Abstract
Advanced driver assistance functions help us prevent the human-based accidents and reduce the damage and costs. One of the most important functions is the lane keeping assist which keeps the car safely in its lane by preventing careless lane changes. Therefore, many researches focused on the lane detection using an onboard camera on the car as a cost-effective sensor solution and used conventional computer vision techniques. Even though these techniques provided successful outputs regarding lane detection, they were time-consuming and required hand-crafted stuff in scenario-based parameter tuning. Deep learning-based techniques have been used in lane detection in the last decade. More successful results were obtained with fewer parameter tuning and hand-crafted things. The most popular deep learning method for lane detection is convolutional neural networks (CNN). In this study, some reputed CNN architectures were used as a basis for developing a deep neural network. This network outputs were the lane line coefficients to fit a second order polynomial. In the experiments, the developed network was investigated by comparing the performance of the CNN architectures. The results showed that the deeper architectures with bigger batch size are stronger than the shallow ones.
Highlights
LANE DETECTION using computer vision techniques has been getting more attention for decades
We gave a deep neural network in which the most reputed convolutional neural network (CNN) architectures were utilized for lane detection
The effect of batch size was considered for the CNN architectures individually
Summary
LANE DETECTION using computer vision techniques has been getting more attention for decades. Conventional computer vision techniques have addressed the lane detection system using three procedures as the following: 1) preprocessing, 2) feature extraction and model fitting, 3) lane tracking. These techniques generally are represented by two categories: featurebased, and model-based [1]. EKŞİ, Department of Mechatronics Engineering, Technology Faculty, University of Marmara, Istanbul, Turkey,
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have