Sensing vehicle dynamics for determining driver phone use

Wang, Yan; Yang, Jie; Liu, Hongbo; Chen, Yingying; Gruteser, Marco; Martin, Richard P.

doi:10.1145/2462456.2464447

Cited by 146 publications

(89 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sampling rate of the microphone on smartphone is up to 44.1kHz. The high sampling rate and the multi-microphone enable other novel applications, such as BeepBeep [22] (a pairwise acoustic ranging system for COTS devices), phone-to-phone 3D localization [24], ENSBox [12] (a distributed and self-calibrating localization system for outdoor environments), and driver detection [35,34].…”

Section: Hardware Supportmentioning

confidence: 99%

Context-free Attacks Using Keyboard Acoustic Emanations

Zhu

Zhang

et al. 2014

Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security

132

View full text Add to dashboard Cite

The emanations of electronic and mechanical devices have raised serious privacy concerns. It proves possible for an attacker to recover the keystrokes by acoustic signal emanations. Most existing malicious applications adopt contextbased approaches, which assume that the typed texts are potentially correlated. Those approaches often incur a high cost during the context learning stage, and can be limited by randomly typed contents (e.g., passwords). Also, context correlations can increase the risk of successive false recognition. We present a context-free and geometry-based approach to recover keystrokes. Using off-the-shelf smartphones to record acoustic emanations from keystrokes, this design estimates keystrokes' physical positions based on the Time Difference of Arrival (TDoA) method. We conduct extensive experiments and the results show that more than 72.2% of keystrokes can be successfully recovered.

show abstract

Section: Hardware Supportmentioning

confidence: 99%

Context-free Attacks Using Keyboard Acoustic Emanations

Zhu

Zhang

et al. 2014

Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security

132

View full text Add to dashboard Cite

show abstract

“…whether the recipient can reply to the call, or should the call be transferred to voicemail or respond with an automatic message [20]. Papers [3] and [4] proposed to use the sensors in a Smartphone such as gyroscopes and accelerometers to detect the position of the camera phone thus determining the position of the person using it.…”

Section: Related Workmentioning

confidence: 99%

“…In [14], the authors exploit the insight that the centripetal the sensed image (the captured image which is compared with the reference image) are acquired.…”

Section: Related Workmentioning

confidence: 99%

Camera Based Localization of a Smartphone in a Vehicle

Paruchuri¹

2016

JCSAIT

View full text Add to dashboard Cite

Open Access Research articleand Prevention (CDC), in year 2011 alone, 3,331 people were killed in accidents involving a distracted driver [18]. CDC also reports that around 31% of the drivers were reported to have used the text message or email features while driving. Combining these data, around 1,033 people were killed by texting and driving.Even without the statistical data, it is evident that cell phone usage while driving is a major distraction. The consequences of distracted driving are well recognized. In United States, as of March 2016, 14 states have laws that ban driving while talking on a handheld cell phone, and Forty-six States, ban text messaging for all drivers [2].Detecting vehicular movement is straightforward but ascertaining whether the user is indeed the driver is a complex problem. The fundamental problem of distinguishing between a driver and passenger using a mobile phone is the critical input to enable numerous safeties and interface enhancements. As in prior work, we seek to determine the in-vehicle location of the phone and use that as a heuristic to determine whether the phone is used by the driver or passenger. It uses a fundamentally different sensing approach to determine this location.Determining the movement of a vehicle is simple in that the speed can be calculated by using data from the GPS. Based on the speed determined, after a preselected speed, the cell phone can be disabled; or at least functions such as texting, games, can be disabled. However, determining if the user of the cell phone is indeed the driver is a challenging step. For an application that limits Smartphone functionality for a driver to execute successfully, the cell phone should be disabled only when it is used by a person driving a vehicle.Determining position of a Smartphone in a vehicle can enable and provide context for numerous interesting in-vehicle applications, including driver distraction prevention, driving behaviour estimation, in-vehicle services customization, etc. However, most of the existing work on in-vehicle positioning relies on special infrastructures, such as the stereo, cigarette lighter adapter or OBD (on-board diagnostic) adapter. In this paper, we propose an infrastructure-free, in-vehicle positioning system via smart phones. Our methodology uses only embedded camera in smart phones to determine the phones' seat-level locations in a vehicle. AbstractDistracted driving is any activity that could divert a person's attention away from the primary task of driving. All distractions endanger driver, passenger, and bystander safety. Cell phone usage while driving is a major distraction. Multiple solutions have been proposed on limiting smart phone functionality when being used by a driver. However, it remains challenge to detect if it is indeed the driver using the Smartphone.The objective of this paper is to address the fundamental problem of distinguishing the driver from passengers, non-intrusively, i.e., enabling driver phone detection without relying on any particular situations, events...

show abstract

“…Automotive Sensing. Recent research has also explored complementary problems in the automotive space, such as sensing driving behavior using vehicle sensors, phone sensors, and specialized cameras [10,2,54,55,52,53]. These algorithms can be modeled as individual predicates in CAR-LOG, so that higher level predicates can be defined using these detection algorithms.…”

Section: Related Workmentioning

confidence: 99%

Carlog

Jiang

Qiu

McCartney

et al. 2014

Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems

View full text Add to dashboard Cite

Automotive apps can improve efficiency, safety, comfort, and longevity of vehicular use. These apps achieve their goals by continuously monitoring sensors in a vehicle, and combining them with information from cloud databases in order to detect events that are used to trigger actions (e.g., alerting a driver, turning on fog lights, screening calls). However, modern vehicles have several hundred sensors that describe the low level dynamics of vehicular subsystems, these sensors can be combined in complex ways together with cloud information. Moreover, these sensor processing algorithms may incur significant costs in acquiring sensor and cloud information. In this paper, we propose a programming framework called CARLOG to simplify the task of programming these event detection algorithms. CARLOG uses Datalog to express sensor processing algorithms, but incorporates novel query optimization methods that can be used to minimize bandwidth usage, energy or latency, without sacrificing correctness of query execution. Experimental results on a prototype show that CARLOG can reduce latency by nearly two orders of magnitude relative to an unoptimized Datalog engine.

show abstract

Sensing vehicle dynamics for determining driver phone use

Cited by 146 publications

References 23 publications

Context-free Attacks Using Keyboard Acoustic Emanations

Context-free Attacks Using Keyboard Acoustic Emanations

Camera Based Localization of a Smartphone in a Vehicle

Carlog

Contact Info

Product

Resources

About