Performance evaluation of support vector machine and convolutional neural network algorithms in real-time vehicle type and color classification

Abstract

Intelligent traffic management systems needs to obtain information about traffic with different sensors to control the traffic flow properly. Traffic surveillance videos are very actively used for this purpose. In this paper, we firstly create a vehicle dataset from an uncalibrated camera. Then, we test Tiny-YOLO real-time object detection and classification system and SVM classifier on our dataset and well-known public BIT-Vehicle dataset in terms of recall, precision, and intersection over union performance metrics. Experimental results show that two methods can be used to classify real time streaming traffic video data.

Citing

Please use the following .bib entry to cite this article:

@article{sentas2020performance,
  title={Performance evaluation of support vector machine and convolutional neural network algorithms in real-time vehicle type and color classification},
  author={{\c{S}}enta{\c{s}}, Ali and Tashiev, {\.I}sabek and K{\"u}{\c{c}}{\"u}kayvaz, Fatmanur and Kul, Seda and Eken, S{\"u}leyman and Sayar, Ahmet and Becerikli, Ya{\c{s}}ar},
  journal={Evolutionary Intelligence},
  volume={13},
  number={1},
  pages={83--91},
  year={2020},
  publisher={Springer}
}