Alibaba Group Holding Limited
VIDEO OBJECT PROCESSING

Abstract:

A computer-implemented method includes: determining, based on a video of a target area, a first number of target objects in the video at each of multiple time points, and a first location of each of the first number of target objects at the corresponding time points; receiving position signals of the corresponding target objects in the target area at each of the multiple time points; determining, based on the position signals, a second number of target objects at each of the multiple time points and a second location of each of the second number of target objects at the corresponding time points; determining that, at each of the multiple time points, the first number equals the second number; determining that, at each of the multiple time points, the first location of each target object matches the second location of the target object; and determining that the video is unmodified.