Real-Time and Accurate Drone Detection in a Video with a Static Background

Abstract

<jats:p> With the increasing number of drones, the danger of their illegal use has become relevant. This has necessitated the creation of automatic drone protection systems. One of the important tasks solved by these systems is the reliable detection of drones near guarded objects. This problem can be solved using various methods. From the point of view of the price–quality ratio, the use of video cameras for a drone detection is of great interest. However, drone detection using visual information is hampered by the large similarity of drones to other objects, such as birds or airplanes. In addition, drones can reach very high speeds, so detection should be done in real time. This paper addresses the problem of real-time drone detection with high accuracy. We divided the drone detection task into two separate tasks: the detection of moving objects and the classification of the detected object into drone, bird, and background. The moving object detection is based on background subtraction, while classification is performed using a convolutional neural network (CNN). The experimental results showed that the proposed approach can achieve an accuracy comparable to existing approaches at high processing speed. We also concluded that the main limitation of our detector is the dependence of its performance on the presence of a moving background.</jats:p>

Comparative Monte Carlo Analysis of Background Estimation Algorithms for Unmanned Aerial Vehicle Detection

“…Background estimation algorithms using machine learning open up new horizons for applications because their effectiveness is the result of the training patterns used, not heuritics, creating a knowledge base for the algorithm. One of the active research topics using CNN is the detection of drones and distinguishing them from bird images [29,30]. UAV images can be obtained with the use of thermovision, thanks to which they are much better distinguishable from the background [31].…”

Advanced Computational Intelligence for Object Detection, Feature Extraction and Recognition in Smart Sensor Environments

“…The topic of using computer vision for autonomous driving systems, aerial vehicles, and vessel classification has been covered by many innovative ideas. In [ 1 ], a model of a system developed for the detection of flying objects for automatic drone protection systems was presented. A proposed solution is composed of a background subtraction model which cooperates with the applied model of the convolutional neural network (CNN).…”

New Approach of UAV Movement Detection and Characterization Using Advanced Signal Processing Methods Based on UWB Sensing

“…Drone detection using images or videos captured by camera sensors is based on computer vision algorithms and can be performed by traditional machine learning algorithms [ 9 , 10 ] or deep learning-based algorithms [ 11 , 12 , 13 ]. For this approach, the line-of-sight (LoS) is mandatory and the performance depends on the quality of the image captured that may be degraded by adverse environment conditions such as fog, cloud, dust, or low ambient light.…”