西华大学学报（自然科学版）2025，Vol.44Issue(3)：19-28,10.DOI:10.12198/j.issn.1673-159X.4955
基于YOLOV5与Jetson TX2的航拍场景目标检测
Object Detection in Aerial Photography Scene Based on YOLOV5 and Jetson TX2
摘要
Abstract
The target detection technology based on convolutional neural network has been rapidly de-veloped and applied.Limited by the detection speed,its large-scale deployment and application on embed-ded platforms are always difficult.Breaking through the model time complexity on the basis of ensuring model accuracy has become the main problem of target detection technology.In order to explore the auto-matic detection method of targets based on microprocessors in the military field,this paper studies the milit-ary target detection system in aerial photography scenes based on YOLOv5,DOTA data set,and Jetson TX2.Firstly,the YOLOv5 model training was completed on the PC side based on the DOTA high-resolu-tion aerial scene target detection data set.The accuracy rate of the model was 54.76%,the recall rate was 81.47%,and the mAP@0.5 reached 74.12%;The target detection and analysis of three potential military target scen-arios in the seaport can still achieve good detection results in high-resolution aerial photography scenarios,and the inference speed reaches 181.8FPS.Finally,a military target detection system based on Jetson TX2 and UAV is designed to achieve The algorithm is transplanted from the PC side to the microprocessor side,and the model inference is completed on the Jetson TX2,and the inference speed reaches 16.13FPS.关键词
目标检测/深度学习/YOLOV5/Jetson TX2/检测速度Key words
object detection/deep learning/YOLOV5/Jetson TX2/inference speed分类
信息技术与安全科学引用本文复制引用
张焕,刘清华,路钊,潘云凡..基于YOLOV5与Jetson TX2的航拍场景目标检测[J].西华大学学报（自然科学版）,2025,44(3):19-28,10.基金项目
国防科学技术预先研究基金项目(KO01071). （KO01071）
