Four days ago, on October the first 2019, a news article came out about the Dutch police force introducing smart cameras to counter smartphone use by drivers. The camera and its software are able to identify smartphones, tablets and other electronics devices and whether they are held by drivers (RTLNieuws, 2019). After reading the article, I shared the news with my housemates. Being both frequent drivers, who often witness smartphone use by other drivers, they shared my positive attitude towards the introduction of this camera.
A study conducted by an American institute, which investigates road safety, monitored 3,500 drivers by using dash cameras and other surveillance equipment. In case of an accident, the researchers looked into what the driver was doing before the moment occurred. This investigation concluded that using a smartphone increased the risk of an accident by six times (Dingus, et al, 2016). These figures help explain why the Dutch government is so extensively campaigning to discourage distracted driving. Despite these efforts, the Dutch police force handed out over 80,000 fines of 240 euro last year for handheld calls (Politie.nl, 2019).
Electronic device distraction causing accidents on the road is the reason the police invested in this machine learning based technology (Politie.nl). Machine learning, a subset of artificial intelligence, allows computer systems to perform a task without explicit instructions (Bishop, 2006). By the input of training data, machine learning algorithms build a mathematical model relying on patterns and inference to identify, in this case, electronic device use on the road. These models learn via training date, which is the input data and the expected outputs (Gonfalonieri, 2019). In the past months, the police have trained the model with input data of pictures displaying drivers holding different kind of objects (Oostvogels, 2019). By telling the computer when an electronic device is used, they gave expected outputs for the model. If the police camera identifies an electronic device held by a drive, the camera makes a picture and send it to the police officer on duty. The officer still has to verify if indeed an electronic device is used before a fine is send to the driver (RTLnieuws, 2019).
I strongly agree with the introduction of the smart camera. Like my housemates, I still witness fellow road users using their smartphone while they should be paying attention to the road. Because campaigning against distracted driving does not have a satisfying effect, a higher likelihood of receiving a fine will hopefully help. I am curious about your thoughts on this topic and whether this post made you think of other emerging technologies the police could adopt, let me know in the comments!
References:
Bishop, C. M. (2006). Pattern recognition and machine learning.
Dingus, T. A., Guo, F., Lee, S., Antin, J. F., Perez, M., Buchanan-King, M., & Hankey, J. (2016). Driver crash risk factors and prevalence evaluation using naturalistic driving data. Proceedings of the National Academy of Sciences, 113(10), 2636-2641
Gonfalonieri, A. (2019). How to Build A Data Set For Your Machine Learning Project. Retrieved from https://towardsdatascience.com/how-to-build-a-data-set-for-your-machine-learning-project-5b3b871881ac
Politie Nederland. Inzet slimme camera´s tegen afleiding in het verkeer. Retrieved from https://www.politie.nl/nieuws/2019/september/30/00-inzet-slimme-cameras-tegen-afleiding-in-het-verkeer.html.
Oostvogels, B. (2019, October 1). Zo werken de slimme smartphone-‘flitspalen’ van de politie. Retrieved from https://autorai.nl/zo-werken-de-slimme-smartphone-flitspalen-van-de-politi.
RTL Nieuws. Politie zet vanaf vandaag camera’s in tegen appende automobilisten. (2019, September 30). Retrieved from https://www.rtlnieuws.nl/nieuws/nederland/artikel/4867361/camera-controle-appen-achter-stuur-auto-politie-boete-240-euro.
