Leveraging sensor information from portable devices towards automatic driving maneuver recognition

Abstract

With the proliferation of smart portable devices, more people have started using them within the vehicular environment while driving. Although these smart devices provide a variety of useful information, using them while driving significantly affects the driver's attention towards the road. This can in turn cause driver distraction and lead to increased risk of crashes. On the positive side, these devices are equipped with powerful sensors which can be effectively utilized towards driver behavior analysis and safety. This study evaluates the effectiveness of portable sensor information in driver assistance systems. Available signals from the CAN-bus are compared with those extracted from an off-the-shelf portable device for recognizing patterns in driving sub-tasks and maneuvers. Through our analysis, a qualitative feature set is identified with which portable devices could be employed to prune the search space in recognizing driving maneuvers and possible instances of driver distraction. An absolute improvement of 15% is achieved with portable sensor information compared to CAN-bus signals, which motivates further study of portable devices to build driver behavior models for driver assistance systems.

Driver classification and driving style recognition using inertial sensors

“…Subsequent research has focus on implementing these systems on a smartphone. Sathyanarayana et al [15] used SVM and other classifying techniques to show detecting driving events from smartphones using inertial sensors works equally well, if not better, compared to using the CAN signals from the vehicles. However these research only focus on driving event detection and classification.…”

Multi-source information fusion for drowsy driving detection based on wireless sensor networks

“…The proposed system was consisted of a physiological signal-acquisition module to monitor longterm EEG and an embedded signal-processing module to detect real-time drowsiness. The research in [6], [7] and [8] had developed devices to recognize driving maneuvers and driver distraction. The proposed device adopted video recordings, GPS latitude and longitude for driving maneuver recognition to build driver behavior models.…”

Overlapped-speech detection with applications to driver assessment for in-vehicle active safety systems

“…This study incorporates maneuver recognition and analysis algorithms presented in [23,14]. However, no further analysis was made in [14] on the contextual information of the speech taken place.…”

“…However, as shown in [23,14], sensor information extracted from low cost portable devices can provide more accurate maneuver recognition. In this study, to better understand the influence of in-vehicle speech on driving performance, we collect in-vehicle speech along with all the available sensor information on the smart portable device (i.e., Tablet) in the UTDrive setup.…”

“…3 shows the inside of the UTDrive vehicle and the mounted Tablet. For more information about the maneuver recognition system see [23,14]. Fig.…”