• D.Varshini
• Dr.D.Gowri Sankar Reddy

Intelligent transport system (ITS) is not just limited to traffic congestion control and information, but also for road safety and efficient infrastructure usage. The problem related to traffic is a complex one requiring proper design and planning for developing a solution. For safety and harmony in the flow of traffic, drivers are expected to pay attention to identify, interpret and follow certain rules while driving. Misinterpretation of traffic signs and signals may lead to catastrophes. An automatic system in a car which detects, recognizes, interprets traffic signs, traffic signals and pedestrians effectively and gives warning to the driver would be of great help in reducing the misinterpretations and accidents. In the present study, traffic sign and signal recognition system has been developed to increase the safety of the road users by installing the developed hardware system inside the car which gives an audio output for alerting the driver. Tensor Flow algorithm was used for the real time object detection through deep learning due to its high accuracy. The algorithm is embedded into Raspberry Pi 4 prototype for processing and analysis to detect the traffic signs, signals and pedestrians from the real-time video which will be recorded by a camera placed in the system and produces an audio output to alert the driver. This work aims to study the accuracy, delay and reliability of the developed system using a Raspberry Pi 4 processor considering several scenarios related to the state of the situation and the condition of the traffic signs and movement of humans. A real-time tested hardware implementation has been conducted for different classes of traffic signs, traffic signals and pedestrians. The result showed more than 98% accuracy and is reliable with an acceptable delay.

Intelligent Transport System, Traffic signs & traffic signals, Raspberry Pi, OpenCV, Tensorflow etc.

"Real Time Object Detection Using Deep Learning Techniques for Effective Intelligent Transport System ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 8, page no.c199-c205, August-2022, Available :http://www.jetir.org/papers/JETIR2208220.pdf

"Real Time Object Detection Using Deep Learning Techniques for Effective Intelligent Transport System ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 8, page no. ppc199-c205, August-2022, Available at : http://www.jetir.org/papers/JETIR2208220.pdf