Automatic Data Labeling by Neural Networks for the Counting of Objects in Videos
Procedia Computer Science. Vol.149: ICTE in Transportation and Logistics 2018 (ICTE 2018) 2019
Ivars Namatēvs, Kaspars Sudars, Inese Poļaka

The paper proposes an efficient method for training a neural network to count moving objects in a video, while another neural network concurrently prepares a labeled dataset for the first one. The detection, tracking, and counting of objects is crucial for effective Intelligence Transportation Systems (ITS), which should reduce congestion and recognize traffic offenders on highways and in urban areas. Creation of labeled data for training a neural network is one of the essential prerequisites for successful application of supervised machine learning. In this paper, the experimental results of the automatic labeling and counting of vehicles under real world conditions are shown. The method shows that by using the Convolutional Neural Network (CNN), the computing power and speed-up time for training a Recurrent Neural Network (RNN) with a Long Short-Term Memory (LSTM) cell for counting moving objects can be decreased.


Keywords
Object Detection, CNN, IOU
DOI
10.1016/j.procs.2019.01.118
Hyperlink
https://www.sciencedirect.com/science/article/pii/S1877050919301255

Namatēvs, I., Sudars, K., Poļaka, I. Automatic Data Labeling by Neural Networks for the Counting of Objects in Videos. In: Procedia Computer Science. Vol.149: ICTE in Transportation and Logistics 2018 (ICTE 2018), Lithuania, Klaipeda, 1-1 January, 2019. Amsterdam: Elsevier B.V., 2019, pp.151-158. ISSN 1877-0509. Available from: doi:10.1016/j.procs.2019.01.118

Publication language
English (en)
The Scientific Library of the Riga Technical University.
E-mail: uzzinas@rtu.lv; Phone: +371 28399196