Deep Bio-Sensing Embedded System for a Robust Car-Driving Safety Assessment

Author(s):  
Francesco Rundo ◽  
Concetto Spampinato ◽  
Sabrina Conoci ◽  
Francesca Trenta ◽  
Sebastiano Battiato
CICTP 2019 ◽  
2019 ◽  
Author(s):  
Jing-Jing Tian ◽  
Liang-Qiu Wang ◽  
Yu-Long He ◽  
Gui-Xian Qu ◽  
Lei Liu

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Yen-Lin Chen ◽  
Chao-Wei Yu ◽  
Zi-Jie Chien ◽  
Chin-Hsuan Liu ◽  
Hsin-Han Chiang

This study presents an on-road driver monitoring system, which is implemented on a stand-alone in-vehicle embedded system and driven by effective solar cells. The driver monitoring function is performed by an efficient eye detection technique. Through the driver’s eye movements captured from the camera, the attention states of the driver can be determined and any fatigue states can be avoided. This driver monitoring technique is implemented on a low-power embedded in-vehicle platform. Besides, this study also proposed monitoring machinery that can detect the brightness around the car to effectively determine whether this in-vehicle system is driven by the solar cells or by the vehicle battery. On sunny days, the in-vehicle system can be powered by solar cell in places without the vehicle battery. While in the evenings or on rainy days, the ambient solar brightness is insufficient, and the system is powered by the vehicle battery. The proposed system was tested under the conditions that the solar irradiance is 10 to 113 W/m2and solar energy and brightness at 10 to 170. From the testing results, when the outside solar radiation is high, the brightness of the inside of the car is increased, and the eye detection accuracy can also increase as well. Therefore, this solar powered driver monitoring system can be efficiently applied to electric cars to save energy consumption and promote the driving safety.


Author(s):  
Sonia Ortiz-Peregrina ◽  
Carolina Ortiz ◽  
José J. Castro-Torres ◽  
José R. Jiménez ◽  
Rosario G. Anera

Cannabis is the most widely used illegal drug in the world. Limited information about the effects of cannabis on visual function is available, and more detail about the possible impact of visual effects on car driving is required. This study investigated the effects of smoking cannabis on vision and driving performance, and whether these effects are correlated. Twenty drivers and occasional users were included (mean (SE) age, 23.3 (1.0) years; five women). Vision and simulated driving performance were evaluated in a baseline session and after smoking cannabis. Under the influence of cannabis, certain visual functions such as visual acuity (p < 0.001), contrast sensitivity (p = 0.004) and stereoacuity (far, p < 0.001; near, p = 0.013) worsened. In addition, there was an overall deterioration of driving performance, with the task of keeping the vehicle in the lane proving more difficult (p < 0.05). A correlation analysis showed significant associations between driving performance and visual function. Thus, the strongest correlations were found between the distance driven onto the shoulder and stereoacuity, for near (ρ = 0.504; p = 0.001) and far distances (ρ = 0.408; p = 0.011). This study provides the first evidence to show that the visual effects of cannabis could impact driving performance, compromising driving safety. The results indicate that information and awareness campaigns are essential for reducing the incidence of driving under the influence of cannabis.


2014 ◽  
Vol 556-562 ◽  
pp. 6111-6114
Author(s):  
Feng Ping Cao

In order to estimating the state of driving safety and reducing accidents, a discrimination method of driving safety states based on BP neural network was presented in the paper. Firstly, the influencing factors on the vehicle driving safety were analyzed, and ten main factors that affected the driving safety of vehicles were confirmed, which constitute the safety assessment index system for vehicle driving. Then the discrimination model of driving safety states based on BP neural network was established, and inputs and outputs for the neurons were determined. At last, the input data for neurons were acquired on the basic of the main evaluation indexes of vehicle driving safety, and these data were used to train the neural network. The training result conform to expectations of the training requires.


Author(s):  
Christian Collet

Several actions and/or operations might interfere with those required during car-driving and thus elicit dual task conditions. Those related to driving itself involve manipulating commands or instruments and should be automated during the learning to drive period to ensure safety. Others, independent of driving may be delayed (eating, smoking a cigarette). Finally, others like manipulating a navigation system or holding a cellphone have potential interference more or less related to driving. The authors now step back about 25 years to analyze the interference between driving and phoning and assess the risk associated with it. Epidemiology provides an overview of mobile phone use and hypotheses about accident causes. If hand-held phones obviously interfere with driving actions, the authors should explain why hands-free kits do not solve all safety concerns. Then, analyzing the operations affected by phoning and describing the objective measures revealing impaired driving performance will address this issue. The authors finally highlight the conditions for relatively safe phone use as well as those that should be banned. Deciding to phone or not will thus depend on driving safety education, during which skills of caution should have been learned.


2011 ◽  
Vol 314-316 ◽  
pp. 123-126
Author(s):  
Hung Yin Tsai ◽  
Mei Ting Lu ◽  
Shao Wei Luo

Simulation on transmittance for different submicron-structures by finite difference time domain method is studied. The objectives of this study are to discuss transmittance for different submicron-structures. Different structures have different effects of transmittance and reflectance; therefore different sizes, shapes, periods and aspect ratios of submicron-structures are discussed in the current study. High transmittance at the visible waveband and heat insulation at the infrared range are expected for application of car window. The simulation results for flat surface and pyramid structures show that the transmittance increases from 95.7 % to 99.8 % at the wavelength of 760 nm and slightly from 96.0 % to 96.3 % at the infrared range. Though the effect of heat insulation slightly decreases while the infrared passes through the submicron-structures, the high visibility helps for car driving safety. The pyramid structure shows the optimal condition for the application of car window at the aspect ratio of 1 to 2 than other shapes.


Sign in / Sign up

Export Citation Format

Share Document