STN-Track: Multiobject Tracking of Unmanned Aerial Vehicles by Swin Transformer Neck and New Data Association Method

Abstract

The gradual development of remote sensing object tracking technology based on unmanned aerial vehicles (UAV) videos has become one of the main research directions in the field of visual tracking. However, due to characteristics of the UAV platform, typical visual tracking algorithms currently applied to natural scenes cannot be used directly. Small-scale objects in UAV remote sensing videos are difficult to detect and have the problem of tracking identity switching. In order to solve these problems, we designed the Swin transformer neck YOLOX (STN-YOLOX) object detection algorithm as the detection module, and the G-Byte data association method as the tracking module. We then combined the two into a new multi-object tracking algorithm named STN-Track. We used STN-Track to conduct experiments on the UAVDT and VisDrone MOT datasets. The experimental results show that compared with the current state-of-the-art (SOTA) methods, our STN-Track has improved detection and tracking accuracy of small-scale objects and greatly improved identification capabilities for object tracking. Compared with the SOTA ByteTrack algorithm, MOTA of STN-Track can be improved by up to 3.2%, AP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</sub> can be improved by up to 4.4%, MT can be improved by up to 6.8%, and IDSW can be reduced by up to 28.0%.