Obtaining stable frames
Implementations of the present application provide a solution for obtaining a stable frame. In the solution, a video stream is obtained, from which a first and second stable frame are determined using at least position-based offset values between one or more frames. The first and second stable frames correspond to a first time interval and second time interval, respectively. The first time interval corresponds to a time before a first vibration is generated by opening a door of a visual vending machine. The second time interval corresponds to a time after the first vibration and before a second vibration generated by closing the door. The two stable frames can be used for image recognition within the visual vending machine to improve accuracy of product recognition.
1. A computer-implemented method for obtaining a stable frame comprising:
obtaining a video stream, wherein the video stream comprises a plurality of video frames;
determining, based on position offset values between a first video frame and video frames adjacent to the first video frame, a first stable frame from video frames corresponding to a first time interval before a first vibration is generated by opening a door of a visual vending machine; and
determining, based on a position offset value between a second video frame and the first stable frame, a second stable frame from video frames corresponding to a second time interval after the first vibration and before a second vibration is generated by closing the door of the visual vending machine.
2. The computer-implemented method of claim 1 , further comprising:
obtaining a door-opening signal and a door-closing signal of the visual vending machine; and
determining, based on a predetermined first duration and by using a time point corresponding to the door-opening signal as a first interval ending point, the first time interval before the first vibration is generated; or
determining, based on a predetermined second duration and by using a time point corresponding to the door-closing signal as a second interval ending point, the second time interval before the second vibration is generated.
3. The computer-implemented method of claim 1 , wherein determining the first stable frame comprises:
calculating the position offset values between the first video frame and the video frames adjacent to the first video frame;
calculating a first time difference value between a first time point corresponding to the first video frame and a second time point corresponding to an end of the first time interval before the first vibration is generated by opening the door of the visual vending machine; and
determining the first stable frame using the position offset values and the first time difference value.
4. The computer-implemented method of claim 1 , wherein determining the second stable frame comprises:
calculating the position offset value between the second video frame and the first stable frame;
calculating a second time difference value between a third time point corresponding to the second video frame and a fourth time point corresponding to an end of the second time interval; and
determining the second stable frame using the position offset value and the second time difference value.
5. The computer-implemented method of claim 1 , further comprising:
calculating position offset values between adjacent video frames in the video stream; and
generating a curve from the position offset values and time in a coordinate system, to determine the first stable frame and the second stable frame.
6. The computer-implemented method of claim 1 , wherein obtaining the video stream comprises:
detecting a triggering condition; and
extracting, after detecting the triggering condition, the video stream from video streams captured by a camera device, wherein the video stream comprises at least a video frame corresponding to the first time interval and a video frame corresponding to the second time interval.
7. The computer-implemented method of claim 6 , wherein the triggering condition comprises:
monitoring a first area in front of the visual vending machine; and
detecting that a user enters a triggering position, wherein the triggering position comprises the first area.
8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
obtaining a video stream, wherein the video stream comprises a plurality of video frames;
determining, based on position offset values between a first video frame and video frames adjacent to the first video frame, a first stable frame from video frames corresponding to a first time interval before a first vibration is generated by opening a door of a visual vending machine; and
determining, based on a position offset value between a second video frame and the first stable frame, a second stable frame from video frames corresponding to a second time interval after the first vibration and before a second vibration is generated by closing the door of the visual vending machine.
9. The non-transitory, computer-readable medium of claim 8 , further comprising:
obtaining a door-opening signal and a door-closing signal of the visual vending machine; and
determining, based on a predetermined first duration and by using a time point corresponding to the door-opening signal as a first interval ending point, the first time interval before the first vibration is generated; or
determining, based on a predetermined second duration and by using a time point corresponding to the door-closing signal as a second interval ending point, the second time interval before the second vibration is generated.
10. The non-transitory, computer-readable medium of claim 8 , wherein determining the first stable frame comprises:
calculating the position offset values between the first video frame and the video frames adjacent to the first video frame;
calculating a first time difference value between a first time point corresponding to the first video frame and a second time point corresponding to an end of the first time interval before the first vibration is generated by opening the door of the visual vending machine; and
determining the first stable frame using the position offset values and the first time difference value.
11. The non-transitory, computer-readable medium of claim 8 , wherein determining the second stable frame comprises:
calculating the position offset value between the second video frame and the first stable frame;
calculating a second time difference value between a third time point corresponding to the second video frame and a fourth time point corresponding to an end of the second time interval; and
determining the second stable frame using the position offset value and the second time difference value.
12. The non-transitory, computer-readable medium of claim 8 , further comprising:
calculating position offset values between adjacent video frames in the video stream; and
generating a curve from the position offset values and time in a coordinate system, to determine the first stable frame and the second stable frame.
13. The non-transitory, computer-readable medium of claim 8 , wherein obtaining the video stream comprises:
detecting a triggering condition; and
extracting, after detecting the triggering condition, the video stream from video streams captured by a camera device, wherein the video stream comprises at least a video frame corresponding to the first time interval and a video frame corresponding to the second time interval.
14. The non-transitory, computer-readable medium of claim 13 , wherein the triggering condition comprises:
monitoring a first area in front of the visual vending machine; and
detecting that a user enters a triggering position, wherein the triggering position comprises the first area.
15. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
obtaining a video stream, wherein the video stream comprises a plurality of video frames;
determining, based on position offset values between a first video frame and video frames adjacent to the first video frame, a first stable frame from video frames corresponding to a first time interval before a first vibration is generated by opening a door of a visual vending machine; and
determining, based on a position offset value between a second video frame and the first stable frame, a second stable frame from video frames corresponding to a second time interval after the first vibration and before a second vibration is generated by closing the door of the visual vending machine.
16. The computer-implemented system of claim 15 , further comprising:
obtaining a door-opening signal and a door-closing signal of the visual vending machine; and
determining, based on a predetermined first duration and by using a time point corresponding to the door-opening signal as a first interval ending point, the first time interval before the first vibration is generated; or
determining, based on a predetermined second duration and by using a time point corresponding to the door-closing signal as a second interval ending point, the second time interval before the second vibration is generated.
17. The computer-implemented system of claim 15 , wherein determining the first stable frame comprises:
calculating the position offset values between the first video frame and the video frames adjacent to the first video frame;
calculating a first time difference value between a first time point corresponding to the first video frame and a second time point corresponding to an end of the first time interval before the first vibration is generated by opening the door of the visual vending machine; and
determining the first stable frame using the position offset values and the first time difference value.
18. The computer-implemented system of claim 15 , wherein determining the second stable frame comprises:
calculating the position offset value between the second video frame and the first stable frame;
calculating a second time difference value between a third time point corresponding to the second video frame and a fourth time point corresponding to an end of the second time interval; and
determining the second stable frame using the position offset value and the second time difference value.
19. The computer-implemented system of claim 15 , further comprising:
calculating position offset values between adjacent video frames in the video stream; and
generating a curve from the position offset values and time in a coordinate system, to determine the first stable frame and the second stable frame.
20. The computer-implemented system of claim 15 , wherein obtaining the video stream comprises:
detecting a triggering condition; and
extracting, after detecting the triggering condition, the video stream from video streams captured by a camera device, wherein the video stream comprises at least a video frame corresponding to the first time interval and a video frame corresponding to the second time interval.