Occupant classification system for automotive airbag suppression

Farmer, Michael; Jain, Achin

doi:10.1109/cvpr.2003.1211429

Cited by 37 publications

(32 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The camera has no absolute calibration and is subject to considerable drift in both gain and offset with temperature. It does have a mechanism for correcting per pixel gain variation, which employs a shutter that momentarily closes in front of the focal plane array every few minutes [13]. Miniaturization and cost reduction is moving at a rapid pace in LWIR cameras, with roughly a four-fold decrease in both size and price in the last two years.…”

Section: Related Studiesmentioning

confidence: 99%

“…Farmer and Jain [13] presented work on an occupant classification system that addresses the static suppression requirement of the NHTSA standard by a system that is able to discern between four categories of occupants with high detection rates. The static suppression requirement specifies occupant types that, when present in the passenger seat, the airbag system must automatically suppress deployment [1].…”

Section: Related Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Occupant Posture Analysis With Stereo and Thermal Infrared Video: Algorithms and Experimental Evaluation

Trivedi

Cheng

Childers

et al. 2004

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Section: Related Studiesmentioning

confidence: 99%

Section: Related Studiesmentioning

confidence: 99%

Occupant Posture Analysis With Stereo and Thermal Infrared Video: Algorithms and Experimental Evaluation

Trivedi

Cheng

Childers

et al. 2004

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

“…A system of sensors can detect who is currently in the passenger/driver seat by utilizing, for example, weight or posture and automatically adjusting the vehicle to personal needs [140][141][142].…”

Section: Occupant Classification Systems (Ocs)mentioning

confidence: 99%

Multi-Factor Authentication: A Survey

et al. 2018

View full text Add to dashboard Cite

Today, digitalization decisively penetrates all the sides of the modern society. One of the key enablers to maintain this process secure is authentication. It covers many different areas of a hyper-connected world, including online payments, communications, access right management, etc. This work sheds light on the evolution of authentication systems towards Multi-Factor Authentication (MFA) starting from Single-Factor Authentication (SFA) and through Two-Factor Authentication (2FA). Particularly, MFA is expected to be utilized for human-to-everything interactions by enabling fast, user-friendly, and reliable authentication when accessing a service. This paper surveys the already available and emerging sensors (factor providers) that allow for authenticating a user with the system directly or by involving the cloud. The corresponding challenges from the user as well as the service provider perspective are also reviewed. The MFA system based on reversed Lagrange polynomial within Shamir's Secret Sharing (SSS) scheme is further proposed to enable more flexible authentication. This solution covers the cases of authenticating the user even if some of the factors are mismatched or absent. Our framework allows for qualifying the missing factors by authenticating the user without disclosing sensitive biometric data to the verification entity. Finally, a vision of the future trends in MFA is discussed.

show abstract

“…Since it has been shown that there is no universally best classifier, we decided to initially apply the k-nearest neighbour based on its simplicity of implementation [28]. We used a modification of the k-nearest neighbor classifier, which computes the average distance of the test sample to the k-nearest training samples in each class, and then uses the average of this distance as the classification distance [1]. This distance-based k-nearest neighbor classifier is related to the nearest mean classifier, where we compute a pruned mean for each class based on the sorted distances of the training samples, however, we select the top k from each class rather than the top k of the combined set of classes.…”

Section: Classification Of Blob Combinationsmentioning

confidence: 99%

“…We will demonstrate our proposed framework on a vision-based smart airbag application, where the airbag is automatically disabled if the occupant is an infant [1]. The smart airbag application can be defined as a 2-class classification problem: (i) infant (referred to as class 1), (ii) adult (referred to as class 2), where the airbag is suppressed when the passenger is an infant.…”

Section: Introductionmentioning

confidence: 99%

Application of Genetic Algorithms for Wrapper-based Image Segmentation and Classification

Farmer

Shugars

2006 IEEE International Conference on Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

The traditional processing flow of segmentation followed by classification in computer vision assumes that the segmentation is able to successfully extract the object of interest. This is challenging without any prior knowledge about the object that is being extracted from the scene. We previously proposed a method of segmentation that uses the classification subsystem as an integral part of the segmentation, which provides contextual information regarding the objects to be segmented. Our approach integrated segmentation and classification in a manner analogous to wrapper methods in feature selection. We initially perform low-level segmentation to label the image as a set of nonoverlapping blobs. We then use the wrapper framework to select the blobs that comprise the final segmentation based on the classification performance of the wrapper. In this paper, the process of combining the blobs and then evaluating these combinations is performed with a genetic algorithm. We show the performance of the Genetic Algorithm based wrapper segmentation on real-world complex images of automotive vehicle occupants, where our overall classification accuracy is roughly 88% and the resultant segmentations are extremely accurate.

show abstract

Occupant classification system for automotive airbag suppression

Abstract: Abstract

Cited by 37 publications

References 6 publications

Occupant Posture Analysis With Stereo and Thermal Infrared Video: Algorithms and Experimental Evaluation

Occupant Posture Analysis With Stereo and Thermal Infrared Video: Algorithms and Experimental Evaluation

Multi-Factor Authentication: A Survey

Application of Genetic Algorithms for Wrapper-based Image Segmentation and Classification

Contact Info

Product

Resources

About