E3S Web of Conferences 309, 01099 (2021) https://doi.org/10.

1051/e3sconf/202130901099
ICMED 2021

New Directions in Traffic Control Analysis through Video

Surveillance
R.V.S. Lalitha1,*, Divya Lalita Sri Jalligampala2, Kayiram Kavitha3, Shaik Vahida4, Goli Rajasekhar5
1,2,4 Department
of C.S.E, Aditya College of Engineering & Technology, Surampalem.
3Departmentof C.S.E, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad,
5Ivy Comptech Pvt ltd., Hyderabad.

Abstract: Traffic management is an increasing problem in both cities and sub urban areas. Authority
people involved in traffic management system spend much of time in controlling traffic at junctions. With
the advances in technology, monitoring traffic through image processing and video surveillance techniques
became the researchers’ attention. These techniques help us in controlling traffic as well as to identification
of kamikaze drivers and speed violators. The key focus of this research is to do traffic analysis using video
surveillance to detect speedy drivers. A wide range of traffic parameters such as flow of traffic, speed of
vehicles and vehicle registration number are the major components involved in this research. In this paper,
traffic analysis is carried out based on streaming video data with YOLO tool. In this paper an eco system is
developed for object detection, vehicle number detection and the speed of the vehicle using computer vision
algorithms. With the application tool developed, traffic control authority people can warn the speedy drivers
on the fly.
Keywords: YOLO tool, Object detection, Video streaming, Classification, ALPR.

1 Introduction stationary cameras for testing at intersections [2, 16,

17,18]. Fedorov, A addressed the problem of traffic flow
Video surveillance acts as a remote eye for traffic estimation using video surveillance. The vehicle count
authority people. This includes observing vehicles on and classification is analyzed using Faster R-CNN by
roads moving with high speed. By viewing selected
taking 982 video frames with 60,000 objets [3,7]. K. K.
images at appropriate time helps in reducing accidents
and to superimpose safety regulations. Vehicle detection Santhosh surveyed about anomaly detection in
is the most budding topic in urban traffic analysis. In Intelligent Traffic System. Timely detection of traffic
order to reduce accidents, reckless drivers are to be violations helps in reducing accidents. The study
identified. Video surveillance grabbed the attention of includes methods, datasets using computer vision [4,
researchers to articulate image processing with artificial 5,15]. J, J., R, B proposed novel approach for automatic
intelligence capabilities using computer vision [19]. vehicle management through video surveillance. Object
Traffic Control Analysis with Video Surveillance is
using computer vision algorithms are best suited for this
developed using Image processing techniques in deep
learning. Video data is used to analyse the parameters of purpose. Automatic vehicle counting is done with blob
vehicle like vehicle number, vehicle speed and vehicle analysis and background subtraction. Detection of
categorization. This gives an elaborate way identifying objects is analyzed using boundary block detection
vehicle number, calculating its speed and the type of the algorithms[6]. M. Naphade discussed intelligent video
vehicle. analysis using AI. 5 Tracks are evaluated using
promising AI and ML techniques in real world [8-14].
2 Related Work The bibliometric analysis is performed using search key
TITLE-ABS-KEY (traffic AND control AND analysis
F. Mehboob worked on autonomous vehicle detection on
AND using AND video AND surveillance) on 8-8-
roads using videos. Fuzzy logic analysis is used to
2021 from www.scopus.com and the following results
decide traffic conditions and to take timely actions. For
are retrieved during 1985 and 2021.
analysis both urban and motorways are considered [1].
W. AL OKAISHI proposed a real time traffic analysis
for detection background subtraction method and
classification using CNN. The work is carried out using

*
Corresponding author: [email protected]

© The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0
(http://creativecommons.org/licenses/by/4.0/).
E3S Web of Conferences 309, 01099 (2021) https://doi.org/10.1051/e3sconf/202130901099
ICMED 2021

Fig.1(a). Documents by author

The total number of documents retrieved is 364 and the

authors mentioned in Fig.1.(i). published 4 documents in
this research area. As per the stats Al-Salih Al-Sudani, Fig.2. Traffic analysis through Video surveillance
A.A.M., Cheng, H.Y., Harrer, M. Michalopoulos, P.G.
Automatic License Plate Recognition (ALPR) is a
and Wang, Y. published 4 documents and most of the
technology used for number plate recognition. This is
authors published more than 2 documents. The topic is mostly used by Police department at toll gates and road
published by several reputed conferences and journals as junctions. This uses the principle of Optical Character
depicted in Fig.1(b) Recognition on vehicles to detect vehicle registration
numbers. Object detection involves recognition of an
object in the real world. It includes three stages,
recognition, localization and detection. These are very
useful for driver assistance based applications.

