The present invention relates to a system for tracking an object. The system includes an image capturing unit configured to capture a video of a predetermined observation area and output the captured video; and a multi-object tracker configured to output an object-tracking image by tracking multiple objects within an object image which is generated by extracting the objects from each of image frames obtained from the video obtained from the image capturing unit, wherein the multi-object tracker determines whether occlusion of the objects or hijacking occurs while performing multi-object tracking, and when it is determined that at least one of the occlusion and hijacking occurs, the multi-object tracker outputs the object-tracking image corrected by removing the occurring occlusion or hijacking.