Detecting Hazards In Anticipation Of Opening Vehicle Doors

Abstract

The present invention extends to methods, systems, and computer program products for detecting hazards in anticipation of opening vehicle doors. Vehicle sensors (e.g., rear viewing cameras) can be used to detect and classify traffic, for example, as pedestrians, bicyclists, skateboarders, roller skaters, wheel chair, etc., approaching on the side of a vehicle. When there is a possibility of a vehicle occupant opening a door into approaching traffic, a warning can be issued in the vehicle cabin to alert vehicle occupants of the approaching traffic. In one aspect, a vehicle prevents a door from opening if opening the door would likely cause an accident.

1 . A method for use at a vehicle, the method comprising:
 determining that traffic is to pass through a space adjacent to a vehicle door;   determining that the vehicle door poses a hazard to the traffic based at least on: a traffic classification of the traffic, the traffic being determined to pass through the space, and a configuration of the vehicle; and   preventing the vehicle door from opening until the traffic passes the space.   
     
     
         2 . The method of  claim 1 , further comprising calculating a speed and a direction of traffic approaching the vehicle; and
 wherein determining that traffic is to pass through a space adjacent to a vehicle door comprises determining that the traffic is to pass through the space based on the calculated speed and direction.   
     
     
         3 . The method of  claim 1 , further comprising receiving the traffic classification from a neural network. 
     
     
         4 . The method of  claim 3 , wherein receiving the traffic classification comprises receiving a classification indicating that the traffic is one of: a walking pedestrian, a bicyclist, a skate boarder, a wheel chair, or a roller skater. 
     
     
         5 . The method of  claim 1 , further comprising outputting a signal in the cabin of the vehicle to indicate the hazard. 
     
     
         6 . The method of  claim 5 , wherein outputting a signal in the cabin of the vehicle comprises outputting one of: an audible signal, a visual signal, or a haptic signal. 
     
     
         7 . The method of  claim 2 , wherein calculating a speed and a direction of traffic approaching the vehicle comprises calculating the speed and direction of the traffic approaching the vehicle from sensor data collected at the vehicle; and
 further comprising filtering the sensor data prior to calculating the speed and direction of the traffic.   
     
     
         8 . The method of  claim 7 , wherein filtering the sensor data comprises determining the optical flow of the traffic; and
 wherein determining that the traffic is to pass through a space adjacent to a vehicle door comprises determining that the traffic is to pass through the space based on the optical flow of the traffic.   
     
     
         9 . The method of  claim 7 , wherein filtering the sensor data comprises filtering data from a plurality of sensors on a heterogeneous computing platform at the vehicle that includes at least two of: a Central Processing Unit (CPU), a Graphical Processing Unit (GPU), or a Programmable Gate Array (FPGA). 
     
     
         10 . The method of  claim 1 , wherein determining that the vehicle door poses a hazard to the traffic comprises detecting that a door handle for the vehicle door has been actuated. 
     
     
         11 . A vehicle comprising:
 a door;   a processor; and   system memory coupled to the processor and storing instructions configured to cause the processor to:
 determine the traffic is to pass through a space adjacent to the door; 
 determine that the door poses a hazard to the traffic based at least on: a traffic classification of the traffic, the traffic being determined to pass through the space, and a configuration of the vehicle; and 
 prevent the door from opening until the traffic passes the space. 
   
     
     
         12 . The vehicle of  claim 11 , further comprising instructions configured to calculate a speed and direction of traffic approaching the vehicle; and
 wherein instructions configured to cause the processor to determine the traffic is to pass through a space adjacent to the door comprises instructions configured to cause the processor to determine that the traffic is to pass through the space based on the calculated speed and direction.   
     
     
         13 . The vehicle of  claim 11 , further comprising instructions configured to cause the processor to receive the traffic classification from a neural network. 
     
     
         14 . The vehicle of  claim 13 , wherein instructions configured to cause the processor to receive the traffic classification comprises instructions configured to cause the processor to receive a classification indicating that the traffic is one of: a walking pedestrian, a bicyclist, a skate boarder, a wheel chair, or a roller skater. 
     
     
         15 . The vehicle of  claim 11 , further comprising instructions configured to cause the processor to output a signal in the cabin of the vehicle to indicate the hazard. 
     
     
         16 . The vehicle of  claim 15 , wherein instructions configured to cause the processor to output a signal in the cabin of the vehicle comprise instructions configured to cause the processor to output one of: an audible signal, a visual signal, or a haptic signal. 
     
     
         17 . The vehicle of  claim 12 , wherein instructions configured to cause the processor to calculate a speed and a direction of traffic approaching the vehicle comprise instructions configured to cause the processor to calculate the speed and direction of the traffic approaching the vehicle from sensor data collected at the vehicle; and
 further comprising instructions configured to cause the processor to filter the sensor data prior to calculating the speed and direction of the traffic.   
     
     
         18 . The vehicle of  claim 17 , wherein instructions configured to cause the processor to filter the sensor data comprise instructions configured to cause the processor to determine the optical flow of the traffic; and
 wherein instructions configured to cause the processor to determine that the traffic is to pass through a space adjacent to the door comprise instructions configured to cause the processor to determine that the traffic is to pass through the space based on the optical flow of the traffic.   
     
     
         19 . The system of  claim 11 , wherein instructions configured to cause the processor to determine that the door poses a hazard to the traffic comprise instructions configured to cause the processor to detect that a door handle has been actuated. 
     
     
         20 . The vehicle of  claim 11 , further comprising instructions configured to cause the processor to output a signal in the cabin of the vehicle indicating a possibility of a collision between the traffic and the door.