Abstract
Aiming at the problems of the large amount of model parameters and false and missing detections of multi-scale drone targets, we present a novel drone detection method, YOLOv4-MCA, based on the lightweight MobileViT and Coordinate Attention. The proposed approach is improved according to the framework of YOLOv4. Firstly, we use an improved lightweight MobileViT as the feature extraction backbone network, which can fully extract the local and global feature representations of the object and reduce the model’s complexity. Secondly, we adopt Coordinate Attention to improve PANet and to obtain a multi-scale attention called CA-PANet, which can obtain more positional information and promote the fusion of information with low- and high-dimensional features. Thirdly, we utilize the improved K-means++ method to optimize the object anchor box and improve the detection efficiency. At last, we construct a drone dataset and conduct a performance experiment based on the Mosaic data augmentation method. The experimental results show that the mAP of the proposed approach reaches 92.81%, the FPS reaches 40 f/s, and the number of parameters is only 13.47 M, which is better than mainstream algorithms and achieves a high detection accuracy for multi-scale drone targets using a low number of parameters.
Funder
Theoretical Research Project
Fusion Special Project of Anhui Province
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference32 articles.
1. Development status of anti-low-slow and small UAV systems;Yuan;Electron. World,2021
2. Review of low and slow small UAV target detection technology;Jiang;Maneuverable Missile,2020
3. Mendis, G.J., Randeny, T., Wei, J., and Madanayake, A. (2016, January 1–3). Deep learning based doppler radar for micro UAS detection and classifica-tion. Proceedings of the Military Communications Conference, Baltimore, MD, USA.
4. Unauthor-ized Amateur UAV Detection Based on WiFi Statistical Fin-gerprint Analysis;Bisio;IEEE Commun. Mag.,2017
5. Hough Transform for UAV’s Acoustic Signals Detection;Bougaiov;Adv. Sci. J.,2015
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献