Significant progress has been made in object tracking tasks thanks to the application of deep learning. However, current deep neural network-based object tracking methods often rely on stacking sub-modules and introducing complex structures to improve tracking accuracy. Unfortunately, these approaches are inefficient and limit the feasibility of deploying efficient trackers on drone AI devices. To address these challenges, this paper introduces ConcatTrk, a high-speed object tracking method designed specifically for drone AI devices. ConcatTrk utilizes a lightweight network architecture, enabling real-time tracking on edge devices. Specifically, the proposed method primarily uses the concatenation operation to construct its core tracking steps, including multi-scale feature fusion, intra-frame feature matching, and dynamic template updating, which aim to reduce the computational overhead of the tracker. To ensure tracking performance in UAV tracking scenarios, ConcatTrk implements a learnable feature matching operator along with a simple and efficient template constraint branch, which enables accurate tracking by discriminatively matching features and incorporating periodic template updates. Results of comprehensive experiments on popular benchmarks, including UAV123, OTB100, and LaSOT, show that ConcatTrk has achieved promising accuracy and attained a tracking speed of 41 FPS on an edge AI device, Nvidia AGX Xavier. ConcatTrk runs 8× faster than the SOTA tracker TransT while using 4.9× fewer FLOPs. Real-world tests on the drone platform have strongly validated its practicability, including real-time tracking speed, reliable accuracy, and low power consumption.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Learning Template-Constraint Real-Time Siamese Tracker for Drone AI Devices via Concatenation


    Beteiligte:
    Zhewei Wu (Autor:in) / Qihe Liu (Autor:in) / Shijie Zhou (Autor:in) / Shilin Qiu (Autor:in) / Zhun Zhang (Autor:in) / Yi Zeng (Autor:in)


    Erscheinungsdatum :

    2023




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    DRONE AND CONTROLLER DETECTOR, DIRECTION FINDER, AND TRACKER

    KASASBEH HADI / GAO ZIANG / SINATRA TAYLOR et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Siamese Adaptive Transformer Network for Real-Time Aerial Tracking

    Xing, Daitao / Tsoukalas, Athanasios / Evangeliou, Nikolaos et al. | IEEE | 2022


    A Real-Time Face Tracker

    Yang, J. / Waibel, A. / IEEE | British Library Conference Proceedings | 1996



    Parallel Concatenation vs. Serial Concatenation Turbo Codes for Wireless Sensor Networks

    Abughalieh, N. / Steenhaut, K. / Lemmens, B. et al. | IEEE | 2011