Skip to content

Detecting small, fast-moving objects at significant distances before they become potential hazards.

Notifications You must be signed in to change notification settings

boemer00/aot-object-tracking-aws

Repository files navigation

Airborne Object Tracking

Airborne Object Tracking (AOT) is a collection of 4,943 flight sequences, each approximately 120 seconds long, collected at 10 Hz under a variety of conditions. The dataset contains over 5.9 million images and more than 3.3 million 2D annotations of airborne objects within the sequences. There are 3,306,350 frames without labels, as they do not contain any airborne objects. For images with labels, there is an average of 1.3 labels per image. All airborne objects in the dataset are labelled.

Ground Truth

Ground truth (present in ImageSets folder) contains all the relevant information regarding airborne objects, their locations, bbox and so on. While the Images folder have accompanied images for your training code to work on.

Before we start, let's check the vocabulary we will need to understand the dataset:

  • flights (a.k.a. samples in ground truth):
    One flight is typically 2 minutes video at 10 fps i.e. 1200 images. Each of the frames are present in Images/{{flight_id}}/ folder. These files are typically 3-4mb each.

  • frame (a.k.a. entity in ground truth):
    This is the most granular unit on which dataset can be sampled. Each frame have information timestamp, frame_id, and label is_above_horizon. There can be multiple entries for same frame in entity when multiple Airborne objects are present.
    When an Airborne object following information is available as well:

    • id -> signifies unique ID of this object (for whole frame)
    • bbox -> it contains 4 floats signifying [left, top, width, height]
    • blob['range_distance_m'] -> distance of airborne object
    • labels['is_above_horizon'] -> details below
    • (derived) planned -> for the planned objects range_distance_m is available
  • is_above_horizon:
    It is marked as 1 when Airborne object is above horizon and -1 when it is below horizon. When unclear, it is marked as 0.

Example for frame level data (multiple per frame):

json
{
    'time': 1550844897919368155,
    'blob': {
        'frame': 480,
        'range_distance_m': nan # signifies, it was an unplanned object
    },
    'id': 'Bird2',
    'bb': [1013.4, 515.8, 6.0, 6.0],
    'labels': {'is_above_horizon': 1},
    'flight_id': '280dc81adbb3420cab502fb88d6abf84',
    'img_name': '1550844897919368155280dc81adbb3420cab502fb88d6abf84.png'
}

About

Detecting small, fast-moving objects at significant distances before they become potential hazards.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages