Ideas for getting started

Here is a list of ideas for getting started and improving baselines on the Airborne Object Detection challenge -

Using YOLO models for object detection and tracking

  • Out of the box YOLOv3 model with DeepSort algorithm for tracking
  • YOLO model fine tuned on the Airprime dataset

Detectron2 provides numerous models for object detection and segmentation and a flexible library for adding new ones. This can be a good starting point for building detection models.


Using JDE based algorithms for object tracking

Most algorithms explored are in SDE (Separate detection and embedding) paradigm. Recent algorithms in the Joint Detection and Embedding (JDE) paradigm have achieved superior performance in MOT leaderboards. Few notable examples -

PaddlePaddle provides a framework with a few MultiObject tracking methods (deepsort, fairmot, jde), and a flexible interface for adding new ones.


A few suggestions for improving object detection

  • Downscaling the input resolution to the model might make it hard to detect smaller airborne objects. Scaling up your input resolution to the model could help.
  • Using a model with high resolution would make your model large and increase inference time. Alternatively, you could tile your images as a preprocessing step and continue using smaller models. (The Power of Tiling for Small Object Detection)
  • Removing birds from predictions can help avoid extra false positives, since we are not interested in alerting birds.
6 Likes

@siddhartha thanks for the suggestions and resources!

Just one additional question about the YOLO: is it allowed to use the code under GPL-3.0 license for this competition?
For example, YOLOv3 implementation from ultralytics: https://github.com/ultralytics/yolov3

1 Like

Hi @yauhen_babakhin,

GPL-3.0 would restrict (or cause complications) running your codebase from reviewing and analyzing the submission, ex, for running inference on the challenges’ private dataset. Due to this, it (or similar) isn’t permitted in this competition.

You can select another open source license of your choice, which doesn’t interfere with that for being eligible for the winner position/prize money. Thanks!

2 Likes