ABSTRACT - Research and/or Engineering Questions/Objective In the research conducted, the objective is to develope a Driver Monitoring System (DMS) based on 3D iToF sensor technology for vital signs extraction. The iToF sensor, installed in the interior of a vehicle and recording the chest of the driver, measures the distance between the camera and the object, in this case the chest of the driver, by detecting the time difference between the emission of the infrared rays and its return to the sensor after being reflected by the chest. - Methodology The algorithms developed extract the respiratory signal by analyzing the changes in the z-axis produced by the change in the diaphragm due to the airflow during inhalation and exhalation processes and the subsequent deformation of the thoracic cage. In order to evaluate the quality of the signal extracted, several tests in controlled and in real conditions has been conducted, comparing the respiratory signal extracted from iToF sensor to a Gold Standard (GS) respiratory signal recorded. - Results This analysis consists in filtering the signal for artefacts elimination, detect peaks related to breathing movements, detect the number and position of every peak of both, extracted and GS respiration signals, and finally calculate the mean of peaks in a 20s sliding window to compare the respiration frequencies variability. To calculate the correlation between both, extracted and GS respiration, we used Pearson’s Correlation Coefficient obtaining results of 0.97-0.99 in all cases. Finally, we analyzed the behavior of both signals with our Thoracic Effort Drowsiness Detection index (TEDD) for drowsiness detection. The TEDD index analyses respiratory signal parameters as amplitude, frequency and appearance of breathing patterns indicative of drowsiness as yawn, sights and apnea. - Limitations of this study The limitations observed are the position of the sensor inside the vehicle, since the sensor provided is a new technology and actually is not designed to be integrated in the cabin of the vehicle. The actual sensor and the support for vehicle installation are susceptible to vibrations and driver position. This issue will b solved in further work. - What does the paper offer that is new in the field including in comparison to other work by the authors? This research is focused of the integration of new iToF technology to the Driver Monitoring Systems solution increasing the robustness of the system regarding external conditions. This new approach implies strategic competitive advantages in the automotive sector. The most important is that the drowsiness analysis performed is based on a physiological variable; this means that the results are objective. In addition, iToF sensors can be used for more than one feature at a time, which means that the analysis of the drowsiness can be done combining analysis of gestures, facial activity, respiratory patterns and other parameters with one single sensor. - Conclusions From the research conducted, it can be concluded that both systems, gold standard system and iToF sensor, give the same general state of the subject, however the iToF system presents a greater robustness in the analysis.
Mrs. Noelia Rodríguez Ibáñez, Innovation Leader, IDNEO Technologies
Drowsiness Prediction Based on an iToF Camera for iCM Applications
FWC2023-SCA-044 • Integrated safety, connected & automated driving
Upgrade your ICC subscription to access all Library items.
Congratulations! Your ICC subscription gives you complete access to the FISITA Library.
Retrieving info...
Available for purchase on the FISITA Store
OR