UAVAI-YOLO：无人机航拍图像的小目标检测模型

何植仟; 曹立杰

doi:10.11959/j.issn.2096-6652.202422

您当前的位置：

首页 >

文章列表页 >

UAVAI-YOLO：无人机航拍图像的小目标检测模型

学术论文 | 更新时间：2024-08-06

- UAVAI-YOLO：无人机航拍图像的小目标检测模型
- UAVAI-YOLO: dense small target detection algorithm based on UAV aerial images
- 智能科学与技术学报 2024年6卷第2期页码：262-271
- 作者机构：
  
  1.大连海洋大学信息工程学院，辽宁大连 116023
  2.辽宁省海洋信息技术重点实验室，辽宁大连 116023
- 作者简介：
  
  [ "何植仟（1997- ），男，大连海洋大学信息工程学院硕士生，主要研究方向为计算机视觉、图像处理。" ]
  [ "曹立杰（1978- ），女，博士，大连海洋大学信息工程学院副教授、副院长，主要研究方向为计算机视觉、无线传感器网络。" ]
- 基金信息：
  
  辽宁省教育厅科研项目(LJKZ0731)
- DOI：10.11959/j.issn.2096-6652.202422
  中图分类号： TP391
- 收稿：2024-04-10，
  
  修回：2024-05-21，
  
  纸质出版：2024-06-15
- 稿件说明：
移动端阅览
何植仟,曹立杰.UAVAI-YOLO：无人机航拍图像的小目标检测模型[J].智能科学与技术学报,2024,06(02):262-271.

HE Zhiqian,CAO Lijie.UAVAI-YOLO: dense small target detection algorithm based on UAV aerial images[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):262-271.
何植仟,曹立杰.UAVAI-YOLO：无人机航拍图像的小目标检测模型[J].智能科学与技术学报,2024,06(02):262-271. DOI： 10.11959/j.issn.2096-6652.202422.

HE Zhiqian,CAO Lijie.UAVAI-YOLO: dense small target detection algorithm based on UAV aerial images[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):262-271. DOI： 10.11959/j.issn.2096-6652.202422.

摘要

针对无人机航拍图像目标检测效果差的问题，提出改进的UAVAI-YOLO模型。首先，为使模型获得更加丰富的语义信息，使用改进可变形卷积网络（deformable convolutional networks，DCN）替换原骨干（backbone）网络部分通道到像素（channel-to-pixel，C2f）模块原始卷积。其次，为增加P2特征层而不增加模型参数量，提出Conv_C模块将骨干网络输出通道降维，同时避免通道降维导致的语义信息丢失，使用改进ODConv卷积替换颈部（neck）部分C2f模块原始卷积。然后，为充分利用上下文语义信息，引入双向特征金字塔网络（bidirectional feature pyramid network，BIFPN）。最后使用Wise-IoU替换原始损失函数，提高模型目标检测框的准确性。在公开的VisDrone2019数据集和UAVDT数据集的实验结果表明，UAVAI-YOLO模型相比于原YOLOv8n模型mAP@0.5分别提升了4.4%和1.1%。与其他主流目标检测模型相比具有较高的检测性精度。

Abstract

An improved UAVAI-YOLO model was proposed to address the problem of poor target detection in UAV aerial images. Firstly

in order to obtain richer semantic information for the model

the original convolution of the C2f module of the original backbone part was replaced with the improved DCN convolution. Secondly

in order to increase the P2 feature layer without increasing the number of model parameters

the Conv_C module was proposed to downscale the output channel of the backbone network

and at the same time

because of avoiding the loss of semantic information due to channel downsizing

the original convolution of the C2f module in the neck part was replaced by the improved ODConv dynamic convolution. Then

the BIFPN module was introduced to make full use of the contextual semantic information. Finally

Wise-IoU was used to replace the original loss function to improve the accuracy of the model target detection frame. Experimental results on the publicly available VisDrone2019 dataset and UAVDT dataset showed that the UAVAI-YOLO model improves 4.4% and 1.1% compared to the original YOLOv8n model mAP0.5

respectively

high detectability accuracy compared to other mainstream object detection models.

关键词

Keywords

references

宗有帅, 俞明, 张红顺, 等. 美军大中型察打一体无人机发展特点及趋势[J]. 战术导弹技术, 2022(6): 32-41.

ZONG Y S, YU M, ZHANG H S, et al. Developing characteristics and trend of US military's large and medium-sized reconnaissance/strike UAV[J]. Tactical Missile Technology, 2022(6): 32-41.

欧阳桃花, 郑舒文, 张凤, 等. 研究型大学服务国家战略工程研究:以长鹰无人机原始创新为例[J]. 科学学与科学技术管理, 2023, 44(1): 20-37.