a) Video capturing
The video is taken for duration of 1 min and vehicle
detection is performed for a test run. If the camera
illusion and light is more the objects will be more
correctly identified. The object detection is programmed
Fig.1(b). Articles published in various reputed journals using OpenCV. The video in mp4 format is submitted to
and conferences. VideoCapture() method. The objects nearby are
classified correctly with confidence of 69% and the
vehicle which is far is with with 55% confidence as
3 Traffic analysis through Video shown in Fig.3.
Surveillance
Traffic Control and Analysis System is a dynamic
system which analyses the video stream based on the
current traffic and also provides traffic rate and
classification to clear the traffic in different junctions.
By video streaming, the required parameters are
extracted using image processing techniques in deep
learning. In this system, the detection of vehicles on
roads is done using OpenCV and the classification of the
vehicles to clear traffic is analyzed using YOLO model.
The recognition of License Number is through open
ALPR. Finally vehicle speed is detected in real time. The
various stages involved are depicted in Fig.2. In this
research work, the traffic analysis through video
surveillance is mainly performed in three phases: Object Fig.3. Vehicle Detection in video Stream
detection using YOLO model, Number plate recognition
b) Vehicle classification
and Computing speed of the vehicle.
The purpose of this research is to detect the speedy and
reckless drivers [22, 23]. Once the object detection
process is completed through video capturing, the
vehicle classification takes place to keep track of type of

2
E3S Web of Conferences 309, 01099 (2021) https://doi.org/10.1051/e3sconf/202130901099
ICMED 2021

vehicles detected. The image database is populated and

vehicle classification is performed using YOLOv3
model. The objects are detected from video using
detectObjectsFromVideo() method from
VideoObjectDetection package. The classification of
vehicles and their accuracies are also displayed in Fig.4.

Fig.7. Vehicles speeds and their numbers

d) A dashboard is created using python and MySQL
database is used to store traffic parameters. The
Authority can make use of this interface to monitor
traffic statistics day wise and week wise. If a vehicle is
detected with the speed more than the required, then it
can be tracked with number plate detected (Fig.8 and
Fig.4. Vehicle Classification in video Fig.9). The people of Traffic control authority can access
c) Traffic rate analysis through video this information through web to keep track of updates.

In this, two components are analyzed. One speed and the

other one is number plate detection to warn speed
drivers. The speed of the vehicle is calculated based on
time of entering into zone and time of leaving. Fig.5.
tells about the sequence of actions performed in
analyzing traffic count, speed ad number plate detection.
Fig.6. exhibit traffic rate analysis using video streaming.

Fig.8. Traffic Analysis detection for speed violators.

The dash board is accessible only to the traffic authority.
It requires login credentials to monitor traffic data, speed
Fig.5. Traffic count, Registration number & speed violators and to classify vehicles on the road. Streaming
of video data gives better result than with the magnetic
sensors detection. This eco system helps in assessing
categorization of vehicle and also the registration
information by tracking the details on the number plate.

Fig.6. Traffic rate in video

OpenALPR open source library is used to detect number
plate detection (Fig.7). The speed and license plate Fig.9. Traffic analysis in a week.
number is displayed.

