Capturing the Image of Occupants Inside the Car by using Inside-Car Camera during Vehicle Collision

Jump To References Section

Authors

  • Department of Computer Applications, St Peter’s University, Avadi , Chennai – 600054, Tamil Nadu ,IN
  • Department of Computer Applications, St Peter’s University, Avadi , Chennai – 600054, Tamil Nadu ,IN

DOI:

https://doi.org/10.15613/sijrs/2016/v3i2/157300

Keywords:

Inside-Car Camera, Or-and Graph (OAG), Sensory Systems, Static Position, Vehicle Collision.

Abstract

The safety concern in means of transport has been considerably increased in last few decades. Distinct Sensory systems have been applied inside and outside vehicles in order to save lives. In this regard, imaging and vision system are used for capturing the static position of the passengers inside the vehicle during collision. There are many approaches to capture an image concatenation from a camera and to analyze them. The image of the passengers is captured during rear end vehicle collision by an inside car camera which is fixed on the left top of front windshield and an event parsing algorithm identifies the collision that has occurred. The decomposing of the collision activity is classified into three activity and uses the Or-And Graph (OAG) to compose the compositions of the temporal relationship among the collision detection. An online parsing (OP) algorithm for OAG formed from Earle's parser is employed to parse the image and identify the passenger's condition. This technique could be used as an enhancement for the safety of the passengers and to provide immediate assistance during vehicle collision.

Downloads

Published

2016-12-01

Issue

Section

Computer Science

 

References

Betke M, Glu EHOA, Davis LS. Real-time multiple vehicle detection and tracking from a moving vehicle. Machine Vision and Applications. 2000; 12(2):69–83. https://doi.org/10.1007/s001380050126

Earley JC. An efficient contex-free parsing algorithm [PhD thesis]. Carnegie-Mellon Univ; 1968.

Han S, Hang Y, Hahn H. Vehicle detection method using Haar-Like feature on real time system. World Academy of Science, Engineering and Technology. 2009; 59.

Hom BKP, Fang Y, Masaki I. Time to contact relative to a planar surface. Proceedings of the 2007 IEEE Intelligent Vehicles Symposium; 2007. p. 68–74.

Liu W, Wen Y, Duan B, Yuan H, Wang N. Rear vehicle detection and tracking for lane change assist. Proceedings of the 2007 IEEE Intelligent Vehicles Symposium; Istanbul. p.252–7. https://doi.org/10.1109/ivs.2007.4290123

Shashua A, Dagan E, Mano O, Stein GP. Forward collision warning with a single camera. Proceedings of the 2004 IEEE Intelligent Vehicles Symposium; 2004. p. 37–42.

Song GY, Lee KY, Lee W. Vehicle detection by edge-based candidate generation and appearance-based classification. Proceedings of the 2008 Intelligent Vehicles Symposium; https://doi.org/10.1109/ivs.2008.4621139

Stain GP, Rushinek E, Hayun G, Shashua A. A computer vision system on a chip: a case study from the automotive domain. IEEE Computer Society Conference on Computer Vision and Pattern Recognition; 2005. https://doi.org/10.1109/ cvpr.2005.387

Viola P, Jones M. Rapid object detection using a boosted cascade of simple. Proc IEEE Conference on Computer Vision and Pattern Recognition; 2001. p. 511–8.

Wedel A, Franke U. Monocular video serves RADAR-based emergency braking. Proceedings of the 2007 IEEE Intelligent Vehicles Symposium; 2007. p. 93–8. https://doi.org/10.1109/ivs.2007.4290097