Investigation of UAV Detection in Images with Complex Backgrounds and Rainy Artifacts

TL;DR

This paper evaluates the performance of state-of-the-art vision-based object detection models for UAV detection in images with complex backgrounds and rain artifacts, providing insights for developing more robust detection methods.

Contribution

It introduces new datasets with complex backgrounds and rainy conditions, and benchmarks popular detection models under these challenging scenarios for the first time.

Findings

Performance varies significantly with background complexity and weather conditions.

Certain models show robustness to rain artifacts but struggle with complex backgrounds.

The study highlights the need for developing more resilient UAV detection algorithms.

Abstract

To detect unmanned aerial vehicles (UAVs) in real-time, computer vision and deep learning approaches are evolving research areas. Interest in this problem has grown due to concerns regarding the possible hazards and misuse of employing UAVs in many applications. These include potential privacy violations. To address the concerns, vision-based object detection methods have been developed for UAV detection. However, UAV detection in images with complex backgrounds and weather artifacts like rain has yet to be reasonably studied. Hence, for this purpose, we prepared two training datasets. The first dataset has the sky as its background and is called the Sky Background Dataset (SBD). The second training dataset has more complex scenes (with diverse backgrounds) and is named the Complex Background Dataset (CBD). Additionally, two test sets were prepared: one containing clear images and the other with images with three rain artifacts, named the Rainy Test Set (RTS). This work also focuses on benchmarking state-of-the-art object detection models, and to the best of our knowledge, it is the first to investigate the performance of recent and popular vision-based object detection methods for UAV detection under challenging conditions such as complex backgrounds, varying UAV sizes, and low-to-heavy rainy conditions. The findings presented in the paper shall help provide insights concerning the performance of the selected models for UAV detection under challenging conditions and pave the way to develop more robust UAV detection methods. The codes and datasets are available at: https://github.com/AdnanMunir294/UAVD-CBRA.