Smart Traffic Density Management System Using Image Processing

Traffic Management is a big issue which impacts us almost daily. Use of technology such as IoT and image processing can lead to a smooth traffic management system. The common reason for traffic congestion is due to the lack of an efficient traffic prioritization system. The internet of things is a network of devices. The embedded systems includes sensors, actuators, and electronics.With software and connectivity locally or over internet helps in transfer of data. Each of these devices is uniquely identifiable in the network and are highly interoperable. Image processing using OpenCV is a technique that is used to process an input image and obtain the traffic densities along various lanes in a junction. Existing traffic management solutions include using RFID tags on vehicles to obtain a vehicle count. This can also be done using ultrasonic sensors. The problem with these methods is that when implemented in a large scale, the cost of the entire system can be exponentially higher than an image processing approach as each vehicle will have to be fitted with an RFID tag. Hence, implementing this model at a largescale level, for example in a metropolitan city will be time consuming and expensive. This has led to the development of our algorithm, which uses image processing and IoT along with CCTV cameras. This system is efficient, as it uses CCTV cameras that are already present in traffic signals of most major metropolitan cities. Hence implementing the system at a largescale level is feasible. This algorithm also takes care of corner cases like heavy utility vehicles and motorbikes. It can also be used at night and during unfavorable weather conditions.The algorithm used detects the density of traffic as opposed to the count of vehicles by taking input images from a CCTV camera, comparing it with a sample image of an empty road and obtaining a match percentage. The traffic density can be found easily using this since it has a disproportionate relation with the match percentage. The traffic signals can be altered accordingly using the traffic density. The output is then sent to the ThingSpeak cloud where it can be analyzed.

Download Full-text

Incremental Multi-Feature Tensor Subspace Learning Based Smart Traffic Control System and Traffic Density Calculation Using Image Processing

2021 2nd International Conference on Computation, Automation and Knowledge Management (ICCAKM) ◽

10.1109/iccakm50778.2021.9357743 ◽

2021 ◽

Author(s):

G. Suseendran ◽

D. Akila ◽

D. Balaganesh ◽

V.R. Elangovan ◽

V. Vijayalakshmi

Keyword(s):

Image Processing ◽

Control System ◽

Traffic Control ◽

Subspace Learning ◽

Traffic Density ◽

Density Calculation ◽

Traffic Control System ◽

Tensor Subspace ◽

Smart Traffic

Download Full-text

IoT based Smart Traffic density Control using Image Processing

2019 4th MEC International Conference on Big Data and Smart City (ICBDSC) ◽

10.1109/icbdsc.2019.8645568 ◽

2019 ◽

Cited By ~ 8

Author(s):

Anilloy Frank ◽

Yasser Salim Khamis Al Aamri ◽

Amer Zayegh

Keyword(s):

Image Processing ◽

Traffic Density ◽

Density Control ◽

Smart Traffic

Download Full-text

Real-Time Area-Based Traffic Density Calculation Using Image Processing for Smart Traffic System

Smart Computing Techniques and Applications - Smart Innovation, Systems and Technologies ◽

10.1007/978-981-16-0878-0_28 ◽

2021 ◽

pp. 287-296

Author(s):

S. Rakesh ◽

Nagaratna P. Hegde

Keyword(s):

Image Processing ◽

Real Time ◽

Traffic Density ◽

Traffic System ◽

Density Calculation ◽

Smart Traffic

Download Full-text

Traffic Density Measurement using Image Processing: An SVM approach

International Journal of Innovative Research in Computer and Communication Engineering ◽

10.15680/ijircce.2015.0306002 ◽

2015 ◽

Vol 03 (06) ◽

pp. 4979-4986

Author(s):

Hosne-Al-Walid, Nafisa Anjum

Keyword(s):

Image Processing ◽

Density Measurement ◽

Traffic Density

Download Full-text

Adaptive Traffic Density Management System

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6si3.173176 ◽

2018 ◽

Vol 06 (03) ◽

pp. 173-176

Author(s):

A Keerthi Infanta Francy ◽

S Visalachi ◽

R Deepa

Keyword(s):

Management System ◽

Traffic Density

Download Full-text

Color image design based on machine learning and SVM algorithm

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189515 ◽

2020 ◽

pp. 1-12

Author(s):

Li Bo

Keyword(s):

Image Processing ◽

Graphic Design ◽

Management System ◽

Computer Network ◽

Color Image ◽

Color Difference ◽

Color Management ◽

Development Mode ◽

Operation Process ◽

Svm Algorithm

In today’s society, graphic design, as a popular image processing technology, plays an increasingly important role in people’s lives. In the specific operation process of graphic design, It is no longer restricted to the traditional development mode, such as file format and other factors. With the development of computer network technology, people promote the development of graphic design by constructing color management system. At the same time, the construction of color management system can help people to change colors and define colors when they process image information and output pictures. In the process of printing pictures, in order to make the colors used in the design process clearly printed out and without color difference, there are still many problems to be considered. First, we need to consider the unexpected situation and the complexity of image processing. Based on the introduction of computer learning, this paper will discuss and study the development of graphic design by SVM theory.

Download Full-text