OUYANG T H, ZHENG S W, ZHANG F, et al. Research on national strategic engineering of research universities: a case study of the original innovation from changying UAV[J]. Science of Science and Management of S & T, 2023, 44(1): 20-37.

LUCAS Simon, 沈甜雨, 王晓, 等. 基于统计前向规划算法的游戏通用人工智能[J]. 智能科学与技术学报, 2019, 1(3): 219-227.

SIMON L, SHEN T Y, WANG X, et al. General game AI with statistical forward planning algorithms[J]. Chinese Journal of Intelligent Science and Technology, 2019, 1(3): 219-227.

QU Z, GAO L Y, WANG S Y, et al. An improved YOLOv5 method for large objects detection with multi-scale feature cross-layer fusion network[J]. Image and Vision Computing, 2022, 125: 104518.

黄路, 李泽平, 杨文帮, 等. 基于区域感知的多尺度目标检测算法[J].计算机工程, 2023, 49(12): 178-185.

HUANG L, LI Z P, YANG W B, et al. Multi-scale target detection algorithm based on area awareness[J]. Computer Engineering, 2023, 49(12): 178-185.

张朝阳, 张上, 王恒涛, 等. 多尺度下遥感小目标多头注意力检测[J]. 计算机工程与应用, 2023, 59(8): 227-238.

ZHANG Z Y, ZHANG S, WANG H T, et al. Multi-head attention detection of small targets in remote sensing at multiple scales[J]. Computer Engineering and Applications, 2023, 59(8): 227-238.

刘晋川, 黎向锋, 刘安旭, 等. 改进RetinaNet的无人机小目标检测[J]. 科学技术与工程, 2023, 23(1): 274-282.

LIU J C, LI X F, LIU A X, et al. Improved RetinaNet for unmanned aerial vehicle small target detection[J]. Science Technology and Engineering, 2023, 23(1): 274-282.

JU M R, LUO J N, LIU G Q, et al. A real-time small target detection network[J]. Signal, Image and Video Processing, 2021, 15(6): 1265-1273.

胡均平, 王鸿树, 戴小标, 等. 改进YOLOv5的小目标交通标志实时检测算法[J]. 计算机工程与应用, 2023, 59(2): 185-193.

HU J P, WANG H S, DAI X B, et al. Real-time detection algorithm for small-target traffic signs based on improved YOLOv5[J]. Computer Engineering and Applications, 2023, 59(2): 185-193.

SHAO Y F, YANG Z X, LI Z H, et al. Aero-YOLO: an efficient vehicle and pedestrian detection algorithm based on unmanned aerial imagery[J]. Electronics, 2024, 13(7): 1190.

CAI D L, ZHANG Z Y, ZHANG Z. Corner-point and foreground-area IoU loss: better localization of small objects in bounding box regression[J]. Sensors, 2023, 23(10): 4961.

顾宙瑜, 於跃成, 者甜甜. Rapider-YOLOX:高效的轻量级目标检测网络[J]. 智能科学与技术学报, 2023, 5(1): 92-103.

GU Z Y, YU Y C, ZHE T T. Rapider-YOLOX: lightweight object detection network with high precision[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(1): 92-103.

宋华杰, 周磊. 基于函数改进的YOLOv3车辆检测与识别算法[J]. 智能科学与技术学报, 2023, 5(4): 535-542.

SONG H J, ZHOU L. Vehicle detection and recognition algorithm based on function improvement of YOLOv3[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 535-542.

DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2017: 764-773.

TONG Z J, CHEN Y H, XU Z W, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB]. arXiv preprint, 2023, arXiv: 2301.10051v3.

DU D W, ZHU P F, WEN L Y, et al. VisDrone-DET2019: the vision meets drone object detection in image challenge results[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Piscataway: IEEE Press, 2019: 213-226.

YU H Y, LI G R, ZHANG W G, et al. The unmanned aerial vehicle benchmark: Object detection, tracking and baseline[J]. International Journal of Computer Vision, 2020, 128(5): 1141-1159.

LIAO J J, PIAO Y C, SU J H, et al. Unsupervised cluster guided object detection in aerial images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 11204-11216.

TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 10778-10787.

YANG R J, LI W F, SHANG X N, et al. KPE-YOLOv5: an improved small target detection algorithm based on YOLOv5[J]. Electronics, 2023, 12(4): 817.

LIU C, YANG D G, TANG L, et al. A lightweight object detector based on spatial-coordinate self-attention for UAV aerial images[J]. Remote Sensing, 2022, 15(1): 83.

LI C L, YANG T, ZHU S J, et al. Density map guided object detection in aerial images[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE Press, 2020: 737-746.

DAI J F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks[C]// Proceedings of the 29th Annual Conference on Neural Information Processing Systems, [S.l.:s.n.], 2016: 379-387.

浏览量

354

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

注意力机制增强的输煤传送带异物检测

Cerberus：基于深度学习的跨站社交网络机器人检测系统