Deep Neuro-Vision Embedded Architecture for Safety Assessment in Perceptive Advanced Driver Assistance Systems: The Pedestrian Tracking System Use-Case

Abstract

In recent years, the automotive field has been changed by the accelerated rise of new technologies. Specifically, autonomous driving has revolutionized the car manufacturer's approach to design the advanced systems compliant to vehicle environments. As a result, there is a growing demand for the development of intelligent technology in order to make modern vehicles safer and smarter. The impact of such technologies has led to the development of the so-called Advanced Driver Assistance Systems (ADAS), suitable to maintain control of the vehicle in order to avoid potentially dangerous situations while driving. Several studies confirmed that an inadequate driver's physiological condition could compromise the ability to drive safely. For this reason, assessing the car driver's physiological status has become one of the primary targets of the automotive research and development. Although a large number of efforts has been made by researchers to design safety-assessment applications based on the detection of physiological signals, embedding them into a car environment represents a challenging task. These mentioned implications triggered the development of this study in which we proposed an innovative pipeline, that through a combined less invasive Neuro-Visual approach, is able to reconstruct the car driver's physiological status. Specifically, the proposed contribution refers to the sampling and processing of the driver PhotoPlethysmoGraphic (PPG) signal. A parallel enhanced low frame-rate motion magnification algorithm is used to reconstruct such features of the driver's PhotoPlethysmoGraphic (PPG) data when that signal is no longer available from the native embedded sensor platform. A parallel monitoring of the driver's blood pressure levels from the PPG signal as well as the driver's eyes dynamics completes the reconstruction of the driver's physiological status. The proposed pipeline has been tested in one of the major investigated automotive scenarios i.e., the detection and monitoring of pedestrians while driving (pedestrian tracking). The collected performance results confirmed the effectiveness of the proposed approach.

Driving drowsiness detection using spectral signatures of EEG-based neurophysiology

“…Behavioral methods incorporate computer vision algorithms that use onboard cameras to detect changes in the driver’s behavior ( Akrout and Mahdi, 2021 ). Drowsiness is characterized by facial recognition, frequent yawning, delayed eye closures, rapid blink rates, lowered head posture, microsleep, or dozing-off behaviors ( Rundo et al, 2021 ). However, identifying tiredness with behavioral cues, such as eye blinks, lip movement, yawn frequency, and facial features, may cause false detections.…”

Intelligent Real-Time Deep System for Robust Objects Tracking in Low-Light Driving Scenario

“…The lack of sufficient illumination of the driving scene does not allow the semantic segmentation algorithms to identify and track objects or the deep classifiers to discriminate one class rather than another due to poor significant pixel-based information and therefore limited discriminating visual features [3]. Autonomous driving (AD) and driver assistance (ADAS) systems require high levels of robustness both in performance and fault-tolerance, often requiring high levels of validation and testing before being placed on the market [4]. The author has already deeply investigated the main issues and critical points of the ADAS technologies [4][5][6][7][8][9][10].…”

“…Autonomous driving (AD) and driver assistance (ADAS) systems require high levels of robustness both in performance and fault-tolerance, often requiring high levels of validation and testing before being placed on the market [4]. The author has already deeply investigated the main issues and critical points of the ADAS technologies [4][5][6][7][8][9][10]. Specifically, in the contributions reported in [4][5][6][7] such drowsiness detection methods based on the analysis of the car driver physiological signals have been reported.…”

“…The author has already deeply investigated the main issues and critical points of the ADAS technologies [4][5][6][7][8][9][10]. Specifically, in the contributions reported in [4][5][6][7] such drowsiness detection methods based on the analysis of the car driver physiological signals have been reported. An innovative method named "hyper-filtering" combined with robust computer vision algorithms has been reported in [8][9][10] to provide an intelligent assistance to the car driver.…”

“…For these Computation 2021, 9, 117 2 of 17 reasons, several scientific studies investigated the "perception" in self-driving technology in a driving scenario with a poor illumination. A very robust perception system includes a LiDAR based approach with an embedded visual camera [4][5][6][7][8][9][10]. As introduced, the performance of the car's camera device is significantly affected by the level of light as well as low contrast, low visibility, and so on.…”