Researchers at the Computer Sciences and IT Department led by Dr Ebrahim Ansari and Dr Parvin Razzaghi have designed a system called “An intelligent safety system for human-centred semi-autonomous vehicles” whose main aim is to prevent accidents that occur when the driver is tired, sleepy, or distracted.
Nowadays, car manufacturers are trying to develop ways of making cars completely safe. Monitoring the driver's actions using computer vision techniques to detect driving mistakes in real-time and then planning for autonomous driving to avoid vehicle collisions is one of the most important issues that is being investigated in the machine vision and Intelligent Transportation Systems (ITS).
The main goal of this study is to prevent accidents caused by fatigue, drowsiness, and driver distraction. To avoid these incidents, this project proposes an integrated safety system that continuously monitors the driver's attention and vehicle surroundings, and finally decides whether the actual steering control status is safe or not. To achieve this, we equipped an ordinary car called FARAZ with a vision system consisting of four mounted cameras along with a universal car tool for communicating with the surrounding factory-installed sensors and other car systems and sending commands to the actuators.
The proposed system leverages a scene understanding pipeline using a deep convolutional encoder-decoder network and a driver state detection pipeline. We have identified and assessed the capabilities within the country for the development of technologies specific to ordinary vehicles in order to manufacture smart cars and provide an intelligent system that would increase safety and assist the driver in various conditions and situations.
More information about this study is available here: https://iasbs.ac.ir/~ansari/faraz/fa/index.html
Mon, 04 Nov 2019
Developed by the IASBS Computer Centre