Pedestrian-motorcycle binary classification using data augmentation and convolutional neural networks
College
Gokongwei College of Engineering
Department/Unit
Electronics And Communications Engg
Document Type
Conference Proceeding
Source Title
Advances in Intelligent Systems and Computing
Volume
997
First Page
725
Last Page
737
Publication Date
1-1-2019
Abstract
One common problem in vehicle and pedestrian detection algorithms is the mis-classification of motorcycle riders as pedestrians. This paper focused on a binary classification technique using convolutional neural networks for pedestrian and motorcycle riders in different road context locations. The study also includes a data augmentation technique to address the un-balanced number of training images for a machine learning algorithm. This problem in un-balanced data sets usually cause a prediction bias, in which the prediction for a learned data set usually favors the class with more image representations. Using four data sets with differing road context (DS0, DS3-1, DS4-3, and DS4-3), the binary classification between pedestrian and motorcycle riders achieved good results. In DS0, training accuracy is 96.96% while validation accuracy is 81.52%. In DS3-1, training accuracy is 93.17% while validation accuracy is 86.58%. In DS4-1, training accuracy is 94.42% while validation accuracy is 97.00%. In DS4-3, training accuracy is 95.94% while validation accuracy is 88.59%. © 2019, Springer Nature Switzerland AG.
html
Digitial Object Identifier (DOI)
10.1007/978-3-030-22871-2_50
Recommended Citation
Billones, R. C., Bandala, A. A., Gan Lim, L. A., Sybingco, E., Fillone, A. M., & Dadios, E. P. (2019). Pedestrian-motorcycle binary classification using data augmentation and convolutional neural networks. Advances in Intelligent Systems and Computing, 997, 725-737. https://doi.org/10.1007/978-3-030-22871-2_50
Disciplines
Computer Sciences
Keywords
Neural networks (Computer science); Human activity recognition; Pedestrians; Image processing
Upload File
wf_yes