According to various aspects of the present disclosure, methods, systems, and media for object tracking are provided. In some embodiments, the systems may include: at least one hardware processor to: detect a target object in first image data provided by a first camera; determine a first plurality of neighboring cameras of the first camera that have detected the target object; determine at least one of the first plurality of neighboring cameras as a next node of the first camera; and generate first topological data for the first camera and the next node of the first camera.