Search
Abstract
Traffic monitoring from closed-circuit television (CCTV) cameras on embedded systems is the subject of the performed experiments. Solving this problem encounters difficulties related to the hardware limitations, and possible camera placement in various positions which affects the system performance. To satisfy the hardware requirements, vehicle detection is performed using a lightweight Convolutional Neural Network (CNN), named SqueezeDet, while, for tracking, the Simple Online and Realtime Tracking (SORT) algorithm is applied, allowing for real-time processing on an NVIDIA Jetson Tx2. To allow for adaptation of the system to the deployment environment, a procedure was implemented leading to generating labels in an unsupervised manner with the help of background modelling and the tracking algorithm. The acquired labels are further used for fine-tuning the model, resulting in a meaningful increase in the traffic estimation accuracy, and moreover, adding only minimal human effort to the process allows for further accuracy improvement. The proposed methods, and the results of experiments organised under real-world test conditions are presented in the paper.
Citations
-
6
CrossRef
-
0
Web of Science
-
7
Scopus
Authors (2)
Cite as
Full text
- Publication version
- Accepted or Published Version
- DOI:
- Digital Object Identifier (open in new tab) 10.3390/app10175763
- License
-
open in new tab
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
Applied Sciences-Basel
no. 10,
ISSN: 2076-3417 - Language:
- English
- Publication year:
- 2020
- Bibliographic description:
- Cygert S., Czyżewski A.: Vehicle Detection with Self-Training for Adaptative Video Processing Embedded Platform// Applied Sciences-Basel -Vol. 10,iss. 17 (2020), s.5763-
- DOI:
- Digital Object Identifier (open in new tab) 10.3390/app10175763
- Sources of funding:
- Verified by:
- Gdańsk University of Technology
seen 132 times