“…This type of method faces more challenging issues than a traditional person Re‐ID system. Relevant research efforts, which have recently become popular, mainly focus on the basic work of constructing datasets, such as DOTA, 6 NWPU VHR, 21 UAV123, 22 VisDrone, 23 AVI, 24 and PRAI‐1581, 7 and the tasks of object detection, 10 tracking, 11 and segmentation 12 . Regarding the person Re‐ID task, which receives little attention, Zhang et al 7 presented an end‐to‐end learning method with a subspace pool using convolution feature mapping; this approach learns discriminative and compact feature representations to represent pedestrian images, effectively improving the accuracy of person Re‐ID in aerial imagery.…”