[1]牛为华,郭迅.融合分块注意力与小波特征聚合的遥感图像目标检测算法[J].智能系统学报,2026,21(3):763-775.[doi:10.11992/tis.202507006]
NIU Weihua,GUO Xun.Remote sensing object detection algorithm integrating block attention and wavelet feature aggregation[J].CAAI Transactions on Intelligent Systems,2026,21(3):763-775.[doi:10.11992/tis.202507006]
点击复制
NIU Weihua,GUO Xun.Remote sensing object detection algorithm integrating block attention and wavelet feature aggregation[J].CAAI Transactions on Intelligent Systems,2026,21(3):763-775.[doi:10.11992/tis.202507006]
融合分块注意力与小波特征聚合的遥感图像目标检测算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第3期
页码:
763-775
栏目:
学术论文—人工智能基础
出版日期:
2026-05-05
- Title:
- Remote sensing object detection algorithm integrating block attention and wavelet feature aggregation
- Keywords:
- object detection; remote sensing imagery; wavelet transform; YOLO; attention mechanism; small object detection; feature extraction; feature fusion
- 分类号:
- TP391.41
- 文献标志码:
- 2026-3-9
- 摘要:
- 针对遥感图像中目标背景复杂和小目标物体检测困难等问题，提出融合分块注意力与小波特征聚合的遥感图像目标检测算法。在主干网络中引入层级分块注意力模块，采用分块下采样操作进行下采样操作，同时融合坐标注意力机制，缓解了细粒度信息丢失的问题；设计融合小波增强的对比驱动特征聚合模块，采用Haar小波变换分离图像高低频信息，并构建局部注意力机制，增强模型对目标边缘与纹理细节的感知能力，抑制复杂背景的干扰；构建浅层注意力增强检测头，融合LSKA（large selective kernel attention）注意力机制增强模型对小目标物体的检测精度。实验结果表明，改进后算法在ShipRSImageNet与VisDrone2019数据集上的mAP50分别达到87.3%与35.5%，相比原始模型分别提升5.9%和4.1%。改进后的模型在遥感图像目标检测任务上的性能得到了有效的提升。
- Abstract:
- A remote sensing image object detection algorithm is proposed to address the challenges of complex backgrounds and small object detection. A hierarchical split attention block attention module is introduced into the backbone network, utilizing block-based downsampling and coordinate attention to mitigate fine-grained information loss. Using the Haar wavelet transform, a wavelet-enhanced contrast-driven feature aggregation module separates high- and low-frequency information, while a local attention mechanism enhances edge and texture perception, suppressing background interference. A shallow enhancement attention detection head with the LSKA attention mechanism improves small object detection accuracy. Experimental results show that the algorithm achieves an mAP50 of 87.3% on the ShipRSImageNet dataset and 35.5% on the VisDrone2019 dataset, with improvements of 5.9% and 4.1%, respectively, over the original model. The improved model considerably enhances performance in remote sensing image object detection.
- 参考文献/References:
-
[1] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). Piscataway: IEEE, 2005: 886-893.
[2] GAN Lu, LIU Peng, WANG Lizhe. Rotation sliding window of the hog feature in remote sensing images for ship detection[C]//2015 8th International Symposium on Computational Intelligence and Design. Piscataway: IEEE, 2016: 401-404.
[3] BI Fukun, YANG Zhihua, LEI Mingyang, et al. Airport aircraft detection based on local context DPM in remote sensing images[C]//2019 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2019: 1362-1365.
[4] DIVVALA S K, EFROS A A, HEBERT M. How important are “deformable parts” in the deformable parts model? [C]//Computer Vision–ECCV 2012. Workshops and Demonstrations. Berlin: Springer, 2012: 31-40.
[5] WANG Xuan, WANG Aoran, YI Jinglei, et al. Small object detection based on deep learning for remote sensing: a comprehensive review[J]. Remote sensing, 2023, 15(13): 3265
[6] 姬晓飞, 秦宁丽, 刘洋. 多特征的光学遥感图像多目标识别算法[J]. 智能系统学报, 2016, 11(5): 655-662 JI Xiaofei, QIN Ningli, LIU Yang. Research on multi-feature based multi-target recognition algorithm for optical remote sensing image[J]. CAAI transactions on intelligent systems, 2016, 11(5): 655-662
[7] LI Yuanyuan, ZHOU Zhengguo, QI Guanqiu, et al. Remote sensing micro-object detection under global and local attention mechanism[J]. Remote sensing, 2024, 16(4): 644
[8] 魏谢根, 曹林, 田澍, 等. 基于多层级自注意力增强的遥感目标检测[J]. 激光与光电子学进展, 2023, 60(20): 2028004 WEI Xiegen, CAO Lin, TIAN Shu, et al. Remote sensing target detection based on multilevel self-attention enhancement[J]. Laser & optoelectronics progress, 2023, 60(20): 2028004
[9] SU Haozheng, YOU Yanan, MENG Gang. Multi-scale context-aware R-cnn for few-shot object detection in remote sensing images[C]//2022 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2022: 1908-1911.
