文献类型：期刊文献

英文题名：High Speed Safe Autonomous Landing Marker Tracking of Fixed Wing Drone Based on Deep Learning

作者：Yuan, Baoxi[1,2,3];Ma, Wenyun[4];Wang, Feng[1,2,3]

第一作者：Yuan, Baoxi

通信作者：Yuan, BX[1];Yuan, BX[2];Yuan, BX[3]

机构：[1]Xijing Univ, Sch Elect Informat, Xian 710123, Shaanxi, Peoples R China;[2]Gansu Univ Chinese Med, Humanities Teaching Dept, Dingxi 743000, Gansu, Peoples R China;[3]Shaanxi Key Lab Integrated & Intelligent Nav, Xian 710065, Shaanxi, Peoples R China;[4]Xijing Univ, Xian Key Lab High Precis Ind Intelligent Vis Meas, Xian 710123, Shaanxi, Peoples R China

第一机构：Xijing Univ, Sch Elect Informat, Xian 710123, Shaanxi, Peoples R China

通信机构：[1]corresponding author), Xijing Univ, Sch Elect Informat, Xian 710123, Shaanxi, Peoples R China;[2]corresponding author), Gansu Univ Chinese Med, Humanities Teaching Dept, Dingxi 743000, Gansu, Peoples R China;[3]corresponding author), Shaanxi Key Lab Integrated & Intelligent Nav, Xian 710065, Shaanxi, Peoples R China.|[10735]甘肃中医药大学;

年份：2022

卷号：10

起止页码：80415

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20223312569354);Scopus(收录号：2-s2.0-85135747415);WOS:【SCI-EXPANDED(收录号:WOS:000838622600001)】；

基金：This work was supported in part by the Foundation of Shaanxi Key Laboratory of Integrated and Intelligent Navigation under Grant SKLIIN-20190102; in part by the Natural Science Foundation of Shaanxi Province under Grant 2021JM-537, Grant 2019JQ-936, and Grant 2021GY-341; and in part by the Research Foundation for Talented Scholars of Xijing University under Grant XJ20B01, Grant XJ19B01, and Grant XJ17B06.

语种：英文

外文关键词：Target tracking; Navigation; Visualization; Object detection; Feature extraction; Global Positioning System; Unmanned aerial vehicle (UAV); drone; autonomous landing; target detection; target tracking; deep learning

摘要：Most of the current research on autonomous landing of Unmanned Aerial Vehicles (UAVs) focus on rotorcrafts, which can fly horizontally over the landing site and then land vertically, with less landing risk. However, some of the unmanned fixed-wing aircrafts take off and land in the sliding mode of wheel landing gears, and their landing stage is difficult to control and easier to failure. In this paper, the autonomous landing of the fixed wing UAVs based on the visual navigation is studied. We propose a deep learning based Vision Transformer Particle Region-based Convolutional Neural Network (VitP-RCNN). Our VitP-RCNN uses Mobile Vision Transformers (MobileViT) as the backbone to accelerate feature extraction. Regarding the innovation of the present study, it is noticed that candidate boxes are chosen as the particles in our methodology, where the confidence is defined as the particle weight, the spatio-temopral correlation between adjacent image is used in video tracking and the Particle Filter theory is employed into the two-stage detection network to construct the present VitP-RCNN. Based on the spatial-temporal correlation, Our VitP-RCNN is efficient in predicting the particle state in the next frame through the state of the previous frame, so as to realize the continuous tracking of the landing marker. The experimental results show that on the Jetson AGX Xavier drone platform, our speed is up to 51FPS, enabling us to perform the landing marker tracking for the autonomous landing of the fixed-wing drones.