Automated Traffic Light System Based on Image Processing and Machine Learning Techniques
Abstract
Management of traffic
is an ever-growing concern and manual management of traffic especially in
metropolitan cities is strenuous task. In this paper, we present an automated
traffic light system based on image processing and machine learning techniques
to automatically identify the number of vehicles in each lane to set the green
signal time optimally to avoid large waiting time and also clear congestion at
faster rate. The YOLO darknet weights and labels are used with categorized
classes to identify and detect number of vehicles in the frame of the captured
image. The entire system is implemented using Raspberry pi 3B+ integrated with
rotatable webcam. The results show that this system is reliable as it produces
100% accuracy in producing the exact vehicle count and setting of green time
optimally to have a wait time no longer than 90 seconds.
Country : India
1 Arakatla Mamatha
Assistant Professor, Department of Electronics and Communication Engineering, Malla Reddy College of Engineering for Women, Hyderabad -500100, Telangana, India
Gul Shahzad; Heekwon Yang; Arbab
Waheed Ahmad; Chankil Lee, “Energy-Efficient Intelligent Street Lighting System
Using Traffic-Adaptive Control”, IEEE 2016, Volume: 16
Nicole Díaz, Jorge Guerra, Juan
Nicola, “Smart Traffic Light Control System”, IEEE 2018.
Khushi, “Smart control of Traffic
Light System using Image Processing”, International Conference on Current
Trends in Computer, Electrical, Electronics and Communication (ICCTCEEC-2017)
J. K. and A. Desai, ”IoT: Networking
Technologies and Research Challenges”, International Journal of Computer
Applications, vol. 154, no. 7, pp. 1-6, 2016.
Application of Raspberry Pi and PIR
Sensor for Monitoring of Smart Surveillance System”, International Journal of
Science and Research (IJSR), vol. 5, no. 2, pp. 736-737, 2016.
K. Choi, “Visible Light Communication
with Color and Brightness Control of RGB LEDs”, ETRI Journal, vol. 35, no. 5,
pp. 927-930, 2013.
P. N R, “Smart pi cam based Internet
of things for motion detection using Raspberry pi”, International Journal of
Engineering and Computer Science, 2016.
