Controlling host vehicle based on detected door opening events
Systems and methods are provided for vehicle navigation. In one implementation, a system may comprise at least one processor. The processor may be programmed to receive an image associated with the environment of the host vehicle. The processor may analyze the image to identify a side of a parked vehicle; a first structural feature of the parked vehicle in a forward region of the side of the parked vehicle or a second structural feature of the parked vehicle in a rear region of the side of the parked vehicle; and a door feature of the parked vehicle in a vicinity of the first or the second structural features. The processor may then determine, based on a subsequent image, a change of an image characteristic of the door feature of the parked vehicle and alter a navigational path of the host vehicle based on the change of the image characteristic.
1. A system for navigating a host vehicle based on detecting a door opening event in an environment of the vehicle, the system comprising:
at least one processing device programmed to:
receive, from an image capture device, at least one image associated with the environment of the host vehicle;
analyze the at least one image to identify a side of a parked vehicle;
identify, in the at least one image, a first structural feature of the parked vehicle in a forward region of the side of the parked vehicle or a second structural feature of the parked vehicle in a rear region of the side of the parked vehicle;
identify, in the at least one image, a door feature of the parked vehicle in a vicinity of the first or the second structural features;
determine, based on analysis of one or more subsequent images received from the image capture device, a change of an image characteristic of the door feature of the parked vehicle; and
alter a navigational path of the host vehicle based at least in part on the change of the image characteristic of the door feature of the parked vehicle.
2. The system of claim 1 , wherein identifying the side of the parked vehicle includes associating at least one bounding box with a shape of the side of the parked vehicle.
3. The system of claim 1 , wherein the first structural feature includes a front wheel component of the parked vehicle and the second structural feature includes a rear wheel component of the parked vehicle.
4. The system of claim 1 , wherein the change of the image characteristic of the door feature includes a widening of the door feature.
5. The system of claim 1 , wherein the change of the image characteristic of the door feature includes a separation of the door feature from the body of the vehicle.
6. The system of claim 1 , wherein determining the change of the image characteristic of the door feature includes monitoring at least two images received from the image capture device for an appearance of a vertical stripe in the vicinity of the first or the second wheel components.
7. The system of claim 6 , wherein determining the change of the image characteristic of the door feature further includes monitoring an expansion of the vertical stripe.
8. The system of claim 7 , wherein a first feature of the vertical stripe is fixed along a body of the parked vehicle in the monitored images, and a second feature of the vertical stripe moves toward a front region of the parked vehicle in the monitored images.
9. The system of claim 8 , wherein the at least one processing device is further configured to determine a width of the vertical stripe.
10. The system of claim 9 , wherein the at least one processing device is further configured to determine a distance that the door feature extends away from the parked vehicle based on the determined width.
11. The system of claim 10 , wherein the at least one processing device is further configured to determine a lateral safety distance for the host vehicle based on the determined distance that the door feature extends away from the parked vehicle.
12. The system of claim 11 , wherein altering the navigational path of the host vehicle is based on the determined lateral safety distance.
13. The system of claim 1 , wherein altering the navigational path of the host vehicle comprises invoking at least one navigational change of the host vehicle.
14. The system of claim 13 , wherein the navigational change is determined based on at least one safety constraint.
15. The system of claim 1 , wherein identifying the first structural feature or the second structural feature comprises applying a trained system.
16. The system of claim 15 , herein the trained system comprises a neural network.
17. The system of claim 1 , wherein determining the change of an image characteristic of the door feature comprises applying a trained system.
18. A method for navigating a host vehicle based on detecting a door opening event in an environment of the vehicle, the method comprising:
receiving, from an image capture device, at least one image associated environment of the host vehicle;
analyzing the at least one image to identify a side of a parked vehicle;
identifying, in the at least one image, a first structural feature of the parked vehicle in a forward region of the side of the parked vehicle or a second structural feature of the parked vehicle in a rear region of the side of the parked vehicle;
identifying, in the at least one image, a door feature of the parked vehicle in a vicinity of the first or the second structural features;
determining, based on analysis of one or more subsequent images received from the image capture device, a change of an image characteristic of the door feature of the parked vehicle; and
altering a navigational path of the host vehicle based at least in part on the change of the image characteristic of the door feature of the parked vehicle.
19. The method of claim 18 , wherein identifying the side of the parked vehicle includes associating at least one bounding box with a shape of the side of the parked vehicle.
20. The method of claim 18 , wherein the first structural feature includes a front wheel component of the parked vehicle and the second structural feature includes a rear wheel component of the parked vehicle.
21. The method of claim 18 , wherein the change of the image characteristic of the door feature includes a separation of the door feature from the body of the vehicle.
22. The method of claim 18 , wherein altering the navigational path of the host vehicle comprises invoking at least one navigational change of the host vehicle.
23. The method of claim 22 , wherein the navigational change is determined based on at least one safety constraint.
24. The method of claim 18 , wherein at least one of identifying the first structural feature or the second structural feature or determining a change of an image characteristic of the door feature comprises applying a trained system.
25. The method of claim 24 , wherein the trained system comprises a neural network.
26. The method of claim 18 , wherein determining the change of an image characteristic of the door feature comprises applying a trained system.