Video occupant detection for airbag deployment

نویسندگان

  • John Krumm
  • Greg Kirk
چکیده

When an airbag deploys on a rear-facing infant seat, it can injure or kill the infant. When an airbag deploys on an empty seat, the airbag and the money to replace it are wasted. We have shown that video images can be used to determine whether or not to deploy the passenger-side airbag in a crash. Images of the passenger seat, taken from a video camera mounted inside the vehicle, can be used to classify the seat as either empty, containing a rear-facing infant seat, or occupied. Our first experiment used a single, monochrome video camera. The system was automatically trained on a series of test images. Using a principle components (eigenimages) nearest neighbor classifier, it achieved a correct classification rate of 99.5% on a test of 910 images. Our second experiment used a pair of monochrome video cameras to compute stereo disparity (a function of 3D range) instead of intensity images. Using a similar algorithm, the second approach achieved a correct classification rate of 95.1% on a test of 890 images. The stereo technique has the advantage of being less sensitive to illumination, and would likely work best in a real system.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Occupant Sensing System Using Single Video Camera and Ultra-sonic Sensor for Advanced Airbag

In this paper, we proposed an occupant detection system using single video camera and a distance sensor for an advanced airbag deployment. We detected occupant face using skin color and motion information in real time. The proposed method acquired the color and size of the occupant face using single video camera and calculated the distance information between the occupant and airbag using a dis...

متن کامل

Decision Algorithm for Smart Airbag Deployment Safety Issues

Airbag deployment has been known to be responsible for huge death, incidental injuries and broken bones due to low crash severity and wrong deployment decisions. Therefore, the authorities and industries have been looking for more innovative and intelligent products to be realized for future enhancements in the vehicle safety systems (VSSs). Although the VSSs technologies have advanced consider...

متن کامل

To Appear in IEEE International Symposium on Intelligent Vehicles in Parma, Italy, June 2004. Occupant Posture Analysis using Reflectance and Stereo Images for “Smart” Airbag Deployment

Robust detection of vehicle occupant posture is necessary for intelligent airbag deployment. This paper presents a vision-based method of estimating the size, posture and pose of the occupant. Utilizing raw reflectance and stereo disparity images, this algorithm presents a mixed-mode approach to finding occupant features. Extensive experiments show the robustness of this mixed-mode method in id...

متن کامل

Vehicle Occupant Head Distance Extraction Method using Stereo-Vision

In recent years, the development of airbag system has improved the safety of the occupants. However, the car occupant can be often killed by improper airbag operation. Robust detection of vehicle occupant posture is necessary for a safer intelligent airbag deployment system. This paper presents a stereobased method of estimating the posture of the occupant. Utilizing the disparity images and th...

متن کامل

Abdominal injury with airbag deployment for belted drivers in frontal crashes - biomed 2009.

The risk of moderate or serious abdominal injury is higher for belted drivers in frontal crashes with a deployed airbag than for belted drivers not exposed to a deployed airbag. An analysis of roughly 13,000 belted front seat occupants in frontal crashes from National Automotive Sampling System / Crashworthiness Data System (NASS/CDS) case years 1993-2007 with and without airbag deployment were...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998