Real-Time Road Lane Detection for Self-driving Cars Using Computer Vision

The design and implementation of autonomous vehicles are a rapidly evolving field of research and development. The purpose of this paper is to provide an overview of the design and implementation of road lane line detection. This paper provides an overview of the history and evolution of road lane line detection, describes the various technologies involved in their operation, and explores the challenges and future prospects of this emerging field. In this work, the current state of road lane line detection was reviewed using autonomous vehicles, research, and development in terms of environment sensing, pedestrian detection, path planning, motion control, and vehicle cybersecurity. Our objective is to study the various techniques proposed and to compare their approaches. For fully self-driving cars, these technologies need to be precise enough to gain public trust and be pinpoint accurate in their methods of solving these problems. The paper also explores public confidence and perceptions of motor vehicles. By discussing opportunities and barriers of road lane line detection using self-driving technology, the aim was to shed light on future possibilities. A camera is a widely used sensor for lane detection. Computer vision and deep learning will be used for detecting the edges and preparing the model for the same. Also, canny-edge detection that uses a multi-stage algorithm to simulate the lane line was used. Then at last, Hough Transmission was used that converted pixels to a line and process frames to detect lanes.