# Track Boosting and Synthetic Data Aided Drone Detection

Source: [Track Boosting and Synthetic Data Aided Drone Detection](<https://www.sota2.com/research/paper/68fa6c9e1e209131cea34fdf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:33:08.518Z

Authors: Fatih Cagatay Akyon, Ogulcan Eryuksel, Kamil Anil Ozfuttu, Sinan Onur Altinuc

Published: 2021-11-24T10:16:27.000Z

## Abstract

This is the paper for the first place winning solution of the Drone vs. Bird Challenge, organized by AVSS 2021. As the usage of drones increases with lowered costs and improved drone technology, drone detection emerges as a vital object detection task. However, detecting distant drones under unfavorable conditions, namely weak contrast, long-range, low visibility, requires effective algorithms. Our method approaches the drone detection problem by fine-tuning a YOLOv5 model with real and synthetically generated data using a Kalman-based object tracker to boost detection confidence. Our results indicate that augmenting the real data with an optimal subset of synthetic data can increase the performance. Moreover, temporal information gathered by object tracking methods can increase performance further.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.12389>)

[PDF](<https://arxiv.org/pdf/2111.12389.pdf>)

[Implementation](<https://github.com/tryolabs/norfair>)
