This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Crash Detection System Using Hidden Markov Models
Technical Paper
2004-01-1781
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
This paper presents the design of a crash detection system based on the principles of continuous-mode Hidden Markov Models (HMM) with real-valued emission parameters. Our design utilizes log-likelihood for optimizing HMM parameters including the number of states in the model and the accelerometer crash-pulse buffer size resulting in lower costs and complexity of the crash detection system. Cross validation technique based on Jackknifing is utilized to estimate the crash pulse detection rate for a variety of crash events involving rigid as well as offset deformable barriers with head-on and oblique angle impacts. The system is simulated using Matlab and Simulink, and the proposed model is able to accurately classify crash-events within 10 ms from the time of the impact.
Recommended Content
Technical Paper | Seat Common Frame Design Optimization |
Technical Paper | Statistical Modeling of Human Liver Incorporating the Variations in Shape, Size, and Material Properties |
Authors
Citation
Singh, G., Song, H., and Chou, C., "Crash Detection System Using Hidden Markov Models," SAE Technical Paper 2004-01-1781, 2004, https://doi.org/10.4271/2004-01-1781.Also In
Safety Test Methodology, and Accelerated Testing and Vehicle Reliability
Number: SP-1879; Published: 2004-03-08
Number: SP-1879; Published: 2004-03-08
References
- Foo Anson Ridella Setphen A. “Advancements in crash sensing.” IEEE Vehicular Technology Society News November 2002 9 13
- Chan Ching-Yao On the detection of vehicular crashes - system characteristics and architecture IEEE Transactions on Vehicular Technology 51 1 2002
- Barnard Robert Riesner Miloslav Vehicular airbag control based on energy, momentum, and semi-metric spaces IEEE Transactions on Vehicular Technology 49 5 2000
- Singh Gautam Song Haiping “Intelligent Algorithms for Early Detection of Automotive Crashes” Society of Automotive Engineers 2002 World Congress & Exhibition , Air Bags (Part A & B) Detroit, MI
- Wuliang Yin Jinhuan Zhang Shilin Huang “Algorithm for airbag actuation based on artificial neural network” Journal of Tsinghua University 39 11 1999
- Liu C.-C. Narayan P. “Order estimation and sequential universal data compression of a hidden markov source by the method of mixtures” IEEE Transactions on Information Theory 40 1167 1180 1994
- Ziv J. Merhav N. “Estimating the number of states of a finite-state source” IEEE Transactions on Information Theory 38 61 65 1992
- Rabiner Lawrence R. “A tutorial on Hidden Markov Models and selected applications in speech recognition” Proceedings of the IEEE 77 2 1989
- Krumm John Kirk Greg “Video occupant detection for airbag deployment” Fourth IEEE Workshop on Applications of Computer Vision October 1998 Princeton, New Jersey, USA
- Bilmes Jeff “What HMMs can do” University of Washington Technical Report , Number UWEETR-2002-0003 Jan. 2003
- Automotive Crash Research: Side impact, rollover and vehicle aggressivity Warrendale, PA Society of Automotive Engineers 2002