Abstract—Abstract—In this paper, we propose a method to detect
pedestrians in real time from road images obtained from a
black-box, which is a vehicle image recording camera, and to
automatically provide pedestrian appearance information to
the driver. To detect a pedestrian in the input road image, the
proposed method applies a pedestrian detector using a cascade
learning device based on the histogram of oriented gradients
(HOG) feature information. The pedestrian detector uses the
cascade learning device to extract feature information about
the pedestrian area based on the histogram description feature
information for pedestrian learning. The pedestrian detector
detects the candidate pedestrian areas, and the final pedestrian
area is detected through the pedestrian verification process.
The results of applying the proposed method to urban road
images indicate that the accuracy of detection is approximately
93%.
Index Terms—Pedestrian detection, HOG, ADAS, vehicle
black-box camera, cascade learning.
J. B. Kim is with the Department of Computer and Software, Sejong Cyber
University, Seoul, 04992, S. Korea (e-mail: jb.kim@sjcu.ac.rk).
Cite: Jong Bae Kim, "Pedestrian Detection Using HOG Feature-Based Cascade Classifier with Vehicle Black-Box Camera for Supporting Driver Assistance in Urban Road Environments," International Journal of Machine Learning and Computing vol. 10, no. 2, pp. 387-392, 2020.
Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).