The present invention relates in particular to a method for re-identification of a target object in images obtained from several image sources, wherein each of the image sources obtains images representing an area associated with the corresponding image source. After having identified a target object in images obtained from one of a pair of image sources, a relative velocity of the target object in comparison with other objects previously identified in images obtained from the one of the pair of image sources is estimated. Then, based on the estimated relative velocity of the target object, a correspondence between the target object identified in images obtained from the one of the pair of image sources and a candidate object represented in images obtained from the other image source of the pair of image sources is established.