Method, apparatus, computing device and computer-readable storage medium for monitoring use of target item

A method for monitoring a use of a target item, comprising:

• obtaining a region of interest of each of video frames in a video to be detected;
• for said each of the video frames, determining whether the target item and a head of a monitored target object are both present in the region of interest;
• in response to the target item and the head of the monitored target object being both present in the region of interest, determining whether a hand of the monitored target object is present in the region of interest;
• in response to the hand of the monitored target object being not present in the region of interest, determining a face orientation of the monitored target object, and based on the face orientation, determining whether said each of the video frames is in a first video frame status, wherein the first video frame status indicates that there is an interaction between the target item and the monitored target object in said each of the video frames;
• in response to the hand of the monitored target object being present in the region of interest, determining a relative position relationship between the hand and the target item, and based on the relative position relationship, determining whether said each of the video frames is in the first video frame status;
• and
• based on a number of video frames continuously in the first video frame status, determining whether the monitored target object uses the target item.