Vehicle crash predictive and evasive operation system by neural networks

  • US 5,541,590 A
  • Filed: 01/19/1995
  • Issued: 07/30/1996
  • Est. Priority Date: 08/04/1992
  • Status: Expired due to Fees
  • ×
    • Pin
First Claim
Patent Images

1. A system for predicting and evading crash of a vehicle comprising:

  • image pick-up means mounted on the vehicle for picking up images of actual views in a direction of running of the vehicle while running of the vehicle,crash predicting means having a neural network, said neural network containing previously taken image data formed of successive scenes for causing accidents and being trained by a back propagation method for recognizing conditions in image data which cause said accidents, said neural network having an input layer formed of processing elements arranged parallel to each other, said input layer continuously receiving actual image data obtained from the image pick-up means, said neural network receiving the actual image data obtained from the image pick-up means while running of the vehicle, evaluating the actual image data by comparing it to said previously taken image data for causing the accidents, judging if the vehicle is predicted to crash based on the comparison of said previously taken image data with an object noticed in the actual image data of the image pick-up means, and outputting an operational signal in case of prediction of occurrence of a crash with said object, andsafety drive ensuring means connected to said crash predicting means, said safety drive ensuring means, in response to the operational signal, operating to evade the crash between the vehicle and the object for protecting an occupant of the vehicle.

View all claims

    Thank you for your feedback