软件导刊2023，Vol.22Issue(12)：56-62,7.DOI:10.11907/rjdk.231712
面向无人机场景的深度网络模型压缩与加速设计方法
Compression and Acceleration Design Methods of Deep Network Models for UAV Scenes
摘要
Abstract
With the increasingly widespread application of drones,target detection technology in drone application scenarios has important ap-plication value and urgent application needs in many fields.In the scene of real-time detection of drone edge devices,due to the presence of a large number of weak target instances in the high-resolution images of drones,the image resolution will be directly reduced,resulting in the loss of weak targets.Therefore,it is crucial to maintain high-resolution information when inputting into the network.To achieve this,high-res-olution images are cut into multiple image blocks and used as network inputs to maintain network accuracy while enabling them to run on edge intelligent devices.At the same time,in order to accelerate the model inference speed,group convolution and channel shuffling strategies are used to lightweight design the backbone network of the detection algorithm,and channel attention mechanism is used to improve network accu-racy.The experiment shows that compared to YOLOv5,the proposed method improves accuracy by 2%and 4%on the unmanned aerial vehi-cle dataset VisDrone and the self built dataset OUC-UAV-DET,respectively,and reduces inference speed by 1 ms on the Nvidia hardware(Xavier).At the network pruning level,combining specific datasets for channel pruning of detection models can reduce inference speed by 2 ms while maintaining algorithm accuracy.In addition,for the single category detection task of unmanned aerial vehicles,optimizing the output part based on the relatively fixed size of the target instance can reduce the number of model parameters by 30%,resulting in a maximum reduc-tion of 2 ms in inference speed.关键词
无人机/高分辨率图像/目标检测/轻量化网络/网络剪枝/模型部署Key words
unmanned aerial vehicle/high resolution images/object detection/lightweight network/network pruning/model deployment分类
信息技术与安全科学引用本文复制引用
张佳奇,郭宣,李魏然,王胜科..面向无人机场景的深度网络模型压缩与加速设计方法[J].软件导刊,2023,22(12):56-62,7.基金项目
国家重点研发计划项目(2018AAA0100400) （2018AAA0100400）
山东省自然科学基金项目(ZR2020MF131,ZR2021ZD19) （ZR2020MF131,ZR2021ZD19）
青岛市科技计划项目(21-1-4-ny-19-nsh) （21-1-4-ny-19-nsh）
中国海洋大学社团培训项目(202265007) （202265007）
HY项目(LZY2022033004) （LZY2022033004）
