Real-Time Traffic Observation and Analysis System
Korubilli Laxmi Swaroopa
, Lingoji Ramya Sri , Madhuri Agrawal
Computer Vision, Convolutional Neural Network, Object Detection, Object Tracking, You Only Look Once (YOLO), ByteTrack
This paper introduces a real-time traffic observation and analysis system empowered by the You Only Look Once (YOLO) object detection model and the Bytetrack algorithm for vehicle tracking. The system is designed to monitor traffic parameters such as vehicle speed, traffic flow rate, and congestion levels using video footage of roadways. YOLO is utilized for real-time object detection. Bytetrack employs the Kalman filter to predict future vehicle positions and association techniques for mapping vehicles across successive frames, facilitating the assignment of tracking IDs. Leveraging the YOLO model from the Ultralytics organization, the system provides accurate and efficient traffic monitoring and analysis, enhancing decision-making for urban traffic management. When provided with a video of a road to the system the system gives as output a video which includes the inputted footage with added information. It marks each identified vehicle with a square. It also displays the count of each vehicle on top of the square along with the calculated speed of each vehicle. The system will use the computer vision model YOLO ( You Only Look Once ) for vehicle detection. The famous object detection model YOLO is a single convolutional neural network whose implementation comes pre-trained with over 80 objects. The YOLO model can identify all the objects involved in the input image by passing the image through a single convolutional neural network only once. The model does not identify the potential object locations using a neural network and then uses another neural network to detect if an object is present in all the predicted areas. So YOLO is very quick compared to other computer vision models. The effective architecture of the model allows us to perform real-time detections. So we are using the YOLO model for vehicle detection in our project. The system then uses the object tracking algorithm ByteTrack to track the detected vehicles. The output contains the total number of vehicles identified in the footage, the count of the number of vehicles entering and leaving the road, the traffic flow rate, and the average speed of the traffic. Therefore the system presents us with a set of observations which would be beneficial in getting a basic understanding of the traffic conditions of the road.
"Real-Time Traffic Observation and Analysis System", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.9, Issue 6, page no.183 - 189, June-2024, Available :https://ijsdr.org/papers/IJSDR2406019.pdf
Volume 9
Issue 6,
June-2024
Pages : 183 - 189
Paper Reg. ID: IJSDR_211588
Published Paper Id: IJSDR2406019
Downloads: 000347107
Research Area: Computer Science & Technology
Country: Hyderabad, Telangana, India
DOI: https://doi.org/10.5281/zenodo.11547315
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
