Vehicle Maneuvering-style Recognition in identifying the Culprit for a Road Accident

Muhammad Shoaib Siddiqui

Keywords: maneuvering style; road-side accident, classification; feature extraction; driving style; driving activity.

Issue I, Volume I, Pages 165-184

One of main reasons of road-side accidents (RSA) is the reckless by the driver. Reckless

drivers induce danger on the road and their surroundings, which could result in deadly accidents

both on road and off the road. High acceleration, frequent lane changes, lane changing in high

speed, turning at high speed, and braking late or suddenly are some of the activities by drivers that

cause these deadly accidents. In this paper, we have proposed and developed a driving style

recognition system, which would alert the driver to drive safely. It would also help in identifying

the driver at mistake during a road-side accident. In this paper, we have gathered data from an

accelerometer and a gyroscope to recognize the vehicle maneuvering style of the driver. We have

applied and compared the results of two well-known classifiers, i.e. Support Vector Machine

(SVM) and K-Nearest Neighbor (KNN) to identify the driving activity. We have also explored

different features extraction techniques to identify the best solution. After, the driving activity is

recognized, it is further classified to detect the driving style, as reckless or adequate. Later on, the

system can generate alarm to the driver through an actuator and use a weight-based algorithm to

identify the driver at fault, based on the driving style, in case of a RSA.

[1] “Report: Saudi Arabia records 526,000 road accidents annually”, Saudi Gazette on Dec. 31, 2015,

http://english.alarabiya.net/en/News/middle-east/2016/01/01/Report-Saudi-Arabia-records-526-

000-road-accidents-annually.html

[2] AM Al-Atwai and W Saleh, “Identification assessment and the enhancement of accident data

collection and analysis in KSA” WIT Transactions on the Built Environment, Vol. 138, 2014

[3] T. Nedal et al., “Characterization of crash-prone drivers in Saudi Arabia – A multivariate analysis”,

Case Studies on Transport Policy, Volume 5, Issue 1, 2017, pp. 134-142

[4] UB Gaffar, SM Ahmed, “A Review of Road traffic accident in Saudi Arabia: the neglected

epidemic”, Indian Journal of Forensic and Community Medicine, 2015;2(4):242-246

[5] “Traffic Accidents In The Kingdom By Region And Place Of Accident”, Ministry of Interior -

General Directorate of Traffic, Saudi Open Data, http://www.data.gov.sa/en/dataset/trafficaccidents

[6] “Driver Activity Recognition in identifying the Culprit for a Road Accident” has been published

by the International Journal of Research and Analytical Reviews (IJRAR), ISBN- 2349-5138

(print); 2348-1269 (online). IJRAR August 2018, Volume 5, Issue 3, page no. 755-761

[7] Khan, A.M.; Tufail, A.; Khattak, A.M.; Laine, T.H. Activity Recognition on Smartphones via

Sensor-Fusion and KDA-Based SVMs. Int. J. Distrib. Sens. Netw. 2014, 2014, 1–14.

[8] Thammasat, E.; Chaicharn, J. A simply fall-detection algorithm using accelerometers on a

smartphone. Proceedings of the Biomedical Engineering International Conference (BMEiCON),

Ubon Ratchathani, Thailand, 5–7 December 2012.

[9] Song, K.-T.; Wang, Y.Q. Remote activity monitoring of the elderly using a two-axis accelerometer.

Proceedings of the CACS Automatic Control Conference, Tainan, Taiwan, November 18–19, 2005.

[10] M. Mladenov, M. Mock, "A Step Counter Service for Java-Enabled Devices Using a Built-in

Accelerometer", Proc. 1st Int'l Workshop Context-Aware Middleware and Services (CAMS), pp.

1-5, 2009.

[11] Hemminki, S.; Nurmi, P.; Tarkoma, S. Accelerometer-based Transportation Mode Detection on

Smartphones. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor

Systems (SenSys ’13), Roma, Italy, 11–15 November 2013.

[12] Cervantes-Villanueva, J.; Carrillo-Zapata, D.; Terroso-Saenz, F.; Valdes-Vela, M.; Skarmeta, A.F.

Vehicle maneuver detection with accelerometer-based classification. Sensors 2016, 16, 1618.

[13] Lara, O.D.; Labrador, M.A. A Survey on Human Activity Recognition using Wearable Sensors.

