Robust Lane Detection and Tracking Algorithm for Steering Assist Systems

Andrei, Mihail-Alexandru; Boiangiu, Costin-Anton; Tarba, Nicolae; Voncilă, Mihai-Lucian

doi:10.3390/machines10010010

Cited by 18 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They replaced the original hough transformation using the probabilistic transformation. They also used the parallelogram ROI instead of the trapezoidal one [ 22 ]. Wang et al proposed a lane detection method based on the Catmull–Rom Spline, which can detect lanes in noisy environments by extracting the lane structures using control points [ 23 ].…”

Section: Literature Reviewmentioning

confidence: 99%

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

Khan

Haque

Hasan

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

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

Khan

Haque

Hasan

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The Gaussian Blur filtering is the operation of blurring the image by multiplying the core matrix and the pixels of the image, and the 2D Gaussian function is expressed with Equation (3) [21].…”

Section: Image Filteringmentioning

confidence: 99%

A new approach for camera supported machine learning algorithms based dynamic headlight model's design

YAŞAR>

ŞAHİN>

Akar

2022

International Journal of Automotive Engineering and Technologies

View full text Add to dashboard Cite

Traffic accidents continue to be a significant issue in modern society. Accidents usually happen on dark, mountainous, narrow, steep and curved roadways. One of the primary causes of such accidents is the drivers’ weak sight brought on by the headlights of moving vehicles. In this study, a dynamic headlight model was designed using camera supported machine learning algorithms to improve the drivers’ vision during night drive. In this design, the issues of enabling a lighting field supported by image processing programmed with machine learning, dynamic adjustment of the high beam headlights’ LED cells in response to the vehicle approaching from the opposite direction, traffic-sign recognition system, lane-keeping system, and automatic adjustment of headlight angles were addressed. In this direction, a novel dynamic headlight model that will reduce the risk of accidents caused by lighting was presented, and its analyses were performed.

show abstract

“…This algorithm is used to automatically detect the road lane boundary based on the image processing technique. Some previous work tried to perform lane detection based on image processing methods [19][20][21][22][23][24]. Most of that research has similar main steps to achieve the result; pre-processing of images, selecting areas of interest, and making lane line decisions.…”

Section: Improved Road Lane Boundaries Based On Cctvmentioning

confidence: 99%

“…Many previous works researched how to detect the road lane in the Advanced Driver-Assistance Systems (ADAS) [16][17][18][19][20][21][22][23]. To summarize the methods used by previous research, there are two main types of techniques used in those work, which are deep learning-based and image processing-based approaches.…”

mentioning

confidence: 99%

“…There are many previous successful and interesting lane detection algorithms. The first one is from [19], Andrei et al aimed to detect if the road is turning to the left or right or going straight according to video from the front vehicle's camera in ADAS. They pre-processed each video frame with the Canny edge detector, Hough transform, and region of interest identification.…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Autonomous Framework for Real-Time Wrong-Way Driving Vehicle Detection from Closed-Circuit Televisions

et al. 2022

View full text Add to dashboard Cite

Around 1.3 million people worldwide die each year because of road traffic crashes. There are many reasons which cause accidents, and driving in the wrong direction is one of them. In our research, we developed an autonomous framework called WrongWay-LVDC that detects wrong-way driving vehicles from closed-circuit television (CCTV) videos. The proposed WrongWay-LVDC provides several helpful features such as lane detection, correct direction validation, detecting wrong-way driving vehicles, and image capturing features. In this work, we proposed three main contributions: first, the improved algorithm for road lane boundary detection on CCTV (called improved RLB-CCTV) using the image processing technique. Second is the Distance-Based Direction Detection (DBDD) algorithm that uses the deep learning method, where the system validates and detects wrong-driving vehicles. Lastly, the Inside Boundary Image (IBI) capturing feature algorithm captures the most precise shot of the wrong-way-of-driving vehicles. As a result, the framework can run continuously and output the reports for vehicles’ driving behaviors in each area. The accuracy of our framework is 95.23%, as we tested with several CCTV videos. Moreover, the framework can be implemented on edge devices with real-time speed for functional implementation and detection in various areas.

show abstract

Robust Lane Detection and Tracking Algorithm for Steering Assist Systems

Cited by 18 publications

References 17 publications

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

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

A new approach for camera supported machine learning algorithms based dynamic headlight model's design

An Autonomous Framework for Real-Time Wrong-Way Driving Vehicle Detection from Closed-Circuit Televisions

Contact Info

Product

Resources

About