LLDNet: A Lightweight Lane Detection Approach for Autonomous Cars Using Deep Learning

Abstract

Lane detection plays a vital role in making the idea of the autonomous car a reality. Traditional lane detection methods need extensive hand-crafted features and post-processing techniques, which make the models specific feature-oriented, and susceptible to instability for the variations on road scenes. In recent years, Deep Learning (DL) models, especially Convolutional Neural Network (CNN) models have been proposed and utilized to perform pixel-level lane segmentation. However, most of the methods focus on achieving high accuracy while considering structured roads and good weather conditions and do not put emphasis on testing their models on defected roads, especially ones with blurry lane lines, no lane lines, and cracked pavements, which are predominant in the real world. Moreover, many of these CNN-based models have complex structures and require high-end systems to operate, which makes them quite unsuitable for being implemented in embedded devices. Considering these shortcomings, in this paper, we have introduced a novel CNN model named LLDNet based on an encoder–decoder architecture that is lightweight and has been tested in adverse weather as well as road conditions. A channel attention and spatial attention module are integrated into the designed architecture to refine the feature maps for achieving outstanding results with a lower number of parameters. We have used a hybrid dataset to train our model, which was created by combining two separate datasets, and have compared the model with a few state-of-the-art encoder–decoder architectures. Numerical results on the utilized dataset show that our model surpasses the compared methods in terms of dice coefficient, IoU, and the size of the models. Moreover, we carried out extensive experiments on the videos of different roads in Bangladesh. The visualization results exhibit that our model can detect the lanes accurately in both structured and defected roads and adverse weather conditions. Experimental results elicit that our designed method is capable of detecting lanes accurately and is ready for practical implementation.

Object Detection, Recognition, and Tracking Algorithms for ADASs—A Study on Recent Trends

“…Zheng et al [ 138 ] introduced CLRNet for lane detection, while Wang et al [ 122 ] proposed a multitask attention network (MAN). Khan et al [ 139 ] developed LLDNet, a lightweight lane detection approach for autonomous cars. Chen and Xiang [ 125 ] incorporated pre-aligned spatial–temporal attention for lane mark detection.…”

Enhanced SCNN-Based Hybrid Spatial-Temporal Lane Detection Model for Intelligent Transportation Systems

“…Additionally, to enhance model robustness, some researchers have amalgamated different datasets. For example, Khan et al [12] trained deep learning models using a combination of the Udacity Machine Learning Nanodegree Project Dataset [13] and the Cracks and Potholes in Road Images Dataset [14], aiming to effectively detect lane markings under adverse weather and lighting conditions.…”

QuantLaneNet: A 640-FPS and 34-GOPS/W FPGA-Based CNN Accelerator for Lane Detection

“…These networks need to be simplified to apply this application on embedded devices with limited resources. LLDNet [ 15 ] introduced a lightweight CNN model based on an encoder–decoder architecture that makes it suitable for being implemented in embedded devices. Podbucki et al [ 16 ] present an NVIDIA Jetson Xavier AGX embedded system to process video sequences for lane detection.…”