IEEE Commun. Surv. Tutor. 2013, 15, 1192–1209.

[14] Shoaib, M.; Bosch, S.; Incel, O.D.; Scholten, H.; Havinga, P.J. A survey of online activity

recognition using mobile phones. Sensors 2015, 15, 2059–2085.

[15] Attal, F.; Mohammed, S.; Dedabrishvili, M. Physical Human Activity Recognition Using Wearable

Sensors. Sensors 2015, 15.

[16] Preece, S.J.; Goulermas, J.Y.; Kenney, L.P.; Howard, D.; Meijer, K.; Crompton, R. Activity

identification using body-mounted sensors—A review of classification techniques. Physiol. Meas

2009, 30, R1–R33

[17] Wang, S.; Chen, C.; Ma, J. Accelerometer based transportation mode recognition on mobile

phones. In Proceedings of the IEEE 2010 Asia-Pacific Conference on Wearable Computing

Systems, Shenzhen, China, 17–18 April 2010; pp. 44–46.

[18] Vaitkus, V.; Lengvenis, P.; Žylius, G. Driving style classification using long-term accelerometer

information. In Proceedings of the 2014 19th International Conference On Methods and Models in

Automation and Robotics (MMAR), Miedzyzdroje, Poland, 2–5 September 2014; pp. 641–644.

[19] Dai, J.; Teng, J.; Bai, X.; Shen, Z.; Xuan, D. Mobile phone based drunk driving detection. In

Proceedings of the 2010 4th International Conference on Pervasive Computing Technologies for

Healthcare, London, UK, 1–3 April 2010; pp. 1–8.

[20] Anguita, D.; Ghio, A.; Oneto, L.; Parra, X.; Reyes-Ortiz, J.L. Ambient Assisted Living and Home

Care. In Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly

Support Vector Machine, Proceedings of the 4th International Workshop (IWAAL 2012), Vitoria-

Gasteiz, Spain, 3–5 December 2012; Springer: Berlin/Heidelberg, Germany, 2012; pp. 216–223.

[21] Thiemjarus, S.; Henpraserttae, A.; Marukatat, S. A study on instance-based learning with reduced

training prototypes for device-context-independent activity recognition on a mobile phone. In

Proceedings of the 2013 IEEE International Conference on Body Sensor Networks (BSN),

Cambridge, MA, USA, 6–9 May 2013; pp. 1–6.

[22] A.M. Khan, Y.-K. Lee, S.Y. Lee, and T.-S. Kim. Human activity recognition via an accelerometer

enabled-smartphone using kernel discriminant analysis. In Proceedings of the 5th International

Conference on Future Information Technology, pages 1–6, 2010

[23] Abdi H, Williams LJ. Principal component analysis. Wiley interdisciplinary reviews:

computational statistics. 2010 Jul;2(4):433-59.

[24] Akaike, Hirotugu. "Fitting autoregressive models for prediction." Annals of the institute of

Statistical Mathematics 21, no. 1 (1969): 243-247.

[25] MotionNode Specification. https://www.motionnode.com/MotionNode_Specification.pdf, 2018

(accessed 20 December 2018).

[26] Balakrishnama, Suresh, and Aravind Ganapathiraju. "Linear discriminant analysis-a brief tutorial."

Institute for Signal and information Processing 18 (1998): 1-8.

[27] Bianchi, Giovanni, and Roberto Sorrentino. Electronic filter simulation & design. McGraw Hill

Professional, 2007.

[28] Zhang, Yong, Junjie Li, Yaohua Guo, Chaonan Xu, Jie Bao, and Yunpeng Song. "Vehicle Driving

Behavior Recognition Based on Multi-View Convolutional Neural Network (MV-CNN) with Joint

Data Augmentation." IEEE Transactions on Vehicular Technology (2019).

[29] World Health Organization (WHO): Global status report on road safety 2018,

https://apps.who.int/iris/bitstream/handle/10665/276462/9789241565684-eng.pdf?ua=1 (accessed

on March 10th, 2019)

[30] Aldegheishem, Abdulaziz, Humera Yasmeen, Hafsa Maryam, Munam Shah, Amjad Mehmood,

Nabil Alrajeh, and Houbing Song. "Smart road traffic accidents reduction strategy based on

intelligent transportation systems (tars)." Sensors 18, no. 7 (2018): 1983.