Siamese multi-scale aggregation network for UAV tracking

Meiyu Yao, Na Wu, Shuo Hu, Hui Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Downloads (Pure)

Abstract

The Siamese-based trackers have received much attention due to their great performance in the field of target tracking. However, it ignores the relationships and interdependencies between different features, impeding the robustness under various conditions. In addition, most Siamese-based trackers suffer from multiple special challenges, such as Fast Motion, Occlusion in UAV tracking. In this paper, we propose an anchor-free based object tracking algorithm with multi-scale aggregation Siamese Network. The proposed method consists of three parts: the feature extraction network, Encoder and Decoder. A multi-scale receptive field structure is designed in the encoder to deal with the problem of multi-scale change. The design of adaptive anchor in the decoder effectively reduces the relevant hyper-parameters. Experiments on three challenging UAV tracking benchmarks have demonstrated the robustness and effectiveness of the proposed method.

Original languageEnglish
Title of host publication2022 Australian & New Zealand Control Conference (ANZCC)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages192-196
Number of pages5
ISBN (Electronic)9781665498876
ISBN (Print)9781665498883
DOIs
Publication statusPublished - 5 Dec 2022
Event2022 Australian & New Zealand Control Conference (ANZCC) - Gold Coast, Australia
Duration: 24 Nov 202225 Nov 2022

Publication series

Name2022 Australian and New Zealand Control Conference, ANZCC 2022
PublisherIEEE
ISSN (Print)2767-7230
ISSN (Electronic)2767-7257

Conference

Conference2022 Australian & New Zealand Control Conference (ANZCC)
Period24/11/2225/11/22

Keywords

  • anchor-free
  • intelligent vehicles
  • object tracking
  • Siamese-based tracker
  • UAV tracking

Cite this