Ensuring security on the fueling forecourt

Patent metadata

Field	Value
Publication number	US-11810349-B2
Application number	US-202016885946-A
Country	US
Kind code	B2
Filing date	May 28, 2020
Priority date	May 28, 2020
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

In one aspect, data characterizing a video feed acquired by a camera oriented toward and including a field of view of a forecourt of a fueling station can be received. The video feed can be monitored for hazards, and the monitoring of the video feed can include performing automatic hazard detection on the video feed using at least one predictive model that predicts a presence of a hazard within the forecourt of the fueling station. A command can be transmitted in response to the detecting of the presence of the hazard within the forecourt of the fueling station. Related apparatus, systems, methods, techniques, and articles are also described.

First claim

What is claimed is:

1. A method comprising:
receiving data characterizing a video feed acquired by a camera continuously and automatically gathering images, the camera being oriented toward and including a field of view of a forecourt of a fueling station;
continuously monitoring the video feed for hazards, the monitoring including performing automatic hazard detection on the video feed using at least one predictive model that predicts a presence of a hazard within the forecourt of the fueling station;
transmitting a command to a forecourt controller, the forecourt controller being configured to manage operation of the fueling station, the command causing the forecourt controller to deactivate at least a portion of the fueling station, and the command identifying the at least the portion of the fueling station to be deactivated;
causing a graphical prompt to be shown on an end user device, the graphical prompt being indicative of the predicted presence of the hazard and the graphical prompt including a first response option that designates the predicted presence of the hazard as a false alarm and a second response option for activing a fire suppression system disposed in the forecourt;
receiving, from the end user device, data characterizing a designation, by a user of the end user device interacting with the graphical prompt, of the predicted presence of the hazard as a false alarm; and
training the at least one predictive model by at least providing the data characterizing the designation to the at least one predictive model.

2. The method of claim 1 , further comprising:
comparing an object present within the forecourt of the fueling station to at least one model object, the model object associated with the hazard;
determining a similarity measure for the object, the similarity measure indicative of a degree to which the object matches the model object; and
transmitting an indication in response to the similarity measure exceeding a predetermined threshold.

3. The method of claim 1 , wherein the end user device is an interactive display of the forecourt controller.

4. The method of claim 1 , wherein the end user device is a mobile device in operable communication with the forecourt controller.

5. The method of claim 1 , further comprising transmitting a fire suppression command to the fire suppression system which causes the fire suppression system to activate at least one sprinkler to dispense a fire extinguishing agent, the fire suppression command transmitted based on an interaction of the user with the second response option.

6. The method of claim 1 , further comprising transmitting an alarm command to an alarm system having at least one speaker oriented toward the forecourt, the alarm command causing an audio message to be provided via the at least one speaker, the audio message indicative of the hazard presence.

7. The method of claim 1 , wherein the automatic hazard detection includes deconstructing, with an edge detection algorithm of the at least one predictive model, an image of the video feed into at least one constituent part, and determining, with the at least one predictive model, a prediction of the presence of the hazard based on the at least one constituent part.

8. The method of claim 1 , wherein the automatic hazard detection including deconstructing, with the at least one predictive model, an image of the video feed into at least one constituent part, determining, with the at least one predictive model, a word string that characterizes at least one constituent part, and determining, with the at least one predictive model, a prediction of the presence of the hazard based on the determined word string.

9. A system comprising:
at least one data processor; and
memory storing instructions configured to cause the at least one data processor to perform operations comprising:
receiving data characterizing a video feed acquired by a camera continuously and automatically gathering images, the camera being oriented toward and including a field of view of a forecourt of a fueling station;
continuously monitoring the video feed for hazards, the monitoring including performing automatic hazard detection on the video feed using at least one predictive model that predicts a presence of a hazard within the forecourt of the fueling station;
transmitting a command to a forecourt controller, the forecourt controller being configured to manage operation of the fueling station, the command causing the forecourt controller to deactivate at least a portion of the fueling station, and the command identifying the at least the portion of the fueling station to be deactivated;
causing a graphical prompt to be shown on an end user device, the graphical prompt being indicative of the predicted presence of the hazard and the graphical prompt including a first response option that designates the predicted presence of the hazard as a false alarm and a second response option for activing a fire suppression system disposed in the forecourt;
receiving, from the end user device, data characterizing a designation, by a user of the end user device interacting with the graphical prompt, of the predicted presence of the hazard as a false alarm; and
training the at least one predictive model by at least providing the data characterizing the designation to the at least one predictive model.

10. The system of claim 9 , wherein the operations further comprise:
comparing an object present within the forecourt of the fueling station to at least one model object, the model object associated with the hazard;
determining a similarity measure for the object, the similarity measure indicative of a degree to which the object matches the model object; and
transmitting an indication in response to the similarity measure exceeding a predetermined threshold.

11. The system of claim 9 , wherein the end user device is an interactive display of the forecourt controller.

12. The system of claim 9 , wherein the end user device is a mobile device in operable communication with the forecourt controller.

13. The system of claim 9 , wherein the operations further comprise transmitting a fire suppression command to the fire suppression system which causes the fire suppression system to activate at least one sprinkler to dispense a fire extinguishing agent, the fire suppression command transmitted based on an interaction of the user with the second response option.

14. The system of claim 9 , wherein the operations further comprise transmitting an alarm command to an alarm system having at least one speaker oriented toward the forecourt, the alarm command causing an audio message to be provided via the at least one speaker, the audio message indicative of the hazard presence.

15. The system of claim 14 , wherein the alarm system includes at least one strobe lamp oriented toward the forecourt, and the alarm command causes the strobe lamp to illuminate to thereby indicate the hazard presence.

16. A non-transitory computer program product storing instructions which, when executed by at least one data processor forming part of at least one computing system, cause the at least one data processor to implement operations comprising:
receiving data characterizing a video feed acquired by a camera continuously and automatically gathering images, the camera being oriented toward and including a field of view of a forecourt of a fueling station;
continuously monitoring the video feed for hazards, the monitoring including performing automatic hazard detection on the video feed using at least one predictive model that predicts a presenc

Assignees

• Wayne Fueling Systems Llc

Inventors

• Fieglein Henry
• Singh Kalpit
• Chinnaswamy Rohith
• Hairston Hob

Classifications

• G06V20/41 Primary

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• A62C3/00

  Fire prevention, containment or extinguishing specially adapted for particular objects or places ({in oil wells E21B29/08, A62C35/00; in mines or tunnels E21F5/00} ; for nuclear reactors G21C9/04) · CPC title

• G06V20/176

  Urban or other man-made structures · CPC title

• G06N20/00

  Machine learning · CPC title

• G08B17/125 Primary

  by using a video camera to detect fire or smoke · CPC title