Driver Activity Assessment with a Machine Vision System

Matti Kutila, Giulia Biamino, Gustav Markkula, Natan Parra

Research output: Contribution to conferenceConference articleScientific

Abstract

A camera vision system is implemented for detecting the driver's gaze and head orientations and detecting the momentary attention targets by using a mapping algorithm. In the developed rule-base classification algorithm, the cockpit view is divided into four clusters of interest: road ahead, windscreen, and left and right exterior mirrors. The early field experiments prognosticate up to 80 % performance for visual distraction detection. Cognitive distraction may occur rapidly, e.g. the mobile phone rings and the conversation steals the driver's attention. Moreover, the assumption is that one parameter alone does not reveal the distraction, but rather by fusing multiple sensor data, the robustness of the detection can be improved. For this reason the work carried out promotes use of the multi-dimensional support vector machine classification method to retrieve possible cognitive workload. According to the laboratory experiments the performance is varying between 68 - 86 % depending on the actual environmental factors.
Original languageEnglish
Pages71-72
Publication statusPublished - 2008
MoE publication typeNot Eligible
EventXXXIX Annual Conference of Italian Operational Research Society, AIRO2008: Optimisation and logistics in transportation and communication networks - Ischia, Italy
Duration: 8 Sep 200811 Sep 2008

Conference

ConferenceXXXIX Annual Conference of Italian Operational Research Society, AIRO2008
CountryItaly
CityIschia
Period8/09/0811/09/08

Fingerprint

Computer vision
Windshields
Mobile phones
Support vector machines
Experiments
Cameras
Sensors

Keywords

  • camera
  • distraction
  • visual workload
  • cognitive workload
  • driver
  • vehicle
  • algorithm

Cite this

Kutila, M., Biamino, G., Markkula, G., & Parra, N. (2008). Driver Activity Assessment with a Machine Vision System. 71-72. Paper presented at XXXIX Annual Conference of Italian Operational Research Society, AIRO2008, Ischia, Italy.
Kutila, Matti ; Biamino, Giulia ; Markkula, Gustav ; Parra, Natan. / Driver Activity Assessment with a Machine Vision System. Paper presented at XXXIX Annual Conference of Italian Operational Research Society, AIRO2008, Ischia, Italy.
@conference{0a1d352d8ef74521bd0717b65258ed71,
title = "Driver Activity Assessment with a Machine Vision System",
abstract = "A camera vision system is implemented for detecting the driver's gaze and head orientations and detecting the momentary attention targets by using a mapping algorithm. In the developed rule-base classification algorithm, the cockpit view is divided into four clusters of interest: road ahead, windscreen, and left and right exterior mirrors. The early field experiments prognosticate up to 80 {\%} performance for visual distraction detection. Cognitive distraction may occur rapidly, e.g. the mobile phone rings and the conversation steals the driver's attention. Moreover, the assumption is that one parameter alone does not reveal the distraction, but rather by fusing multiple sensor data, the robustness of the detection can be improved. For this reason the work carried out promotes use of the multi-dimensional support vector machine classification method to retrieve possible cognitive workload. According to the laboratory experiments the performance is varying between 68 - 86 {\%} depending on the actual environmental factors.",
keywords = "camera, distraction, visual workload, cognitive workload, driver, vehicle, algorithm",
author = "Matti Kutila and Giulia Biamino and Gustav Markkula and Natan Parra",
year = "2008",
language = "English",
pages = "71--72",
note = "XXXIX Annual Conference of Italian Operational Research Society, AIRO2008 : Optimisation and logistics in transportation and communication networks ; Conference date: 08-09-2008 Through 11-09-2008",

}

Kutila, M, Biamino, G, Markkula, G & Parra, N 2008, 'Driver Activity Assessment with a Machine Vision System' Paper presented at XXXIX Annual Conference of Italian Operational Research Society, AIRO2008, Ischia, Italy, 8/09/08 - 11/09/08, pp. 71-72.

Driver Activity Assessment with a Machine Vision System. / Kutila, Matti; Biamino, Giulia; Markkula, Gustav; Parra, Natan.

2008. 71-72 Paper presented at XXXIX Annual Conference of Italian Operational Research Society, AIRO2008, Ischia, Italy.

Research output: Contribution to conferenceConference articleScientific

TY - CONF

T1 - Driver Activity Assessment with a Machine Vision System

AU - Kutila, Matti

AU - Biamino, Giulia

AU - Markkula, Gustav

AU - Parra, Natan

PY - 2008

Y1 - 2008

N2 - A camera vision system is implemented for detecting the driver's gaze and head orientations and detecting the momentary attention targets by using a mapping algorithm. In the developed rule-base classification algorithm, the cockpit view is divided into four clusters of interest: road ahead, windscreen, and left and right exterior mirrors. The early field experiments prognosticate up to 80 % performance for visual distraction detection. Cognitive distraction may occur rapidly, e.g. the mobile phone rings and the conversation steals the driver's attention. Moreover, the assumption is that one parameter alone does not reveal the distraction, but rather by fusing multiple sensor data, the robustness of the detection can be improved. For this reason the work carried out promotes use of the multi-dimensional support vector machine classification method to retrieve possible cognitive workload. According to the laboratory experiments the performance is varying between 68 - 86 % depending on the actual environmental factors.

AB - A camera vision system is implemented for detecting the driver's gaze and head orientations and detecting the momentary attention targets by using a mapping algorithm. In the developed rule-base classification algorithm, the cockpit view is divided into four clusters of interest: road ahead, windscreen, and left and right exterior mirrors. The early field experiments prognosticate up to 80 % performance for visual distraction detection. Cognitive distraction may occur rapidly, e.g. the mobile phone rings and the conversation steals the driver's attention. Moreover, the assumption is that one parameter alone does not reveal the distraction, but rather by fusing multiple sensor data, the robustness of the detection can be improved. For this reason the work carried out promotes use of the multi-dimensional support vector machine classification method to retrieve possible cognitive workload. According to the laboratory experiments the performance is varying between 68 - 86 % depending on the actual environmental factors.

KW - camera

KW - distraction

KW - visual workload

KW - cognitive workload

KW - driver

KW - vehicle

KW - algorithm

M3 - Conference article

SP - 71

EP - 72

ER -

Kutila M, Biamino G, Markkula G, Parra N. Driver Activity Assessment with a Machine Vision System. 2008. Paper presented at XXXIX Annual Conference of Italian Operational Research Society, AIRO2008, Ischia, Italy.