Can ADAS Distract Driver’s Attention? An RGB-D Camera and Deep Learning-Based Analysis

Ulrich, Luca; Nonis, Francesca; Vezzetti, Enrico; Moos, Sandro; Caruso, Giandomenico; Shi, Yuexi; Marcolin, Federica

doi:10.3390/app112411587

Cited by 7 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hardware and software required for this method are relatively inexpensive, making it a feasible solution for mass deployment. In a study by Ulrich, L et al [26], 11 participants participated in an auditory and haptic ADAS experiment while having their attention tracked while driving. The drivers' faces were captured using an RGB-D camera.…”

Section: Related Workmentioning

confidence: 99%

IoT-Assisted Automatic Driver Drowsiness Detection through Facial Movement Analysis Using Deep Learning and a U-Net-Based Architecture

Das,

Pratihar,

Pradhan

et al. 2024

Information

View full text Add to dashboard Cite

The main purpose of a detection system is to ascertain the state of an individual’s eyes, whether they are open and alert or closed, and then alert them to their level of fatigue. As a result of this, they will refrain from approaching an accident site. In addition, it would be advantageous for people to be promptly alerted in real time before the occurrence of any calamitous events affecting multiple people. The implementation of Internet-of-Things (IoT) technology in driver action recognition has become imperative due to the ongoing advancements in Artificial Intelligence (AI) and deep learning (DL) within Advanced Driver Assistance Systems (ADAS), which are significantly transforming the driving encounter. This work presents a deep learning model that utilizes a CNN–Long Short-Term Memory network to detect driver sleepiness. We employ different algorithms on datasets such as EM-CNN, VGG-16, GoogLeNet, AlexNet, ResNet50, and CNN-LSTM. The aforementioned algorithms are used for classification, and it is evident that the CNN-LSTM algorithm exhibits superior accuracy compared to alternative deep learning algorithms. The model is provided with video clips of a certain period, and it distinguishes the clip by analyzing the sequence of motions exhibited by the driver in the video. The key objective of this work is to promote road safety by notifying drivers when they exhibit signs of drowsiness, minimizing the probability of accidents caused by fatigue-related disorders. It would help in developing an ADAS that is capable of detecting and addressing driver tiredness proactively. This work intends to limit the potential dangers associated with drowsy driving, hence promoting enhanced road safety and a decrease in accidents caused by fatigue-related variables. This work aims to achieve high efficacy while maintaining a non-intrusive nature. This work endeavors to offer a non-intrusive solution that may be seamlessly integrated into current automobiles, hence enhancing accessibility to a broader spectrum of drivers through the utilization of facial movement analysis employing CNN-LSTM and a U-Net-based architecture.

show abstract

Section: Related Workmentioning

confidence: 99%

IoT-Assisted Automatic Driver Drowsiness Detection through Facial Movement Analysis Using Deep Learning and a U-Net-Based Architecture

Das,

Pratihar,

Pradhan

et al. 2024

Information

View full text Add to dashboard Cite

show abstract

“…In many road accidents, a significant proportion is caused by driver-related factors. To reduce the occurrence rate of road accidents and improve driving safety, many domestic and international universities and companies have conducted extensive research on ADAS [1][2][3][4]. Machine vision-based lane line type recognition technology is part of the ADAS perception module.…”

Section: Introductionmentioning

confidence: 99%

Lane Line Type Recognition Based on Improved YOLOv5

Liu,

Wang,

Wang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The recognition of lane line type plays an important role in the perception of advanced driver assistance systems (ADAS). In actual vehicle driving on roads, there are a variety of lane line type and complex road conditions which present significant challenges to ADAS. To address this problem, this paper proposes an improved YOLOv5 method for recognising lane line type. This method can accurately and quickly identify the types of lane lines and can show good recognition results in harsh environments. The main strategy of this method includes the following steps: first, the FasterNet lightweight network is introduced into all the concentrated-comprehensive convolution (C3) modules in the network to accelerate the inference speed and reduce the number of parameters. Then, the efficient channel attention (ECA) mechanism is integrated into the backbone network to extract image feature information and improve the model’s detection accuracy. Finally, the sigmoid intersection over union (SIoU) loss function is used to replace the original generalised intersection over union (GIoU) loss function to further enhance the robustness of the model. Through experiments, the improved YOLOv5s algorithm achieves 95.1% of mAP@0.5 and 95.2 frame·s−1 of FPS, which can satisfy the demand of ADAS for accuracy and real-time performance. And the number of model parameters are only 6M, and the volume is only 11.7 MB, which will be easily embedded into ADAS and does not require huge computing power to support it. Meanwhile, the improved algorithms increase the accuracy and speed of YOLOv5m, YOLOv5l, and YOLOv5x models to different degrees. The appropriate model can be selected according to the actual situation. This plays a practical role in improving the safety of ADAS.

show abstract

“…Three-dimensional data are foundational to computer graphics and computer vision, and it contains a wealth of geometric, shape, and scale information. The use of 3D models is increasing in daily life, such as in autonomous driving [1,2], virtual reality, and remote sensing mapping [3], all of which require advanced processing [4] and analysis of the collected 3D data. The study of how to effectively classify, identify, and segment 3D models is a hot topic at present.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network for 3D Shape Classification Based on Mesh Feature

Gao

Ruan

Shi

et al. 2022

Sensors

View full text Add to dashboard Cite

Virtual reality, driverless cars, and robotics all make extensive use of 3D shape classification. One of the most popular ways to represent 3D data is with polygonal meshes. In particular, triangular mesh is frequently employed. A triangular mesh has more features than 3D data formats such as voxels, multi-views, and point clouds. The current challenge is to fully utilize and extract useful information from mesh data. In this paper, a 3D shape classification network based on triangular mesh and graph convolutional neural networks was suggested. The triangular face of this model was viewed as a unit. By obtaining an adjacency matrix from mesh data, graph convolutional neural networks can be utilized to process mesh data. The studies were performed on the ModelNet40 dataset with an accuracy of 91.0%, demonstrating that the classification network in this research may produce effective results.

show abstract

Can ADAS Distract Driver’s Attention? An RGB-D Camera and Deep Learning-Based Analysis

Cited by 7 publications

References 33 publications

IoT-Assisted Automatic Driver Drowsiness Detection through Facial Movement Analysis Using Deep Learning and a U-Net-Based Architecture

IoT-Assisted Automatic Driver Drowsiness Detection through Facial Movement Analysis Using Deep Learning and a U-Net-Based Architecture

Lane Line Type Recognition Based on Improved YOLOv5

Deep Neural Network for 3D Shape Classification Based on Mesh Feature

Contact Info

Product

Resources

About