[10] 姚婷婷, 肇恒鑫, 冯子豪, 等. 上下文感知多感受野融合网络的定向遥感目标检测[J]. 电子与信息学报, 2025, 47(1): 233-243 YAO Tingting, ZHAO Hengxin, FENG Zihao, et al. A context-aware multiple receptive field fusion network for oriented object detection in remote sensing images[J]. Journal of electronics & information technology, 2025, 47(1): 233-243
[11] 文斌, 张俊, 王浚银, 等. 基于FNM-Net的轻量级遥感目标检测算法[J]. 现代电子技术, 2025, 48(13): 1-10 WEN Bin, ZHANG Jun, WANG Junyin, et al. Lightweight remote sensing object detection algorithm based on FNM-Net[J]. Modern electronics technique, 2025, 48(13): 1-10
[12] 周沁坤, 周华平, 孙克雷, 等. ARST-YOLOv7: 用于航空遥感图像的小目标检测网络[J]. 计算机工程与应用, 2025, 61(12): 232-242 ZHOU Qinkun, ZHOU Huaping, SUN Kelei, et al. ARST-YOLOv7: small target detection network for aerial remote sensing images[J]. Computer engineering and applications, 2025, 61(12): 232-242
[13] LI Wentong, CHEN Yijie, HU Kaixuan, et al. Oriented RepPoints for aerial object detection[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 1819-1828.
[14] 赵文清, 赵振寰, 巩佳潇. 结合倒残差自注意力机制的遥感图像目标检测[J]. 智能系统学报, 2025, 20(1): 64-72 ZHAO Wenqing, ZHAO Zhenhuan, GONG Jiaxiao. Remote sensing image object detection based on inverted residual self-attention mechanism[J]. CAAI transactions on intelligent systems, 2025, 20(1): 64-72
[15] 许思源, 吴伟林. 多尺度特征融合的遥感图像目标检测算法研究[J]. 计算机工程与应用, 2024, 60(23): 249-256 XU Siyuan, WU Weilin. Research on object detection algorithm for remote sensing images based on multi-scale fea-ture fusion[J]. Computer engineering and applications, 2024, 60(23): 249-256
[16] HOU Qibin, ZHOU Daquan, FENG Jiashi. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13708-13717.
[17] HOWARD A G, ZHU Menglong, CHEN Bo, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. (2017-04-17)[2025-01-01]. https://arxiv.org/abs/1704.04861.
[18] LEI Mengqi, WU Haochen, LYU Xinhua, et al. ConDSeg: a general medical image segmentation framework via contrast-driven feature enhancement[J]. Proceedings of the AAAI conference on artificial intelligence, 2025, 39(5): 4571-4579
[19] LAU K W, PO Laiman, REHMAN Y A U. Large separable kernel attention: rethinking the large kernel attention design in CNN[J]. Expert systems with applications, 2024, 236: 121352
[20] CHEN Jierun, KAO S H, HE Hao, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 12021-12031.
[21] GUO Menghao, LU Chengze, LIU Zhengning, et al. Visual attention network[J]. Computational visual media, 2023, 9(4): 733-752
[22] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149
[23] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Computer Vision–ECCV 2016. Cham: Springer, 2016: 21-37.
[24] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: fully convolutional one-stage object detection[C]//2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2020: 9626-9635.
[25] GE Zheng, LIU Songtao, WANG Feng, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. (2021-07-18)[2025-01-01]. https://arxiv.org/abs/2107.08430.
[26] LIU Shilong, LI Feng, ZHANG Hao, et al. DAB-DETR: dynamic anchor boxes are better queries for DETR[EB/OL]. (2022-01-28)[2025-01-01]. https://arxiv.org/abs/2201.12329.
[27] ZHANG Shilong, WANG Xinjiang, WANG Jiaqi, et al. Dense distinct query for end-to-end object detection[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 7329-7338.
[28] MIN Lingtong, DOU Feiyang, ZHANG Yani, et al. CM-YOLO: context modulated representation learning for ship detection[J]. IEEE transactions on geoscience and remote sensing, 2025, 63: 4202414
[29] ZHANG Yani, ER M J. Asymmetric aggregation network for accurate ship detection in optical imagery[J]. IEEE transactions on geoscience and remote sensing, 2024, 62: 4211914
[30] LIU Shanwei, BU Xi, XU Mingming, et al. SVSDet: a fine-grained recognition method for ship target using satellite video[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2024, 17: 4726-4742
[31] LYU Chengqi, ZHANG Wenwei, HUANG Haian, et al. RTMDet: an empirical study of designing real-time object detectors[EB/OL]. (2022-12-14)[2025-01-01]. https://arxiv.org/abs/2212.07784.
[32] ZHAO Yian, LYU Wenyu, XU Shangliang, et al. DETRs beat YOLOs on real-time object detection[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 16965-16974.
