A Deep Learning approach using Action Recognition for Pedestrians & Vehicle Overtaking of Bangladesh Highway Road Dataset & it’s Implementation

Intelligent transportation systems have been met with resounding approval from individuals, governments and automobile manufacturers located all over the globe. The primary problems in the field of intelligent and self-driving & non self driving vehicles are identifying impediments, particularly people, and preventing accidents with them. In order to advance intelligent transportation systems for both self-driving cars and all other manual cars, we focused on using deep learning methods to identify pedestrians. After that, some of the most popular deep learning techniques were covered. The accurate identification of pedestrians in self-built automobiles still has a lot of flaws. This study highlights the challenges the transportation industry faces. The solutions are intended to help reduce traffic, accidents. Large automakers (including Google and Tesla) , working to develop self-driving and non-selfdriving vehicles that can transport passengers safely even while the driver is sleepy. Sensors that can sense their surroundings, identify what is close by, and communicate that information to the driver must be installed in these cars. neural networks, which often include several hidden layers and nonlinear processing units, are the basis for most deep learning approaches.
TECHNOLOGY::Electrical engineering, electronics and photonics::Electrical engineering
Department Name
Electrical and Computer Engineering
North South University
Printed Thesis