Bus passenger flow statistics algorithm based on deep learning
- PDF / 3,848,549 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 49 Downloads / 215 Views
Bus passenger flow statistics algorithm based on deep learning Yong Zhang 1,2,3 & Wentao Tu 1 & Kairui Chen 4 & C. H. Wu 5 & Li Li 6 C. Y. Chan 8
7
& W. H. Ip &
Received: 10 February 2020 / Revised: 4 July 2020 / Accepted: 28 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Bus passenger flow statistics can be used to improve passenger travelling experience and reduce trip delay, this is very important for intelligent transportation. In this paper, a bus passenger flow statistics algorithm based on SSD (Single Shot MultiBox Detector) and Kalman filter is proposed to obtain passenger flow statistics from surveillance cameras on the buses. The method modifies the SSD model to a two-class model and trains the twoclass SSD model using the bus dataset first, then the model is used to detect the position of the passengers in each frame and are tracked with the Kalman filter. Finally, according to the passenger trajectory, the traffic statistics of passenger getting on and off will be generated. The results of some conducted experiments show that the proposed bus passenger flow statistics algorithm is more accurate and robust than traditional methods. Keywords Computer vision . Deep learning . Bus passenger flow statistics . SSD algorithm
* Li Li [email protected]
1
ATR Key Laboratory of National Defence Technology, Shenzhen University, Shenzhen 518060, China
2
Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China
3
Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ), Shenzhen University, Shenzhen 518060, China
4
School of Science and Technology, Georgia Gwinnett College, Lawrenceville, GA 30043, USA
5
Department of Supply Chain and Information Management, Hang Seng University of Hong Kong, Hong Kong 999077, China
6
Shenzhen Institute of Information Technology, Shenzhen 518172, China
7
College of Engineering, University of Saskatchewan, Saskatoon, Canada
8
Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, China
Multimedia Tools and Applications
With the popularization of vehicle networking technology and the improvement of public transportation infrastructure, the intelligent public transportation system has been gradually improved. Whether you are an ordinary passenger, the real-time bus information is important. The bus information such as location, traffic conditions and speed can be ignored for you, but you may care the spare seats and the passenger density in the bus. The passengers may wait for a bus for a long time, but the bus is overloaded. It is an inconvenience and unpleasantness for the waiting passenger. There are many difficulties in bus passenger flow statistics, such as the passenger dress, luggage, weather changes, light changes, etc. all of these will affect the algorithm to identify passengers. In the literature of Ravi et al. [1], a target statistical algorithm for region segmentation is proposed, which uses ba
Data Loading...
