|
License Agreement on scientific materials use.
|
SYSTEM OF ANALYSIS OF ROAD TRAFFIC ONSITE (IN LOGISTICS) BASED ON IMAGE RECOGNITION FROM CCTV CAMERAS
|
Kirill Ivanovich Morev
Southern Federal University in Taganrog
Aleksandr Nikolaevich Tselykh
Southern Federal University in Taganrog
|
|
Submitted:
March 7, 2017
|
|
Abstract.
The article is devoted to the process of creating a system for recording automobile traffic on the protected object. The system is based on the analysis of images coming from the CCTV camera. By analyzing video fragments the system counts the number of the vehicles entering and leaving the protected area. In the process of implementation of the technical task the program for video analysis was written in the Python language, problems of preparing videos to machine processing were solved, the place for the camera-detector was selected.
|
Key words and phrases:
компьютерное зрение
распознавание образов
автомобильный трафик
видеонаблюдение
система анализа видеоизображения
computer vision
images recognition
road traffic
CCTV
video analysis system
|
|
Open
the whole article in PDF format. Free PDF-files viewer can be downloaded here.
|
|
References:
- Вазаев А. В., Носков В. П., Рубцов И. В., Цариченко С. Г., Ярошевич Н. В. Распознавание объектов и типов опорной поверхности по данным комплексированной системы технического зрения // Известия Южного федерального университета. Технические науки. 2016. № 2. С. 127-139.
- Юревич Е. И. Основы робототехники: уч. пособие для студ. вуз. 2-е изд. СПб, 2007. 203 с.
- Bay H., Tuytelaars T., Van Gool L. SURF: Speeded Up Robust Features // Computer Vision and Image Understanding. 2008. Vol. 110. P. 346-359.
- Bechtel W. The Cardinal Mercier Lectures at the Catholic University of Louvain. Lecture 2: An Exemplar Neural Mechanism: The Brain’s Visual Processing System [Электронный ресурс]. Leuven, 2003. URL: http://mechanism.ucsd.edu/~bill/ research/mercier/2ndlecture.pdf (дата обращения: 15.02.2017).
- Ciresan D. C., Meier U., Masci J., Schmidhuber J. Multi-Column Deep Neural Network for Traffic Sign Classification // Neural Networks. 2012. Vol. 34. P. 333-338.
|
