Signal Processing - July 2017 - 138

with intelligent transportation systems or V2V or V2I communication, share the information, and realize a wider Internet of
Vehicles. However, the challenges of smartphone platform use
in the vehicle come from the deployment difficulty, measurement accuracy, and system reliability.
In this section, we first discuss the deployment of smartphones as an in-vehicle data collection platform, utilizing its
hardware resources. Additionally, we explore the implementation of the voice-based human-machine interface, and its
capabilities in applications for vehicle/driver telematics.

and GPS within the device provide accurate estimates of vehicle dynamics. Mobile-UTDrive has been further developed to
take advantage of capabilities such as speech recognition and
on-screen map navigation. Figure 9 displays a screenshot of the
Mobile-UTDrive app running on a tablet. Using this approach
has resulted in studies to detect maneuvers and design driving safety systems that combine in-vehicle speech and video
analysis with driving performance evaluation [86], [87]. Freely
distributing this platform will offer researchers the opportunity
to customize their data collection scenarios while maintaining
current goals for naturalistic driving data advancements.
In-vehicle data collection platform:
In previous studies, it has been shown
Mobile-UTDrive app
how vehicle dynamic signals can potentially
Freely distributing
Smartphones contain a variety of useful
replace the information extracted from a
this platform will
sensors, including cameras, microphones,
CAN bus and thereby extend the use of
offer researchers the
inertial measurement units (IMU), and
maneuver recognition and monitoring algoopportunity to customize
GPS. These multichannel signals make the
rithms to any vehicle that uses the app [32],
smartphone a potentially leveraged plat[45]. However, the orientation and relative
their data collection
form for in-vehicle data sensing and monimovement of the smartphone inside the vehiscenarios while
toring, and can be employed for driving
cle yields the main challenge for platform
maintaining current goals
distraction analysis. The use of smart pordeployment. A recent study [88] proposed a
for naturalistic driving
table devices in vehicles creates the possisolution of converting the smartphone-referdata advancements.
bility to record useful data and helps
enced IMU readings into vehicle-referenced
develop a better understanding of driving
accelerations, which allows free positioning
behavior. This option allows a wider range of naturalistic
of smartphones for the in-vehicle dynamics sensing. In this
driving study opportunities for drivers operating their own
proposed framework, the raw smartphone IMU readings are
vehicles [82]-[84].
first processed through a geometry coordinate transformation
The UTDrive mobile app (Mobile-UTDrive) has been
to rotate/reorient the smartphone-referenced accelerations into
developed with the goal of improving driver/passenger safea vehicle-referenced coordinate system. Next, a regression
ty while simultaneously maintaining the ability to establish
model is established to map the relationship between IMU
monitoring techniques that can be used on mobile devices in
and GPS data, and therefore provide an adaptive filtering provarious vehicles [85]. Mobile-UTDrive has been primarily
cess to decouple the smartphone's relative movement in the
used and developed as a multimodal data acquisition platform
vehicle. This serves as a preprocess module and therefore prothat collects driver, vehicle, and environmental information
vides the basis for further applications using the smartphone
describing the comprehensive driving scenario. The modalidata (see Figure 10).
ties captured by Mobile-UTDrive are audio, video, GPS, and
IMU sensor signals. The app runs on any Android-based smart
Voice-based human-machine interaction
portable device and uses the front and rear cameras to record
The smartphone in the vehicle provides easy access to speech
naturalistic driving video as well as in-vehicle audio. The IMU
recording and processing, and offers potential integration with

(a)

(b)

FIGURE 9. The mobile-UTDrive app display showing (a) the original and (b) the updated version [85].
138

IEEE SIGNAL PROCESSING MAGAZINE

July 2017

Table of Contents for the Digital Edition of Signal Processing - July 2017