| Deep Learning For Autonomous Vehicles Comprehencive Survay |
| Paper ID : 1110-ISCHU |
| Authors |
|
Esraa Mohamed Salah *1, MOURAD REEFAT2, Mohamed Zorkany3, ASHRAF DARWISH4 1Department of Mathematics, Faculty of Science, Helwan University, Helwan, Egypt 2Faculty of scince,Helwan university, Cairo,Egypt 3Electronics department, National telecommunication Institute. 4Department of Mathematics, Faculty of Science, Helwan University. |
| Abstract |
| Autonomous Vehicle Perception (AVP) has emerged as a critical aspect of ensuring the safety and situational awareness of moving vehicles. The decision-making process within autonomous vehicles relies heavily on the input provided by perception systems to make informed decisions aimed at minimizing risks to passengers. In this context, two primary tasks hold significant importance: Semantic Segmentation and Object Detection. These tasks are integral components of an autonomous vehicle's navigation system, contributing to its ability to navigate safely. This paper provides a comprehensive review of the current state-of-the-art deep learning techniques utilized in perception and decision-making processes for autonomous vehicles, with a specific focus on image and LiDAR point cloud data. The discussion encompasses the various sensors and simulation tools commonly employed in semantic segmentation and object detection tasks, particularly in the context of autonomous driving scenarios. By exploring these advancements, this research contributes to our understanding of the critical role played by perception systems in enhancing the safety and efficacy of autonomous vehicles. |
| Keywords |
| Autonomous vehicle, deep learning,semantic segmentation, object detection. |
| Status: Abstract Accepted (Poster Presentation) |