Safety detection camera system for door closure
A computer implemented method, comprising: detecting presence of an object of interest within a plurality of image frames received from a sensor; determining that the object of interest is moving towards an automatic door that is configured to close within a predetermined time period; determining, based on position, speed and direction of the object of interest, a likelihood that the object of interest may impede closing of the automatic door; and when the likelihood exceeds a threshold value, maintaining the automatic door in an open position for a longer period of time than the predetermined time period.
1. A computer implemented method, comprising:
detecting presence of an object of interest within a plurality of image frames received from a sensor;
determining that the object of interest is moving towards an automatic door that is configured to close within a predetermined time period;
determining, based on position, speed and direction of the object of interest, a likelihood that the object of interest may impede closing of the automatic door; and
when the likelihood exceeds a threshold value, maintaining the automatic door in an open position for a longer period of time than the predetermined time period.
2. The method of claim 1 , wherein the sensor is a video camera.
3. The method of claim 2 wherein video analytics are used to determine position, speed and direction of the object of interest.
4. The method of claim 1 wherein the automatic door is positioned on a train.
5. The method of claim 1 wherein the position, speed and direction of the object of interest is defined as at least a vector.
6. The method of claim 5 wherein the vector is used to determine a predicted vector of movement.
7. The method of claim 6 wherein the vector is compared to similar movement vectors generated by the sensor in the past.
8. The method of claim 7 wherein the predicted vector of movement is at least partially based on movement associated with the similar movement vectors generated by the sensor in the past.
9. The method of claim 8 wherein the predicted vector of movement is an average of the similar movement vectors generated by the sensor in the past.
10. The method of claim 1 wherein the automatic door is for an elevator.
11. A system for controlling an automatic door, comprising:
a sensor configured to detect a presence of an object of interest within a plurality of image frames;
a processor, configured to:
determine that the object of interest is moving towards the automatic door, the automatic door configured to close within a predetermined time period;
determine, based on position, speed and direction of the object of interest, a likelihood that the object of interest may impede closing of the automatic door; and
when the likelihood exceeds a threshold value, maintain the automatic door in an open position for a longer period of time than the predetermined time period.
12. The system of claim 11 , wherein the sensor is a video camera.
13. The system of claim 12 wherein the processor uses video analytics to determine position, speed and direction of the object of interest.
14. The system of claim 11 wherein the automatic door is positioned on a train.
15. The system of claim 11 wherein the position, speed and direction of the object of interest is defined as at least a vector.
16. The system of claim 15 wherein the vector is used to determine a predicted vector of movement.
17. The system of claim 16 wherein the vector is compared to similar movement vectors generated by the sensor in the past.
18. The system of claim 17 wherein the predicted vector is at least partially based on movement associated with the similar movement vectors generated by the sensor in the past.
19. The system of claim 18 wherein the predicted vector is an average of the similar movement vectors generated by the sensor in the past.
20. The system of claim 11 wherein the automatic door is for an elevator.