[1]李琛,丁胜,付佳俊.基于LOD-RSINet的轻量化遥感图像目标检测[J].计算机技术与发展,2024,34(12):165-171.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0277]
　LI Chen,DING Sheng,FU Jia-jun.Lightweight Remote Sensing Images Object Detection Based on LOD-RSINet[J].,2024,34(12):165-171.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0277]
点击复制

基于LOD-RSINet的轻量化遥感图像目标检测()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年12期
页码:
165-171
栏目:
人工智能
出版日期:
2024-12-10

文章信息/Info

Title:
Lightweight Remote Sensing Images Object Detection Based on LOD-RSINet
文章编号:
1673-629X(2024)12-0165-07
作者:
李琛1; 2; 丁胜1; 2; 付佳俊1; 2
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065;2. 武汉科技大学 智能信息处理与实时工业系统湖北省重点实验室,湖北 武汉 430065
Author(s):
LI Chen1; 2; DING Sheng1; 2; FU Jia-jun1; 2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;2. Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial Systems,Wuhan University of Science and Technology,Wuhan 430065,China
关键词:
YOLOv8; 轻量化; 遥感图像目标检测; 跨尺度特征融合; 损失函数
Keywords:
YOLOv8; lightweight; remote sensing images object detection; cross-scale feature fusion; loss function
分类号:
TP391
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0277
摘要:
为了满足遥感图像目标检测任务中轻量化和快速推理的需求,提出了一种基于改进 YOLOv8s 的轻量化遥感图像目标检测算法(A Lightweight Object Detection Network for Remote Sensing Images,LOD-RSINet)。 首先,提出基于 SENetv2 机制构建的 C2SE(C2f-SENetv2)模块,在略微增加模型参数量的同时让网络更有效地学习到输入数据的不同特征,提升特征表达的精细度和全局信息的整合能力;其次,设计一种轻量级跨尺度特征融合模块 CCFM,以增强模型对于尺度变化的适应性和对小目标的检测能力,在不影响模型检测精度的情况下降低了参数量并提高了检测速度;最后,引入了一种 Shape IoU 损失函数,通过关注边界框本身的形状和尺度来计算损失,从而使边界框回归更加准确。 实验证明,改进后的算法在 DIOR 数据集上的检测精度 mAP50 和 mAP50-95 分别达到了 0. 867 和 0. 668,参数量 GFLOPs 降低了 5. 61 百分点,检测速度 FPS 提高了 5. 94 百分点,性能表现优于其他对比方法,能够在轻量化的同时提高模型的目标检测能力。
Abstract:
In order to meet the needs of lightweight and fast inference in remote sensing image target detection tasks,a lightweight remote sensing image target detection algorithm (A Lightweight Object Detection Network for Remote Sensing Images,LOD-RSINet) based on improved YOLOv8s is proposed. Firstly,a C2SE (C2f-SENetv2) module based on the SENetv2 mechanism is proposed,which slightly increases the number of model parameters while allowing the network to learn different features of the input data more efficiently,and im-proves the finesse of feature expression and the integration of global information. Secondly,a lightweight cross - scale feature fusion module,CCFM,is designed to enhance the model’s adaptability to scale changes and its ability to detect small targets,which reduces the number of parameters and improves the detection speed without affecting the model’s detection accuracy. Finally, a Shape IoU loss function is introduced to calculate the loss by focusing on the shape and scale of the bounding box itself,which makes the bounding box regression more accurate. Experiments demonstrate that the improved algorithm achieves detection accuracy mAP50 and mAP50-95 of 0. 867 and 0. 668 on the DIOR dataset,respectively,with a reduction of 5. 61 percentage points in the number of parametric GFLOPs,and an improvement of 5. 94 percentage points in the detection speed FPS,which outperforms the other comparative methods,and is able to improve the model’s target detection capability while being lightweight.

相似文献/References:

[1]熊 毅.中小企业轻量化无线企业网架构方案研究[J].计算机技术与发展,2020,30(05):195.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 037]
　XIONG Yi.Research on Structure Scheme of Lightweight Wireless Enterprise Network for Small and Medium Enterprises[J].,2020,30(12):195.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 037]
[2]余 进,史燕中,王春华,等.一种轻量化目标检测算法研究[J].计算机技术与发展,2020,30(11):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
　YU Jin,SHI Yan-zhong,WANG Chun-hua,et al.Research of a Lightweight Object Detection Algorithm[J].,2020,30(12):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
[3]许 伟,熊卫华.一种改进的轻量级垃圾目标检测算法[J].计算机技术与发展,2022,32(02):63.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 010]
　XU Wei,XIONG Wei-hua.An Improved Lightweight Garbage Target Detection Algorithm[J].,2022,32(12):63.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 010]
[4]盛良睿,程 旗,李 捷,等.基于稀疏裁剪和深度可分离的轻量化方法[J].计算机技术与发展,2022,32(S1):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 008]
　SHENG Liang-rui,CHENG Qi,LI Jie,et al.Lightweight Method Based on Sparse Clipping and Depth Separability[J].,2022,32(12):36.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 008]
[5]张国有,高 希.融合注意力的轻量型垃圾分类研究[J].计算机技术与发展,2023,33(03):49.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 008]
　ZHANG Guo-you,GAO Xi.Research on Lightweight Garbage Sorting with Fusion Attention[J].,2023,33(12):49.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 008]
[6]朱昭云,张 波,叶昭良,等.基于 YOLOv5s 的海上风电设施检测与预警评估[J].计算机技术与发展,2023,33(04):182.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 027]
　ZHU Zhao-yun,ZHANG Bo,YE Zhao-liang,et al.Offshore Wind Power Facilities Detection and Early Warning Assessment Based on Improved YOLOv5s[J].,2023,33(12):182.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 027]
[7]章佳琪,肖 建 *.DID-YOLO:一种适用于嵌入式设备的移动机器人目标检测算法[J].计算机技术与发展,2023,33(10):8.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 002]
　ZHANG Jia-qi,XIAO Jian *.DID-YOLO:A Mobile Robot Target Detection Algorithm for Embedded Devices[J].,2023,33(12):8.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 002]
[8]熊风光,陈 霖,韩慧妍,等.基于 MQTT 协议的轻量化文本信息分发技术研究[J].计算机技术与发展,2024,34(02):90.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 014]
　XIONG Feng-guang,CHEN Lin,HAN Hui-yan,et al.Research on Lightweight Text Information Distribution Technology Based on MQTT Protocol[J].,2024,34(12):90.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 014]
[9]张 杨,辛国江,王 鑫,等.基于改进的 YOLOv5 网络的舌象检测算法[J].计算机技术与发展,2024,34(02):156.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 023]
　ZHANG Yang,XIN Guo-jiang,WANG Xin,et al.Tongue Image Detection Algorithm Based on Improved YOLOv5 Network[J].,2024,34(12):156.[doi:10. 3969 / j. issn. 1673-629X. 2024. 02. 023]
[10]沈学利,关刘美,翟宇琦.基于卷积神经网络的颜色修正水下图像增强方法[J].计算机技术与发展,2024,34(08):42.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0130]
　SHEN Xue-li,GUAN Liu-mei,ZHAI Yu-qi.Color Correction Underwater Image Enhancement Method Based on Convolutional Neural Network[J].,2024,34(12):42.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0130]
[11]王一评,王改华.智能看护场景下的婴幼儿表情识别[J].计算机技术与发展,2025,(02):16.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0307]
　WANG Yi-ping,WANG Gai-hua.Infants Expression Recognition in Intelligent Nursing Scene[J].,2025,(12):16.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0307]

更新日期/Last Update: 2024-12-10