• Compared to the previous challenge, we further enlarge the dataset this year by adding more challenging video sequences with dynamic backgrounds, complex movements, and tiny-scale targets, such that the resulting new dataset covers a greater variety of scenarios with multi-scale UAVs. Examples are shown as follows.

    • cloud background
    • building background
    • mountain background
    • sea background
    • fast movement
    • out_of_focus
    • scale variation
    • no-target scene
    • large target
    • medium target
    • small target
    • tiny target




  • In addition, we have presented a new track for multiple UAV tracking (Track3). This track contains a total of 300 video sequences, with 200 used as the training set and 100 as the test set. The task is to continuously track the drone in the video frames given the initial target position. The algorithm must handle situations such as target disappearance, target reappearance, target overlap, and the appearance of new targets, as well as complex background environments. The number of targets per frame ranges from 0 to over 40.

    • Subset for Each Track

    Train-Track1: 223 videos for training your algorithm.

    Train-Track2: 223 videos for training your algorithm.

    Train-Track3: 200 videos for training your algorithm.

    Test-Track1: 216 videos for the final submission for track 1.

    Test-Track2: 216 videos for the final submission for track 2.

    Test-Track3: 100 videos for the final submission for track 3.

    Attribute Description

    Attribute
    Description
    OV/VE Out-of-View:the target moves out of the current view.
    OC Occlusion: the target is partially or heavily occluded.
    FM Fast Motion: the target moves quickly.
    SV Scale Variation: the scale of the bounding boxes over the frames vary significantly.
    TC/IC Thermal/Infrared Crossover: the target has a similar temperature to other objects or background surroundings.
    DBC Dynamic Background Clusters: there are dynamic changes (e.g., waves, leaves, birds) in the background around the target.
    LR Low Resolution: the area of the bounding box is small.
    TS Target Scale: the target is with a tiny, small, medium or large scale.