Advances in lane marking detection algorithms for all-weather conditions

Ghani, Hadhrami Ab.; Besar, Rosli; Sani, Zamani Md; Kamaruddin, Mohd Nazeri; Syahali, Syabeela; Daud, Atiqullah Mohamed; Martin, Aerun

doi:10.11591/ijece.v11i4.pp3365-3373

Cited by 6 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tang et al [7] also included optimization strategies for these methods, which aimed to obtain good performance with a smaller dataset or to avoid post-processing. Ghani et al [11] reviewed different lane detection algorithms, considering weather conditions such as fog, haze, or rain. Additionally, they proposed a new contour angle method for lane marker classification.…”

Section: Related Workmentioning

confidence: 99%

Analyzing Performance Effects of Neural Networks Applied to Lane Recognition under Various Environmental Driving Conditions

Ortegon-Sarmiento

Kélouwani

Alam

et al. 2022

WEVJ

View full text Add to dashboard Cite

Lane detection is an essential module for the safe navigation of autonomous vehicles (AVs). Estimating the vehicle’s position and trajectory on the road is critical; however, several environmental variables can affect this task. State-of-the-art lane detection methods utilize convolutional neural networks (CNNs) as feature extractors to obtain relevant features through training using multiple kernel layers. It makes them vulnerable to any statistical change in the input data or noise affecting the spatial characteristics. In this paper, we compare six different CNN architectures to analyze the effect of various adverse conditions, including harsh weather, illumination variations, and shadows/occlusions, on lane detection. Among all the aforementioned adverse conditions, harsh weather in general and snowy night conditions particularly affect the performance by a large margin. The average detection accuracy of the networks decreased by 75.2%, and the root mean square error (RMSE) increased by 301.1%. Overall, the results show a noticeable drop in the networks’ accuracy for all adverse conditions because the features’ stochastic distributions change for each state.

show abstract

Section: Related Workmentioning

confidence: 99%

Analyzing Performance Effects of Neural Networks Applied to Lane Recognition under Various Environmental Driving Conditions

Ortegon-Sarmiento

Kélouwani

Alam

et al. 2022

WEVJ

View full text Add to dashboard Cite

show abstract

“…There is a lot of sky and other areas of the lane line in the data set, which will not only prolong the calculation time of the system detection, but also affect the accuracy of the lane line detection. In order to extract important features from the image for the classification decision, the image must be preprocessed [14] so that the processed image can meet the requirements of the lane line detection method of deep learning and save computing resources as much as possible. In this study, we will preprocess the image from the steps of image gray processing, target area extraction, image scaling, reverse perspective conversion and image flipping.…”

Section: Image Preprocessingmentioning

confidence: 99%

Lane Image Detection Based on Convolution Neural Network Multi-Task Learning

Zhang

et al. 2021

Electronics

View full text Add to dashboard Cite

Based on deep neural network multi-task learning technology, lane image detection is studied to improve the application level of driverless technology, improve assisted driving technology and reduce traffic accidents. The lane line database published by Caltech and Tucson company is used to extract the ROI (Region of Interest), scale, and inverse perspective transformation as well as to preprocess the image, so as to enrich the data set and improve the efficiency of the algorithm. In this study, ZFNet is used to replace the basic networks of VPGNet, and their structures are changed to improve the detection efficiency. Multi-label classification, grid box regression and object mask are used as three task modules to build a multi-task learning network named ZF-VPGNet. Considering that neural networks will be combined with embedded systems in the future, the network will be compressed to CZF-VPGNet without excessively affecting the accuracy. Experimental results show that the vision system of driverless technology in this study achieved good test results. In the case of fuzzy lane line and missing lane line mark, the improved algorithm can still detect and obtain the correct results, and achieves high accuracy and robustness. CZF-VPGNet can achieve high real-time performance (26FPS), and a single forward pass takes about 36 ms or less.

show abstract

“…NVIDIA's Jetson is a feasible enabler for the introductory phase of machine and computer vision due to its low-power processing capability that it offers as one of forefronts in artificial-intelligence hardware development for computer vision [28]- [30]. The CPU-graphics processing unit (GPU) architecture of Jetson Nano [31], [32], enables the CPU to load faster while the GPU seamlessly runs the machine-learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Face mask detection and counting using you only look once algorithm with Jetson Nano and NVDIA giga texel shader extreme

Al-Selwi

Hassan

Ghani

et al. 2023

IJ-AI

View full text Add to dashboard Cite

Deep learning and machine learning are becoming more extensively adopted artificial intelligence techniques for machine vision problems in everyday life, giving rise to new capabilities in every sector of technology. It has a wide range of applications, ranging from autonomous driving to medical and health monitoring. For image detection, the best reported approach is the you only look once (YOLO) algorithm, which is the faster and more accurate version of the convolutional neural network (CNN) algorithm. In the healthcare domain, YOLO can be applied for checking the face mask wearing of the people, especially in a public area or before entering any closed space such as a building to avoid the spread of the air-borne disease such as COVID-19. The main challenges are the image datasets, which are unstructured and may grow large, affecting the accuracy and speed of the detection. Secondly is the portability of the detection devices, which are generally dependent on the more portable like NVDIA Jetson Nano or from the existing computer/laptop. Using the low-power NVDIA Jetson Nano system as well as NVDIA giga texel shader extreme (GTX), this paper aims to design and implement real-time face mask wearing detection using the pre-trained dataset as well as the real-time data.

show abstract

Advances in lane marking detection algorithms for all-weather conditions

Cited by 6 publications

References 35 publications

Analyzing Performance Effects of Neural Networks Applied to Lane Recognition under Various Environmental Driving Conditions

Analyzing Performance Effects of Neural Networks Applied to Lane Recognition under Various Environmental Driving Conditions

Lane Image Detection Based on Convolution Neural Network Multi-Task Learning

Face mask detection and counting using you only look once algorithm with Jetson Nano and NVDIA giga texel shader extreme

Contact Info

Product

Resources

About