An Integrated Vision-based Detection-tracking-estimation System for Dynamic Localization of Small Aerial Vehicles

Srigrarom, Sutthiphong; Lee, Shawndy Michael; Lee, Mengda; Foong, Shaohui; Ratsamee, Photchara

doi:10.1109/iccre49379.2020.9096259

Cited by 15 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Novel approach for detection and 3D localization of drones using a hybrid motion-based object detector has been described by Srigrarom and Hoe Chew [26]. Another approach for dynamic tracking and localization of small aerial vehicles based on computer vision has been demonstrated by Srigrarom et al [27].…”

Section: Related Workmentioning

confidence: 99%

Lightweight Multi-Drone Detection and 3D-Localization via YOLO

Sharma¹,

Nitik²,

Kothari³

2022

Preprint

View full text Add to dashboard Cite

In this work, we present and evaluate a method to perform real-time multiple drone detection and three-dimensional localization using state-of-the-art tiny-YOLOv4 object detection algorithm and stereo triangulation. Our computer vision approach eliminates the need for computationally expensive stereo matching algorithms, thereby significantly reducing the memory footprint and making it deployable on embedded systems. Our drone detection system is highly modular (with support for various detection algorithms) and capable of identifying multiple drones in a system, with real-time detection accuracy of up to 77% with an average FPS of 332 (on Nvidia Titan Xp). We also test the complete pipeline in AirSim environment, detecting drones at a maximum distance of 8 meters, with a mean error of 23% of the distance. We also release the source code for the project, with pre-trained models and the curated synthetic stereo dataset which can be found at github.com/aryanshar/swarm-detection

show abstract

Section: Related Workmentioning

confidence: 99%

Lightweight Multi-Drone Detection and 3D-Localization via YOLO

Sharma¹,

Nitik²,

Kothari³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The advantages of optical sensors in combination with the rapid advances in computer vision (CV) have especially accelerated the research and development of imagebased detection techniques built on deep learning (DL) algorithms [5,8,[10][11][12][13][14]. Despite the promising performance of modern object detectors (e.g., region-based convolutional neural networks (R-CNNs) [15][16][17], single-shot multibox detector (SSD) [18], or you only look once (YOLO) [19]), developing robust drone detection algorithms has proven to be a challenging task which necessitates large amounts of diversified and annotated data.…”

Section: Introductionmentioning

confidence: 99%

Quantifying the Simulation–Reality Gap for Deep Learning-Based Drone Detection

Dieter

Weinmann²,

Jäger

et al. 2023

Electronics

View full text Add to dashboard Cite

The detection of drones or unmanned aerial vehicles is a crucial component in protecting safety-critical infrastructures and maintaining privacy for individuals and organizations. The widespread use of optical sensors for perimeter surveillance has made optical sensors a popular choice for data collection in the context of drone detection. However, efficiently processing the obtained sensor data poses a significant challenge. Even though deep learning-based object detection models have shown promising results, their effectiveness depends on large amounts of annotated training data, which is time consuming and resource intensive to acquire. Therefore, this work investigates the applicability of synthetically generated data obtained through physically realistic simulations based on three-dimensional environments for deep learning-based drone detection. Specifically, we introduce a novel three-dimensional simulation approach built on Unreal Engine and Microsoft AirSim for generating synthetic drone data. Furthermore, we quantify the respective simulation–reality gap and evaluate established techniques for mitigating this gap by systematically exploring different compositions of real and synthetic data. Additionally, we analyze the adaptation of the simulation setup as part of a feedback loop-based training strategy and highlight the benefits of a simulation-based training setup for image-based drone detection, compared to a training strategy relying exclusively on real-world data.

show abstract