[33] XIAO Yao, XU Tingfa, XIN Yu, et al. FBRT-YOLO: faster and better for real-time aerial image detection[J]. Proceedings of the AAAI conference on artificial intelligence, 2025, 39(8): 8673-8681
- 相似文献/References:
-
[1]胡光龙,秦世引.动态成像条件下基于SURF和Mean shift的运动目标高精度检测[J].智能系统学报,2012,7(1):61.
HU Guanglong,QIN Shiyin.High precision detection of a mobile object under dynamic imaging based on SURF and Mean shift[J].CAAI Transactions on Intelligent Systems,2012,7():61.
[2]韩峥,刘华平,黄文炳,等.基于Kinect的机械臂目标抓取[J].智能系统学报,2013,8(2):149.[doi:10.3969/j.issn.1673-4785.201212038]
HAN Zheng,LIU Huaping,HUANG Wenbing,et al.Kinect-based object grasping by manipulator[J].CAAI Transactions on Intelligent Systems,2013,8():149.[doi:10.3969/j.issn.1673-4785.201212038]
[3]韩延彬,郭晓鹏,魏延文,等.RGB和HSI颜色空间的一种改进的阴影消除算法[J].智能系统学报,2015,10(5):769.[doi:10.11992/tis.201410010]
HAN Yanbin,GUO Xiaopeng,WEI Yanwen,et al.An improved shadow removal algorithm based on RGB and HSI color spaces[J].CAAI Transactions on Intelligent Systems,2015,10():769.[doi:10.11992/tis.201410010]
[4]曾宪华,易荣辉,何姗姗.流形排序的交互式图像分割[J].智能系统学报,2016,11(1):117.[doi:10.11992/tis.201505037]
ZENG Xianhua,YI Ronghui,HE Shanshan.Interactive image segmentation based on manifold ranking[J].CAAI Transactions on Intelligent Systems,2016,11():117.[doi:10.11992/tis.201505037]
[5]葛园园,许有疆,赵帅,等.自动驾驶场景下小且密集的交通标志检测[J].智能系统学报,2018,13(3):366.[doi:10.11992/tis.201706040]
GE Yuanyuan,XU Youjiang,ZHAO Shuai,et al.Detection of small and dense traffic signs in self-driving scenarios[J].CAAI Transactions on Intelligent Systems,2018,13():366.[doi:10.11992/tis.201706040]
[6]莫宏伟,汪海波.基于Faster R-CNN的人体行为检测研究[J].智能系统学报,2018,13(6):967.[doi:10.11992/tis.201801025]
MO Hongwei,WANG Haibo.Research on human behavior detection based on Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2018,13():967.[doi:10.11992/tis.201801025]
[7]宁欣,李卫军,田伟娟,等.一种自适应模板更新的判别式KCF跟踪方法[J].智能系统学报,2019,14(1):121.[doi:10.11992/tis.201806038]
NING Xin,LI Weijun,TIAN Weijuan,et al.Adaptive template update of discriminant KCF for visual tracking[J].CAAI Transactions on Intelligent Systems,2019,14():121.[doi:10.11992/tis.201806038]
[8]伍鹏瑛,张建明,彭建,等.多层卷积特征的真实场景下行人检测研究[J].智能系统学报,2019,14(2):306.[doi:10.11992/tis.201710019]
WU Pengying,ZHANG Jianming,PENG Jian,et al.Research on pedestrian detection based on multi-layer convolution feature in real scene[J].CAAI Transactions on Intelligent Systems,2019,14():306.[doi:10.11992/tis.201710019]
[9]刘召,张黎明,耿美晓,等.基于改进的Faster R-CNN高压线缆目标检测方法[J].智能系统学报,2019,14(4):627.[doi:10.11992/tis.201905026]
LIU Zhao,ZHANG Liming,GENG Meixiao,et al.Object detection of high-voltage cable based on improved Faster R-CNN[J].CAAI Transactions on Intelligent Systems,2019,14():627.[doi:10.11992/tis.201905026]
[10]单义,杨金福,武随烁,等.基于跳跃连接金字塔模型的小目标检测[J].智能系统学报,2019,14(6):1144.[doi:10.11992/tis.201905041]
SHAN Yi,YANG Jinfu,WU Suishuo,et al.Skip feature pyramid network with a global receptive field for small object detection[J].CAAI Transactions on Intelligent Systems,2019,14():1144.[doi:10.11992/tis.201905041]
备注/Memo
收稿日期:2025-7-4。
基金项目:国家自然科学基金项目(62371188).
作者简介:牛为华，副教授，博士，主要研究方向为数字图像处理、模式识别与计算机视觉。主持省部级教改项目6项，主持科研项目8项，参与科研项目40余项，发表学术论文20余篇。E-mail：niuwh@ncepu.edu.cn。;郭迅，硕士研究生，主要研究方向为深度学习与遥感图像处理。E-mail：guo_x0315@163.com。
通讯作者:牛为华. E-mail：niuwh@ncepu.edu.cn
更新日期/Last Update:
1900-01-01