SafeWatch

Abstract

Driving with distraction or losing alertness increases the risk of the traffic accident. The emerging Internet of Things (IoT) systems for smart driving hold the promise of significantly reducing road accidents. In particular, detecting the unsafe hand motions and warning the driver using smart sensors can improve the driver's self-alertness and the driving skill. However, due to the impact of the vehicle's movement and the significant variation across different driving environments, detecting the position of the driver's hand is challenging. This paper presents SafeWatch -a system that employs commodity smartwatches and smartphones to detect the driver's unsafe behaviors in a real-time manner. SafeWatch infers driver's hand motions based on several important features such as the posture of the driver's forearm and the vibration of the smartwatch. SafeWatch employs a novel adaptive training algorithm which keeps updating the training dataset at runtime based on inferred hand positions in certain driving conditions. The evaluation with 75 real driving trips from 6 subjects shows that SafeWatch achieves over 97.0% recall and precision rates in detecting of the unsafe hand positions. CCS CONCEPTS•Human-centered computing →Ubiquitous and mobile computing;

MagTrack

“…In terms of driving applications, there are ear-worn head nodding detectors [4]. Particularly, previous work [7] used two smartwatches and a smartphone to monitor manual distractions. Compared to such multi-wearable designs, our system has three unique advantages: first, the magnetic tags are low cost and they don't require battery recharge.…”

“…Wearable technologies have been used to monitor driving activity. For example, previous research used inertial measurement units (IMUs), commonly found on smartwatches, to detect erratic steering wheel movements [6] and manual distractions [7], but these solutions are limited to the detection of the hands where smartwatches are worn. Therefore, the development of reliable, robust, and low-cost technologies to monitor various driver activities is desirable.…”

dWatch

“…Because the driver's driving posture when holding the steering wheel is similar to the posture of other events, such as the user holding a book on the table with both hands or holding the left and right sides of an iPad, only д x,watch is used to detect the forearm gesture of the driver's hand holding the steering wheel is not enough. So we introduce the vibration signal in the vertical direction, which is one feature that detects whether the driver's hand is on the steering wheel in [5]. When the engine of the vehicle is started, continuous vibration in the vertical direction is generated and radiated into the cockpit.…”

“…In the driving environment, the detection of a relative movement between the vehicle and the driver's hand can be used to indicate that the driver's hand may be operating the steering wheel. We leverage the work from Bi et al [5] to detect if the driver's hand is moving by comparing the acceleration of the smart watch ( a w ) and the acceleration of the smart phone (| a p |) [20]. Since the coordinates of the smart phone and the smart watch are not aligned, the components of the acceleration of the two devices in various directions cannot be directly compared.…”