Deep Learning Based Distance Estimation Method Using SSD and Deep ANN for Autonomous Braking/Steering

Abstract

The Automatic Emergency Braking (AEB) system is a mechanism that enables drivers to leverage the capabilities of their vehicles by warning them of potential collisions and assisting them in averting them. Autonomous Emergency Steering (AES) is one of the active safety systems that can assist with evasive steering. It will make it simpler for the driver to avoid an accident that could have been prevented. Concerns include the distance necessary to prevent a collision when turning or reversing and the required space when braking and turning. Given such inquiries, developing a system to estimate the distance between the vehicles is necessary. Consequently, this study suggested utilizing deep learning for AEB and AES to estimate the distance between vehicles using a monocular vision sensor. In addition, the object distance estimation method is employed as a distance estimation method. Experiments are conducted to determine the precision of the proposed method for estimating the distance between the target vehicle and the camera using LiDAR distances. The result indicates that the proposed method for estimating distance has an accuracy of 92% compared to LiDAR distance. As a result, the findings of this research have the potential to contribute to the methodological foundation for further understanding drivers’ behavior, with the ultimate objective of lowering the number of accidents involving rear-end crashes.