Skip-scanning identification method, apparatus, and self-service checkout terminal and system

A system comprising one or more processors and one or more non-transitory computer-readable memories coupled to the one or more processors, the one or more non-transitory computer-readable memories storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

• obtaining a video of a user scanning an item;
• extracting a plurality of video frames from the obtained video;
• determining posture data of the user based on the plurality of video frames, wherein the posture data comprises a location trajectory of the user's hand, and the determining of the posture data comprises:
• identifying a plurality of key points of the user's hand in the plurality of video frames;
• for each of the plurality of key points of the user's hand, determining a brightness pattern of the key point of the user's hand based on a motion of the user's hand in the plurality of video frames;
• obtaining an optical flow corresponding to the key point based on the brightness pattern;
• and
• determining the location trajectory of the user's hand based on the optical flows of the plurality of key points of the user's hand;
• determining, according to the posture data of the user, a time period in which a scanning action of the user takes place;
• receiving a scanning result of the item;
• and
• determining whether the user has skipped scanning the item based on the scanning result and the time period.

A non-transitory computer-readable storage medium configured with instructions executable by one or more processors to cause the one or more processors to perform operations comprising:

• obtaining a video of a user scanning an item;
• extracting a plurality of video frames from the obtained video;
• determining posture data of the user based on the plurality of video frames, wherein the posture data comprises a location trajectory of the user's hand, and the determining of the posture data comprises:
• identifying a plurality of key points of the user's hand in the plurality of video frames;
• for each of the plurality of key points, determining a brightness pattern of the key point of the user's hand as the user's hand moves in the plurality of video frames;
• obtaining an optical flow corresponding to the key point based on the brightness pattern;
• and
• determining the location trajectory of the user's hand based on the optical flows of the plurality of key points of the user's hand;
• determining, according to the posture data of the user, a time period in which a scanning action of the user takes place;
• receiving a scanning result of the item;
• and
• determining whether the user has skipped scanning the item based on the scanning result and the time period.