International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 183 - Number 21 |
Year of Publication: 2021 |
Authors: Felix Larbi Aryeh, Emmanuel Kweku Eshun, Abdul-Harisu Inusah |
10.5120/ijca2021921575 |
Felix Larbi Aryeh, Emmanuel Kweku Eshun, Abdul-Harisu Inusah . A Smart Vehicular Forward Collision Alert System using Neural Network. International Journal of Computer Applications. 183, 21 ( Aug 2021), 8-17. DOI=10.5120/ijca2021921575
Road accidents over the years have led to an increased mortality rate in Ghana. Most accidents are caused by stress, tiredness, and loss of concentration of drivers while driving. This paper sought to design and build an automatic detection forward collision alert system for already existing vehicles in Ghana. Specifically, a deep learning model was built using a convolutional neural network for detection of stationary/moving objects (person, cars, bicycle, truck, bus and others). The object's relative speed to that of the subject vehicle is used to determine the probability of a collision. A buzzing alarm sound occurs when the possibility of collision is higher. The proposed system is an economical technique of alerting drivers of any impending danger on our roads.