feature reduction. Adv. Electr. Comput. Eng. 16(4), 101–108 (2016)CrossRefGoogle Scholar
  10. 10.
    Weixing, L., Haijun, S., Feng, P., Qi, G., Bin, Q.: A fast pedestrian detection via modified HOG feature. In: 34th Chinese Control Conference (CCC), Hangzhou, pp. 3870–3873 (2015)Google Scholar
  11. 11.
    Enzweiler, M., Gavrila, D.M.: Monocular pedestrian detection: survey and experiments. IEEE Trans. Pattern Anal. Mach. Intell. 31(12), 2179–2195 (2009)CrossRefGoogle Scholar
  12. 12.
    CSIRO-Australia. Data61 Pedestrian Dataset. Accessed on 12 Dec 2017

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Electrical and Electronic EngineeringUniversiti Sains Malaysia, USM Engineering CampusNibong TebalMalaysia

Personalised recommendations