DMS

The Driver fatigue often becomes a direct cause of many traffic accidents.

Introduction to DMS

The Driver fatigue often becomes a direct cause of many traffic accidents. Therefore, there is a need to develop the systems that will detect and notify a driver of her/him bad psychophysical condition, which could significantly reduce the number of fatigue-related car accidents. However, the development of such systems encounters many difficulties related to fast and proper recognition of a driver’s fatigue symptoms. One of the technical possibilities to implement driver drowsiness detection systems is to use the vision-based approach. This article presents the currently used driver drowsiness detection systems.

Objective

Active safety systems that significantly reduce the number of accidents are among the top priorities for automotive manufacturers. Over the years, engineers have been trying different techniques to detect a drowsy driver, which is one of the most common causes of road accidents. These techniques included analyzing the steering wheel operation, drivers’ brain waves and heartbeat, and monitoring the driver’s response to the designed queries. Despite all these techniques, reliable detection of driver drowsiness remains elusive.

Tek Labs Driver Drowsiness Detection solution leverages an on-board camera to detect eyelid closure of the driver. The on-board camera continuously captures the driver’s face, and the captured video stream is processed in real-time by a proprietary algorithm to detect the drowsiness condition based on the eyelid pattern. As soon as the system identifies an impending unsafe condition, it generates a warning sign so that the driver can react and take immediate action.

Tek Labs proprietary engine for image processing and drowsiness detection The key steps performed by the engine are as below.

Concept

Image acquisition and processing

After the image acquisition by the video camera, a lighting compensation is performed based on the average luminescence of the scenario.
The overall skin of the driver is determined based on the chrominance information of the image. The image is then converted into a binary form and the noise is removed.

Face and eye detection

Using Tek Lab’s proprietary techniques, the binary image is converted to a labeled matrix and facial components are determined to detect the face. The region of interest is reduced to the eye region of the face as shown in the image, on next page.

Pattern analysis for drowsiness detection

TEKLabs’s proprietary algorithm analyzes the pattern of the eyes and eyelid closure to detect driver drowsiness as shown in below picture

Solution Highlights

The Tek Lab’s drowsiness detection solution features the following key attributes:

The algorithm can detect driver drowsiness under various conditions such as:

Drivers with different types of faces, skin colors, eye colors, and facial hair patterns
Various light conditions in the vehicle and noise due to reflection of light from different objects
Scenarios such as a tilted head of the driver
Dynamic detection during driver head movement due to jerks in the vehicle
High speed video processing and detection
Efficient customization through model-based architecture
Scalable and configurable for ease of customization or adding new features such as emotion detection, smile detection, and other dynamic scenarios.
Can support automatic code generation as per MISRA standard for a wide range of Digital Signal Processors
(DSPs) used in advanced driver assistance systems.