An example method includes receiving the one or more image frames successively in time, wherein a first image frame is received before a second image frame in time and defining one or more blocks in each of the one or more image frames, wherein the first image frame includes a first block, and the second image frame includes a second block. The method also includes in response to the second block having a probability higher than a threshold to be associated with a region of interest (ROI), selecting the second block from the one or more blocks in the second image frame, and in response to the selected second block being associated with the first block, determining an ROI status of the second block to represent whether the second block includes any part of the ROI based on an ROI status of the first block.