Systems and methods for identifying characteristics of electric vehicles
The disclosed embodiments provide a method performed at a computer system that is in communication with an electric vehicle charging station (EVCS). The EVCS includes a camera for obtaining images in a region proximal to the EVCS. The method includes capturing, using the camera, a plurality of images of electric vehicles, each image in the plurality of images being an image of a respective electric vehicle. The method further includes, for each respective image of the plurality of images of electric vehicles: determining, without user intervention, a characteristic of the respective electric vehicle; and tagging, without user intervention, the respective image with the characteristic of the respective electric vehicle. The method further includes training a first machine learning algorithm to identify the characteristic of other electric vehicles using the tagged plurality of images.
1. A method comprising:
at a computer system comprising one or more processors, and memory, wherein the computer system is in communication with an electric vehicle charging station (EVCS) comprising a camera for obtaining video of a region proximal to the EVCS:
capturing, using the camera, video comprising a plurality of frames for a contiguous period of time;
monitoring a status of the EVCS, wherein the status of the EVCS is indicative of whether the EVCS is in use;
detecting a change in the status of the EVCS;
in accordance with the detected change in the status of the EVCS, identifying a respective frame of the video as including at least a portion of an image of an electric vehicle; and
training a machine learning algorithm to identify characteristics of electric vehicles using a subset of the plurality of frames for the contiguous period of time, wherein the subset comprises the respective frame identified as including at least a portion of an image of an electric vehicle.
2. The method of claim 1 , wherein each frame of the subset of the plurality of frames includes an image of at least a portion of an electric vehicle.
3. The method of claim 1 , wherein the change in the status of the EVCS corresponds to initiating charging of an electric vehicle.
4. The method of claim 1 , wherein the change in the status of the EVCS corresponds to an action selected from the group consisting of:
disconnecting an electrical connection between an electric vehicle and the EVCS;
receiving input from a user of the EVCS;
receiving an indication that an electronic device of a user is located within a predetermined distance from the EVCS;
establishing a connection between an electronic device of a user and the EVCS; and
establishing a connection between the EVCS and an electric vehicle.
5. The method of claim 1 , further comprising:
transmitting the respective frame of the video to a remote computer system for tagging, wherein:
the subset of the plurality of frames used in training the machine learning algorithm comprises a respective tagged frame; and
the respective tagged frame comprises information regarding any one or more of: a make, a model, and a year of the electric vehicle.
6. The method of claim 1 , further comprising:
tagging the respective frame of the subset of the plurality of frames using information received from the electric vehicle, wherein the information received from the electric vehicle includes a characteristic selected from the group consisting of: a make, a model, and a year of the electric vehicle.
7. The method of claim 1 , wherein detecting the change in the status of the EVCS comprises detecting a user action to begin charging an electric vehicle, and the method further comprises:
identifying frames of the video that are captured within a predetermined time period after the detected change, wherein the subset of the plurality of frames includes at least one of the identified frames.
8. The method of claim 1 , wherein detecting the change in the status of the EVCS comprises detecting a user action to cease charging an electric vehicle, and the method further comprises:
identifying frames of the video that are captured within a predetermined time period before the detected change, wherein the subset of the plurality of frames includes at least one of the identified frames.
9. The method of claim 1 , wherein detecting the change in the status of the EVCS comprises detecting a user action to begin charging an electric vehicle, and the method further comprises:
detecting a second change in the status of the EVCS corresponding to a user action to cease charging the electric vehicle; and
identifying frames of the video that are captured between the detected change in status and the second change in status, wherein the subset of the plurality of frames includes at least one of the identified frames.
10. The method of claim 1 , wherein at least a frame of the plurality of frames does not include an image of a vehicle.
11. The method of claim 1 , further comprising:
using the plurality of frames for the contiguous period of time to perform an operation at the EVCS during the contiguous period of time, the operation being distinct from training the machine learning algorithm.
12. A computer system that is in communication with an electric vehicle charging station (EVCS), the EVCS comprising a camera for obtaining video of a region proximal to the EVCS, the computer system comprising:
one or more processors;
memory storing one or more programs, the one or more programs including instructions for:
capturing, using the camera, video comprising a plurality of frames for a contiguous period of time;
monitoring a status of the EVCS, wherein the status of the EVCS is indicative of whether the EVCS is in use;
detecting a change in the status of the EVCS;
in accordance with the detected change in the status of the EVCS, identifying a respective frame of the video as including at least a portion of an image of an electric vehicle; and
training a machine learning algorithm to identify characteristics of electric vehicles using a subset of the plurality of frames for the contiguous period of time, wherein the subset comprises the respective frame identified as including at least a portion of an image of an electric vehicle.
13. The computer system of claim 12 , wherein each frame of the subset of the plurality of frames includes an image of at least a portion of an electric vehicle.
14. The computer system of claim 12 , wherein the change in the status of the EVCS corresponds to initiating charging of an electric vehicle.
15. The computer system of claim 12 , wherein the change in the status of the EVCS corresponds to an action selected from the group consisting of:
disconnecting an electrical connection between an electric vehicle and the EVCS;
receiving input from a user of the EVCS;
receiving an indication that an electronic device of a user is located within a predetermined distance from the EVCS;
establishing a connection between an electronic device of a user and the EVCS; and
establishing a connection between the EVCS and an electric vehicle.
16. The computer system of claim 12 , wherein the one or more programs further includes instructions for:
transmitting the respective frame of the video to a remote computer system for tagging, wherein:
the subset of the plurality of frames used in training the machine learning algorithm comprises a respective tagged frame; and
the respective tagged frame comprises information regarding any one or more of: a make, a model, and a year of the electric vehicle.
17. The computer system of claim 12 , wherein the one or more programs further include instructions for:
tagging the respective frame of the subset of the plurality of frames using information received from the electric vehicle, wherein the information received from the electric vehicle includes a characteristic selected from the group consisting of: a make, a model, and a year of the electric vehicle.
18. The computer system of claim 12 , wherein detecting the change in the status of the EVCS comprises detecting a user action to begin charging an electric vehicle, and the one or more programs further include instructions for:
identifying frames of the video that are captured within a predetermined time period after the detected change, wherein the subset of the plurality of frames includes at least one of the identified frames.
19. The computer system of claim 12 , wherein detecting the change in the status of the EVCS comprises detecting a user action to cease charging an electric vehicle, and the one or more programs further comprise instructions for:
identifying frames of the video that are captured within a predetermined time period before the detected change, wherein the subset of the plurality of frames includes at least one of the identified frames.
20. A non-transitory computer readable storage medium storing including instructions that, when executed by one or more processors of a computer system that is in communication with an electric vehicle charging station (EVCS), the EVCS comprising a camera for obtaining video of a region proximal to the EVCS, cause the computer system to perform operations comprising:
capturing, using the camera, video comprising a plurality of frames for a contiguous period of time;
monitoring a status of the EVCS, wherein the status of the EVCS is indicative of whether the EVCS is in use;
detecting a change in the status of the EVCS;
in accordance with the detected change in the status of the EVCS, identifying a respective frame of the video as including at least a portion of an image of an electric vehicle; and
training a machine learning algorithm to identify characteristics of electric vehicles using a subset of the plurality of frames for the contiguous period of time, wherein the subset comprises the respective frame identified as including at least a portion of an image of an electric vehicle.