Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge (original) (raw)
Related papers
A DEEP LEARNING APPROACH TO CLASSIFY DRONES AND BIRDS
IRJET, 2023
Drones are gaining popularity not just for recreational use, but also for various engineering, disaster management, logistics, and airport security applications. However, their potential use in malicious activities has raised concerns about physical infrastructure security, safety, and surveillance at airports. There have been several reports in recent years of unauthorized drone use causing disruptions in airline operations. To address this problem, a new deep learning-based method has been proposed in this study. This approach is efficient in detecting and recognizing two types of drones and birds, and it outperforms existing detection systems in the literature. The physical and behavioral similarities between drones and birds often lead to confusion, but the proposed method can not only detect the presence or absence of drones but also distinguish between different types of drones and differentiate them from birds.
Drone-vs-Bird detection challenge at IEEE AVSS2017
2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2017
Small drones are a rising threat due to their possible misuse for illegal activities, in particular smuggling and terrorism. The project SafeShore, funded by the European Commission under the Horizon 2020 program, has launched the "drone-vs-bird detection challenge" to address one of the many technical issues arising in this context. The goal is to detect a drone appearing at some point in a video where birds may be also present: the algorithm should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds. This paper reports on the challenge proposal, evaluation, and results 1 .
Drone-vs-Bird Detection Challenge at IEEE AVSS2019
2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Small drones are a rising threat due to their possible misuse for illegal activities, in particular smuggling and terrorism. The project SafeShore, funded by the European Commission under the Horizon 2020 program, has launched the "drone-vs-bird detection challenge" to address one of the many technical issues arising in this context. The goal is to detect a drone appearing at some point in a video where birds may be also present: the algorithm should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds. This paper reports on the challenge proposal, evaluation, and results 1 .
Aerospace, 2022
Drones are becoming increasingly popular not only for recreational purposes but also in a variety of applications in engineering, disaster management, logistics, securing airports, and others. In addition to their useful applications, an alarming concern regarding physical infrastructure security, safety, and surveillance at airports has arisen due to the potential of their use in malicious activities. In recent years, there have been many reports of the unauthorized use of various types of drones at airports and the disruption of airline operations. To address this problem, this study proposes a novel deep learning-based method for the efficient detection and recognition of two types of drones and birds. Evaluation of the proposed approach with the prepared image dataset demonstrates better efficiency compared to existing detection systems in the literature. Furthermore, drones are often confused with birds because of their physical and behavioral similarity. The proposed method is...
Drone Detection Using Deep Learning
EPRA International Journal of Multidisciplinary Research (IJMR)
Drones have widespread application in real life and the industry is expanding rapidly. As they are growing increasingly it is more accessible to the public at cheaper prices. They are used for espionage and can be converted into gruesome weapons. Hence it is very important to monitor and detect unauthorized drones entering into the restricted regions in order to maintain peace and prevent chaos. The Technology stack implied here is You Only Look Once (YOLO v5) which is a real time object detection system. In recent times Yolo is a profound algorithm used for real time object or image detection . The Yolo trained model is trained with pictures of drones and birds so that the trained model can differentiate between and prevent false prediction of drones . Everytime a drone is detected in the camera an alert message is sent to the higher officials so that the drone could be eliminated. This algorithm comprises 3 techniques namely: Residual blocks, Bounding box regression and Intersecti...
Drone Detection Using Image Processing Based on Deep Learning
The Annals of "Dunărea de Jos" University of Galaţi, 2021
The objective of this experimental research is to identify solutions to detect drones using computer vision algorithm. Nowadays danger of drones operating near airports and other important sites is of utmost importance. The proposed techniques resolution pictures with a good rate of detection. The technique is using information concerning movement patterns of drones.
Drone Detection Using Convolutional Neural Networks
2020
In image processing, it is essential to detect and track air targets, especially UAVs. In this paper, we detect the flying drone using a fisheye camera. In the field of diagnosis and classification of objects, there are always many problems that prevent the development of rapid and significant progress in this area. During the previous decades, a couple of advanced classification methods such as convolutional neural networks and support vector machines have been developed. In this study, the drone was detected using three methods of classification of convolutional neural network (CNN), support vector machine (SVM), and nearest neighbor. The outcomes show that CNN, SVM, and nearest neighbor have total accuracy of 93%, 88%, and 80%, respectively. Compared with other classifiers with the same experimental conditions, the accuracy of the convolutional neural network classifier is satisfactory.
Model-Aided Drone Classification Using Convolutional Neural Networks
2022 IEEE Radar Conference (RadarConf22)
Classifiers using convolutional neural networks (CNNs) often yield high accuracies on samples that come from the same distribution as the training data. In this study we evaluate a CNN classifier's ability to discriminate drones from non-drone targets, such as birds, when they are not represented in the training data. We found that the mean accuracy on such out-of-distribution drones was 78%. By introducing a synthetic drone class, generated from a mathematical model, the out-ofdistribution drone accuracy was improved to 86%. When trained on all drone types the mean accuracy over all classes was 90%. The data was collected with a 77 GHz mechanically scanning radar with only 9 ms dwell time.
Machine learning CS-433 Drone and pigeon detection
2020
Drone detection is an important step to make drones more autonomous. Convolutional Neural Network (CNN) are a fundamental Machine Learning tool that can be used to create detection algorithms. This report will use the DEtection TRansformer[1] (DETR) architecture developed by Facebook in 2020 to build models able to identify and locate drones and pigeons on images. This architecture will be combined with ”ResNet18” and ”ResNet50” backbones to train models on images containing respectively drones and pigeons. The general findings of this paper shows promising baseline models that could be even more improved.
2019 11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)
As maritime smuggling is being combatted more effectively, the criminal "modus operandi" consists more frequently of using small aircraft and drones for drug transport. To address this issue, we report our efforts to develop a system capable of accurately tracking suspicious flying objects and identifying them on video streams. Our solution consists in coupling classical computer vision with deep learning to perform tracking and object detection. A discrete Kalman filter is used to predict the location of each object being tracked while the Hungarian algorithm is used to match objects between successive frames. Whenever a potential target is considered suspicious the input images are zoomed and fed into a deep learning pipeline that separates images into the classes aircraft, drones, birds or clouds. A literature survey indicates that this problem with important applications is yet to be fully explored.