3
E3S Web of Conferences 309, 01099 (2021) https://doi.org/10.1051/e3sconf/202130901099
ICMED 2021

For visual analytics video surveillance plays key role. networked vehicle surveillance in ITS: A survey.
The streaming of data from video [24] is a complex IEEE Transactions on Intelligent Transportation
method but the conversion of traffic video contents is Systems 18, 1 (2017), 25--48.
very much required in detection of objects. The proposed 6. J, J., R, B., & Al-Heety, A. (2021). Moving vehicle
approach outcome gives promising results in conveying detection from video sequences for Traffic
emergency information to the speedy drivers. Intelligent Surveillance System. ITEGAM-JETIA, 7(27), 41-
monitoring using video surveillance at highways alerts 48.
public in maintaining regular speed. Constantly viewing
7. R. Babitha Lincy, Gayathri, R. Optimally
video and observing traffic rate is replaced with the eco
configured convolutional neural network for Tamil
system developed in this paper. Web approach [25, 26]
Handwritten Character Recognition by improved
drives traffic authority to monitor historic data as well as
lion optimization model. Multimedia Tools and
current day statistics.
Application (2020).
Conclusion 8. M. Naphade, S. Wang, D. C. Anastasiu, Z. Tang,
M.- C. Chang, X. Yang, Y. Yao, L. Zheng, P.
Video surveillance is basically beneficial to the Chakraborty, A. Sharma, Q. Feng, V. Ablavsky, and
public transportation system. Traffic police can S. Sclaroff, “The 5th ai city challenge,” in The IEEE
conveniently keep track of traffic updates from the Conference CVPR Workshops, June 2021.
framework developed. The adaptation of intelligent 9. Shuai Bai, Zhedong Zheng, Xiaohan Wang, Junyang
video surveillance at various junctions alerts people in Lin, Zhu Zhang, Chang Zhou, Hongxia Yang, and
maintaining regular speed of their vehicles. Video Yi Yang. Connecting language and vision for
surveillance techniques in new directions have natural language-based vehicle retrieval. In CVPR
exponential growth because of their ability in detection Workshop, 2021.
and investigation of number plates. Further extension of
this system will also resolve the problem of finding the 10. Jingyuan Chen, Guanchen Ding, Yuchen Yang,
theft of vehicles. This type of research on video Wenwei Han, Kangmin Xu, Tianyi ao, Zhe Zhang,
surveillance can serve multiple functions like remote Wanping Ouyang, Hao Cai, and Zhenzhong Chen.
monitoring, tracking, traffic estimation in both public Dual modality vehicle anomaly detection via
and private sectors. bidirectional-trajectory tracing. In CVPR Workshop,
2021
11. Keval Doshi and Yasin Yilmaz. An efficient
approach for anomaly detection in traffic videos. In
Acknowledgements CVPR Workshop, 2021.
Authors would like to acknowledge the efforts of K. S.D 12. Qi Feng, Vitaly Ablavsky, and Stan Sclaroff.
Shankar, Akshat jain and S.Anusai Reddy in taking CityFlow-NL: Tracking and retrieval of vehicles at
videos of traffic data and analyzing them during the city scaleby natural language descriptions.
progress of this research work. arXiv:2101.04741, 2021.
13. Marta Fernandez, Paula Moral, Alvaro Garcia-
Martin, and Jose M. Martinez. Vehicle re-
identification based on ensembling deep learning
References features including a synthetic training dataset,
orientation and background features, and camera
1. F. Mehboob, M. Abbas and R. Jiang, "Traffic event verification. In CVPR Workshop, 2021.
detection from road surveillance vide os based on 14. Derek Gloudemans and Daniel B. Work. Fast
fuzzy logic," SAI, 2016, vehicle turning-movement counting using
doi: 10.1109/SAI.2016.7555981. localization-based tracking. In CVPR Workshop,
2. W. Al Okaishi, A. Zaarane, I. Slimani, I. Atouf and 2021
M. Benrabh, "A Traffic Surveillance System in 15. Luna E, San Miguel JC, Ortego D, Martínez JM.
Real-Time to Detect and Classify Vehicles by Using Abandoned Object Detection in Video-Surveillance:
Convolutional Neural Network," SysCoBIoTS, Survey and Comparison. Sensors (Basel).
2019, pp. 1-5. 2018;18(12):4290. Published 2018 Dec 5.
3. Fedorov, A., Nikolskaia, K., Ivanov, S. et al. Traffic doi:10.3390/s18124290
flow estimation with data from a video surveillance 16. V. Ghanavanth et al., "Smart CCTV surveillance
camera. J Big Data 6, 73, 2019. system for intrusion detection with live streaming",
4. K. K. Santhosh, D. P. Dogra, and P. P. Roy. 2020. 3rd IEEE International Conference RTEICT, 2018.
Anomaly Detection in Road Traffic Using Visual 17. Apoorva Raghunandan, Pakala Raghav and HV
Surveillance: A Survey. ACM Comput. Surv. 53, 6, Ravish Aradhya, "Object detection algorithms for
Article 119, February 2021. video surveillance applications", ICCSP, 2018.
5. B. Tian, B. T. Morris, M. Tang, Y. Liu, Y. Yao, C. 18. Archana Kalyankar, Shikha Nema and Umesh
Gou, D. Shen, and S. Tang. 2017. Hierarchical and Mahind, "Advance and automatic motion detection

4
E3S Web of Conferences 309, 01099 (2021) https://doi.org/10.1051/e3sconf/202130901099
ICMED 2021

prediction data association with object tracking

system", International Conference ICIRCA, 2018.
19. Suma, G.J., Lalitha, R.V.S. Vehicular Ad hoc
Networks: A hybrid approach to data dissemination
in exigency situations. Wireless Netw 22, 1725–
1737 2016.
20. Lalitha RVS, Srinivas R, Kumar PSVVSR, Kavitha
K,Sameera PVSNS. Intelligent signalling system to
control traffic in vehicular ad hoc networks. Indian
Journal of Science and Technology. 13(28).
21. Lalitha, R.V.S., Kavitha, K., Krishna Rao,
N.V., Rama Mounika, G., Sandhya, V., Smart
surveillance with smart doorbell , IJITEE, Volume-8
Issue-8, June 2019,pp 1841-44.
22. Nayak, Padmalaya, K. Kavitha, and Nausheed
Khan. "Cluster head selection in wireless sensor
network using bio-inspired algorithm." In TENCON
2019-2019 IEEE Region 10 Conference
(TENCON), pp. 1690-1696. IEEE, 2019.
23. Reddy, T. Raghunadha, B. Vishnu Vardhan, and P.
Vijaypal Reddy. "A survey on authorship profiling
techniques." International Journal of Applied
Engineering Research 11, no. 5 (2016): 3092-3102.
24. Kumar, Praveen, Ayush Singhal, Sanyam Mehta,
and Ankush Mittal. "Real-time moving object
detection algorithm on high-resolution videos using
GPUs." Journal of Real-Time Image Processing 11,
no. 1 (2016): 93-109.
25. Dhanalaxmi, B., G. Apparao Naidu, and K.
Anuradha. "Adaptive PSO based association rule
mining technique for software defect classification
using ANN." Procedia Computer Science 46 (2015):
432-442.
26. Kumar, Singamaneni Kranthi, Pallela Dileep
Kumar Reddy, Gajula Ramesh, and Venkata Rao
Maddumala. "Image transformation technique using
steganography methods using LWT
technique." Traitement du Signalvol 36 (2019): 233-
237.