An electronic device comprises an image sensor that captures a sequence of image frames of a scene. The electronic device includes circuitry that generates an optical flow map for a current frame of the sequence of image frames received from the image sensor. The circuitry determines a plurality of likelihood-of-prominence values for the plurality of regions, based on the generated optical flow map and a motion vector that maps to a direction of motion of the electronic device. The circuitry is configured to detect at least a first region that has a direction of motion similar to that of the electronic device, as a region-of-prominence, based on the determined plurality of likelihood-of-prominence values for the plurality of regions. The circuitry is configured to track the desired object in the sequence of image frames based on the detection of the first region of the current frame as the region-of-prominence.