AD-YOLOv5s based UAV detection for low altitude security

Abstract

UAV (Unmanned Aerial Vehicle) black flight at low altitude could cause serious safety risks. Consequently, it is crucial to detect and manage low altitude small UAVs. The existing methods of low altitude small UAV detection suffer from problems such as high false alarm rate, and poor real-time performance. In order to solve the above problems, we present a novel approach, named AD-YOLOv5s, to achieve low altitude small UAV detection with high precision and high real-time performance. Firstly, the feature enhancement method is used to expand the dataset. We optimize the model feature fusion, the prediction head structure, and the loss function. Based on the CBAM (Convolutional Block Attention Module) attention mechanism, feature enhancement is performed to improve the detection accuracy. Secondly, the ghost module and depthwise separable convolution are used to reduce the number of parameters of the model, and we propose the method of lightweight design of model to improve the detection speed. Compared with the YOLOv5s model, the experiment result shows that our proposed AD-YOLOv5s model improves the value of mAP by 2.2% and the value of Recall by 1.8%, reduces the value of GFLOPs by 29.9% and parameters by 38.8%, and achieves 27.6 FPS when the proposed model deploy on a low-cost edge computing device (jetson nano).

UAV detection using neural networks

“…Еще стоит отметить статью, посвященную усовершенствованию модели YOLOv5 [8] с целью уменьшения числа параметров и ускорения. В работе используется набор данных, содержащий порядка 8000 дронов среднего размера (до 32 × 32) и порядка 1000 штук размера 8 × 8 и меньше.…”

“…• Набор изображений дронов «Drone Dataset (UAV)» c сайта Kaggle Поиск остальных открытых наборов данных был затруднен тем, что информация о них содержится только в научных статьях по обнаружению дронов. Так в открытом доступе был найден набор данных FL-dataset 8 , который содержит 14 черно-белых видео с дронами (38948 кадров) разрешения 752×480, съемка с дрона, в кадре одновременно до 2-х дронов. Минимальный, средний и максимальный размеры дронов: 9×9, 25.5×16.4 и 259×197 соответственно.…”

Advances and Challenges in Drone Detection and Classification Techniques: A State-of-the-Art Review

“…In recent years, many research works have been published to address UAV detection, tracking, and classification problems. The main drone detection technologies are: radar sensors [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ], RF sensors [ 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 ], audio sensors [ 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 ], and camera sensors using visual UAV characteristics [ 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 ]. Based on the above-mentioned sources, the advantages and disadvantages of each drone detection technology are compared in Table 2 .…”

“…Object detection with learned features based on one-stage detectors : In [ 61 ], the authors proposed a novel anti-drone YOLOv5s approach to detect low-altitude small-sized UAVs, which is mainly oriented towards border defense applications. Initially, the low-altitude, small-size object detection problem was solved based on the optimization method for feature enhancement.…”

“…The process of capturing visual data from objects is called image acquisition and consists of three main steps: first, energy is reflected from the object of interest; then, it is focused by an optical system; and finally, the amount of energy is measured using a camera sensor (see Figure 5). Object detection with learned features based on one-stage detectors: In [61], the authors proposed a novel anti-drone YOLOv5s approach to detect low-altitude small-sized UAVs, which is mainly oriented towards border defense applications. Initially, the low-altitude, small-size object detection problem was solved based on the optimization method for feature enhancement.…”