Detecting Drivers Smartphone: A Learned Features Approach using Aggregated Scalogram Images

In this paper, we propose an image representation approach for detecting driver mobile phone from the accelerometer signals produced by a set of smartphones in a vehicle. Rather than following the classic paradigm of classifying the signal as driver or non-driver, we propose an original paradigm whereby we aggregate the signals together and train a classifier to detect the driver signal in that aggregation. We do so by stacking-up the Scalograms images of the smartphone signals and training a CNN classifier to identify the driver's Scalograms instance in the Scalograms stack image. To the best our knowledge, this is the first time such an image-fusion and classification scheme is proposed for detecting driver's smartphone. Experiments performed with an in-house dataset confirms the potential and the merit of our approach.