A Tracking-by-Detection System for Pedestrian Tracking Using Deep Learning Technique and Color Information

Mai Thanh Nhat Truong and Sanghoon Kim
Volume: 15, No: 4, Page: 1017 ~ 1028, Year: 2019
10.3745/JIPS.04.0132
Keywords: Color Distribution, Convolutional Neural Network, Pedestrian Tracking, Tracking-by-Detection
Full Text:

Abstract
Pedestrian tracking is a particular object tracking problem and an important component in various visionbased applications, such as autonomous cars and surveillance systems. Following several years of development, pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surrounding environments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, which incorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames are localized using a CNN-based algorithm, and then detected pedestrians are assigned to their corresponding tracklets based on similarities between color distributions. The experimental results show that our system is able to overcome various difficulties to produce highly accurate tracking results.

Article Statistics
Multiple requests among the same broswer session are counted as one view (or download).
If you mouse over a chart, a box will show the data point's value.


Cite this article
IEEE Style
M. T. N. T. S. Kim, "A Tracking-by-Detection System for Pedestrian Tracking Using Deep Learning Technique and Color Information," Journal of Information Processing Systems, vol. 15, no. 4, pp. 1017~1028, 2019. DOI: 10.3745/JIPS.04.0132.

ACM Style
Mai Thanh Nhat Truong and Sanghoon Kim. 2019. A Tracking-by-Detection System for Pedestrian Tracking Using Deep Learning Technique and Color Information, Journal of Information Processing Systems, 15, 4, (2019), 1017~1028. DOI: 10.3745/JIPS.04.0132.