Browse Publications Technical Papers 2020-01-1212

Heartbeat Detection Technology for Monitoring Driver's Physical Condition 2020-01-1212

In recent years, the number of reported traffic accidents due to sudden deterioration in driver’s physical condition has been increasing, and it is expected to develop a system that prevents accidents even if physical condition suddenly changes while driving, or reduces damage through vehicle body control.For this purpose it is necessary to detect sudden changes of the driver’s physical condition, and research is being conducted widely. Among them, it is reported that some of such changes may appear in the heartbeat interval. In other words, by acquiring the driver's heartbeat interval in real time, it may be possible to detect the sudden changes, and reduce traffic accident. Even if a traffic accident has occurred, the damage can be reduced by emergency evacuation immediately after detecting sudden changes. Therefore, we focused on the technology to detect the heartbeat interval wiht 24GHz microwave doppler radar, which can acquire heartbeat non-contactly while maintaining the interior design and passenger’s privacy. Doppler radar with microwave is sensitive enough to detect heartbeat, but vibration noise is also superimposed on the sensor signal easily. So, in general algorithm studied widely,the problem is that the accuracy of detecting the heartbeat interval deteriorates especially while driving, because superimposition of vehicle vibration on the frequency band used for heartbeat analysis, and the SN ratio decreases.In order to solve this problem, we have been developing an algorithm that extracts power spectrum over wide band including harmonic components of heartbeat and detects the peaks of power spectrum fluctuation.This time, our new peak-searching method, in which multiple peak intervals are selected simultaneously based on the previous estimation results, suppresses false detection of peaks caused by vibration noise. As a result, the error rate of the heartbeat interval detection was reduced by half compared to the conventional algorithm.


Subscribers can view annotate, and download all of SAE's content. Learn More »


Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Members save up to 18% off list price.
Login to see discount.
Special Offer: With TechSelect, you decide what SAE Technical Papers you need, when you need them, and how much you want to pay.