Click on the blue word "
ON Semiconductor
" above to follow us
Much has been written about the rapid proliferation of advanced driver assistance systems (ADAS) in modern vehicles. The primary purpose of these systems is to improve road safety and is a necessary step towards the fully autonomous vehicles of the future.
Vehicles increasingly have multiple cameras looking outside the vehicle to detect and identify objects in the vehicle's path, or to read roadside signs and control the vehicle.
Other cameras monitor the vehicle's perimeter to maintain lanes on highways or help park safely in crowded spaces.
While these life-saving systems are making significant progress, the most dangerous part of any vehicle remains the driver, and more specifically, their distraction and poor decision-making. Sometimes referred to as the "nut behind the wheel," the National Highway Traffic Safety Administration (NHTSA) has shown that drivers are responsible for more than 90 percent of road accidents.
Automakers and safety regulators are aware that ADAS systems have limited capabilities, and that if the driver is distracted, the likelihood of an accident is still high - even with ADAS. As a result, cameras and vision systems are now being added to the interior to monitor the driver and, increasingly, other occupants as well.
In fact, these driver monitoring cameras (DMC) are considered so important to road safety that the European New Car Assessment Programme (Euro NCAP) has made them a primary safety feature from 2020. By discreetly pointing the camera at the driver and adding advanced image processing software, ADAS systems can measure many things that contribute to road safety.
ADAS systems equipped with DMC can tell if a driver is looking at the road ahead or trying to read a message on a smartphone. It can detect if a driver is seriously ill and incapacitated, and more advanced systems can use facial expressions as cues to infer a driver’s emotional state.
If an accident occurs, the same camera can detect the size, weight and position of the driver and adjust the airbag deployment accordingly, reducing the risk of injury.
Extending the field of view is the Occupant Monitoring Camera (OMC), which further improves safety by detecting the presence of other people in the cabin. With OMC, ADAS systems are able to determine if children or pets are present and if seat belts are being used. Detecting the presence of children in the vehicle, especially unattended children, will be a future requirement.
Safety is the main goal of DMC and OMC, and they also provide many convenience features. DMC is able to detect the driver and adjust the cabin according to their preferences (seat position, climate control, etc.). When using toll roads, advanced biometrics can be used to authorize payments. OMC can record dangerous passengers in taxis to provide safety for drivers.
To demonstrate the capabilities of this technology, ON Semiconductor, together with ecosystem partners, has developed a complete in-cabin monitoring system with DMC and OMC. The core of the system is a 1-megapixel (MP) global shutter AR0144AT image sensor and three 2.3-megapixel red, green, blue and infrared (RGB-IR) image sensors.
The multi-camera system uses Ambarella's CV2AQ system-on-chip (SoC) to process real-time high-quality RGB-IR video and integrates Eyeris' AI software to perform complex body and facial analysis, passenger activity monitoring and object detection.
Driver and occupant monitoring applications require the ability to capture images under variable lighting conditions from direct sunlight to pitch black. RGB-IR CMOS image sensor technology features excellent near-infrared (NIR) sensitivity, 3.0 μm backside illumination (BSI), and triple-exposure high dynamic range (HDR), providing full HD 1080p output. These sensors are sensitive to both RGB and infrared (IR) light, capable of capturing color images during the day, and black-and-white IR images with NIR illumination.
【Previous Reading】
Please click to read the original text to learn more.