Next Article in Journal
Optical Planar Waveguide Sensor with Integrated Digitally-Printed Light Coupling-in and Readout Elements
Previous Article in Journal
An Embedded Sensor System for Real-Time Detecting 5-DOF Error Motions of Rotary Stages
Previous Article in Special Issue
Multi-Layer Feature Based Shoeprint Verification Algorithm for Camera Sensor Images
Open AccessArticle

Vehicle Counting in Video Sequences: An Incremental Subspace Learning Approach

1
Instituto Politecnico Nacional, ESIME Culhuacan, Mexico City 04440, Mexico
2
Group of Analysis, Security and Systems (GASS), Department of Software Engineering and Artificial Intelligence (DISIA), Faculty of Computer Science and Engineering, Office 431, Universidad Complutense de Madrid (UCM), Calle Profesor José García Santesmases, 9, Ciudad Universitaria, 28040 Madrid, Spain
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(13), 2848; https://doi.org/10.3390/s19132848
Received: 20 April 2019 / Revised: 31 May 2019 / Accepted: 19 June 2019 / Published: 27 June 2019
The counting of vehicles plays an important role in measuring the behavior patterns of traffic flow in cities, as streets and avenues can get crowded easily. To address this problem, some Intelligent Transport Systems (ITSs) have been implemented in order to count vehicles with already established video surveillance infrastructure. With this in mind, in this paper, we present an on-line learning methodology for counting vehicles in video sequences based on Incremental Principal Component Analysis (Incremental PCA). This incremental learning method allows us to identify the maximum variability (i.e., motion detection) between a previous block of frames and the actual one by using only the first projected eigenvector. Once the projected image is obtained, we apply dynamic thresholding to perform image binarization. Then, a series of post-processing steps are applied to enhance the binary image containing the objects in motion. Finally, we count the number of vehicles by implementing a virtual detection line in each of the road lanes. These lines determine the instants where the vehicles pass completely through them. Results show that our proposed methodology is able to count vehicles with 96.6% accuracy at 26 frames per second on average—dealing with both camera jitter and sudden illumination changes caused by the environment and the camera auto exposure. View Full-Text
Keywords: video processing; motion detection; incremental learning; Incremental PCA; traffic flow video processing; motion detection; incremental learning; Incremental PCA; traffic flow
Show Figures

Graphical abstract

MDPI and ACS Style

Rosas-Arias, L.; Portillo-Portillo, J.; Hernandez-Suarez, A.; Olivares-Mercado, J.; Sanchez-Perez, G.; Toscano-Medina, K.; Perez-Meana, H.; Sandoval Orozco, A.L.; García Villalba, L.J. Vehicle Counting in Video Sequences: An Incremental Subspace Learning Approach. Sensors 2019, 19, 2848.

AMA Style

Rosas-Arias L, Portillo-Portillo J, Hernandez-Suarez A, Olivares-Mercado J, Sanchez-Perez G, Toscano-Medina K, Perez-Meana H, Sandoval Orozco AL, García Villalba LJ. Vehicle Counting in Video Sequences: An Incremental Subspace Learning Approach. Sensors. 2019; 19(13):2848.

Chicago/Turabian Style

Rosas-Arias, Leonel; Portillo-Portillo, Jose; Hernandez-Suarez, Aldo; Olivares-Mercado, Jesus; Sanchez-Perez, Gabriel; Toscano-Medina, Karina; Perez-Meana, Hector; Sandoval Orozco, Ana L.; García Villalba, Luis J. 2019. "Vehicle Counting in Video Sequences: An Incremental Subspace Learning Approach" Sensors 19, no. 13: 2848.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop