航空兵器2025，Vol.32Issue(2)：104-112,9.DOI:10.12132/ISSN.1673-5048.2024.0175
基于复合缩放的动态航拍小目标检测算法
Dynamic Aerial Small Target Detection Algorithm Based on Compound Zoom Scaling
摘要
Abstract
Unmanned aerial vehicles(UAVs)equipped with computer vision technology have emerged as a po-werful tool for information acquisition and are widely applied across various fields.However,during multi-angle ima-ging,UAVs often encounter challenges such as a low target pixel ratio and significant background interference,leading to missed detection and false detection.To address these issues,this paper proposes a novel small-object detection al-gorithm.Firstly,a more efficient backbone network is introduced,and a composite scaling method is employed to opti-mize the balance among network depth,width,and image resolution.Additionally,an attention mechanism is integ-rated to effectively capture contextual details of targets with varying scales,orientations,and shapes by leveraging the hierarchical connections of the C2f module,and parallel network is further utilized to enhance interactive modeling of small-target positional information.Secondly,to mitigate the issue of low pixel utilization ratio in small-target detec-tion,a DTADH module is designed,and a shared feature interaction module is constructed.This module,coupled with a task alignment predictor,facilitates both target classification and localization allocation,and the task decomposition is performed by dynamically computing task features through an attention mechanism,thereby reducing the number of pa-rameters effectively and enhancing overall performance.Experiments conducted on the VisDrone2019 UAV aerial ima-gery dataset demonstrate that the proposed algorithm improves mAP by 2.1％,reduces FLOPs by 32.5％,and decrea-ses computational complexity,resulting in superior detection performance.关键词
深度学习/目标检测/注意力机制/计算机视觉/复合缩放/航拍/无人机Key words
deep learning/target detection/attention mechanism/computer vision/compound zoom scaling/aerial imagery/UAV分类
武器工业引用本文复制引用
蒋源,朱高峰,朱凤华,熊刚..基于复合缩放的动态航拍小目标检测算法[J].航空兵器,2025,32(2):104-112,9.基金项目
国家自然科学基金项目(U1909204) （U1909204）
江西省自然科学基金项目(20232ABC03A07) （20232ABC03A07）
