[1]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.[doi:10.11992/tis.202312001]
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.[doi:10.11992/tis.202312001]
点击复制
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.[doi:10.11992/tis.202312001]
结合倒残差自注意力机制的遥感图像目标检测
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第1期
页码:
64-72
栏目:
学术论文—机器学习
出版日期:
2025-01-05
- Title:
- Remote sensing image object detection based on inverted residual self-attention mechanism
- Keywords:
- remote sensing image; object detection; inverted residual; self-attention mechanism; multi-scale; spatial pyramid; feature extraction; feature fusion
- 分类号:
- TP391
- 摘要:
- 针对遥感图像目标检测存在背景信息干扰严重、待检测目标尺寸差异大等问题，提出一种结合倒残差自注意力机制的目标检测方法。首先，使用具有强特征提取能力的倒残差自注意力机制骨干网络充分提取目标特征，降低复杂背景信息的干扰；其次，构造多尺度空间金字塔池化模块，提供多尺度感受野，增强捕捉不同尺寸目标的能力；最后，提出轻量级特征融合模块，对骨干网络提取的特征图进行融合，充分结合低层与高层特征，提高网络对不同尺寸目标的检测能力。与传统网络及其他改进目标检测算法进行对比，实验发现该方法的检测精度明显优于其他算法。此外，在DIOR数据集和RSOD数据集上设计消融实验，结果表明，该方法在DIOR数据集与RSOD数据集上的平均精度均值比YOLOv8算法分别提升4.6和4.2百分点，明显提升遥感图像目标检测的精度。
- Abstract:
- An inverted residual self-attention method (IRSAM) was proposed in this study as an approach for object detection in remote sensing images. The method was designed to address challenges related to significant variations in object sizes and substantial interference from background information in remote sensing image object detection. Firstly, an inverted residual self-attention mechanism backbone network with strong feature extraction ability was utilized to fully extract the object features, thus reducing the interference of complex background information on the object. Additionally, a multi-scale spatial pyramid pooling module was constructed to offer diverse sensory fields at multiple scales and improve the capacity to detect objects of varying sizes. Finally, a lightweight feature fusion structure was employed to integrate the feature maps extracted from the backbone network, effectively combining low-level and high-level features. The study compared the performance of IRSAM with both traditional network and enhanced object detection algorithms. The results indicated that the proposed method exhibited significantly higher detection accuracy. In addition, ablation experiments were designed on the DIOR and the RSOD datasets. The results show that the mean accuracy is 4.6 and 4.2 percentage points higher than the YOLOv8 algorithm on the DIOR dataset and the RSOD dataset, respectively. Consequently, the proposed method significantly enhances the accuracy of object detection in remote sensing images.
- 参考文献/References:
-
[1] 石争浩, 仵晨伟, 李成建, 等. 航空遥感图像深度学习目标检测技术研究进展[J]. 中国图象图形学报, 2023, 28(9): 2616-2643.
SHI Zhenghao, WU Chenwei, LI Chengjian, et al. Research progress on deep learning object detection technology for aerial remote sensing images[J]. Journal of image and graphics, 2023, 28(9): 2616-2643.
[2] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.
[3] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1440-1448.
[4] 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.
[5] LU Dongchen, LI Dongmei, LI Yali, et al. OSKDet: orientation-sensitive keypoint localization for rotated object detection[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 1172-1182.
[6] XIA Guisong, BAI Xiang, DING Jian, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3974-3983.
[7] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2016: 21-37.
[8] 唐嘉潞, 杨钟亮, 张凇, 等. 结合显微视觉和注意力机制的毛羽检测方法[J]. 智能系统学报, 2022, 17(6): 1209-1219.
TANG Jialu, YANG Zhongliang, ZHANG Song, et al. Detection of yarn hairiness combining microscopic vision and attention mechanism[J]. CAAI transactions on intelligent systems, 2022, 17(6): 1209-1219.
[9] GUO Chaoxu, FAN Bin, ZHANG Qian, et al. AugFPN: improving multi-scale feature learning for object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 12592-12601.
[10] 吴珺, 董佳明, 刘欣, 等. 注意力优化的轻量目标检测网络及应用[J]. 智能系统学报, 2023, 18(3): 506-516.
WU Jun, DONG Jiaming, LIU Xin, et al. Attention-optimized lightweight object detection network and its application[J]. CAAI transactions on intelligent systems, 2023, 18(3): 506-516.
[11] 胡硕, 王洁, 孙妍, 等. 无人机视角下的多车辆跟踪算法研究[J]. 智能系统学报, 2022, 17(4): 798-805.
HU Shuo, WANG Jie, SUN Yan, et al. Research on multi-vehicle tracking algorithm from the perspective of UAV[J]. CAAI transactions on intelligent systems, 2022, 17(4): 798-805.
[12] FARHADI A, REDMON J. YOLOv3: an incremental improvement[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 1804-2767.
[13] 曾文健, 朱艳, 沈韬, 等. 面向非对称特征注意力和特征融合的太赫兹图像检测[J]. 中国图象图形学报, 2022, 27(8): 2496-2505.
ZENG Wenjian, ZHU Yan, SHEN Tao, et al. Terahertz image detection combining asymmetric feature attention and feature fusion[J]. Journal of image and graphics, 2022, 27(8): 2496-2505.
[14] BOCHKOVSKIY A, WANG C. Y, LIAO H. M, et al. YOLOv4: optimal speed and accuracy of object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle: IEEE, 2020: 2-7.
[15] 张正, 马渝博, 柳长安, 等. 面向遥感图像旋转目标检测的双向衰减损失方法研究[J]. 电子与信息学报, 2023, 45(10): 3578-3586.
ZHANG Zheng, MA Yubo, LIU Chang’an, et al. Research on bidirectional attenuation loss method for rotating object detection in remote sensing image[J]. Journal of electronics & information technology, 2023, 45(10): 3578-3586.
[16] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2999-3007.
[17] 曲海成, 王蒙, 柴蕊. 双向多尺度特征融合的高效遥感图像车辆检测[J]. 计算机工程与应用, 2024, 60(12): 346-356.
QU Haicheng, WANG Meng, CHAI Rui. Efficient remote sensing image vehicle detection with bidirectional multi-scale feature fusion [J]. Computer engineering and applications, 2024, 60(12): 346-356.
[18] SANDLER M, HOWARD A, ZHU Menglong, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510-4520.
[19] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[20] MEHTA S, RASTEGARI M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer[EB/OL]. (2021-10-05)[2023-11-26]. https://arxiv.org/abs/2110.02178.
[21] ZHANG Jiangning, LI Xiangtai, LI Jian, et al. Rethinking mobile block for efficient attention-based models[C]//2023 IEEE/CVF International Conference on Computer Vision. Paris: IEEE, 2023: 1389-1400.
[22] 郑哲, 雷琳, 孙浩, 等. FAGNet: 基于MAFPN和GVR的遥感图像多尺度目标检测算法[J]. 计算机辅助设计与图形学学报, 2021, 33(6): 883-894.
ZHENG Zhe, LEI Lin, SUN Hao, et al. FAGNet: A multi-scale object detection algorithm for remote sensing images based on MAFPN and GVR[J]. Journal of computer-aided design and computer graphics, 2021, 33(6): 883-894.
[23] 赵文清, 康怿瑾, 赵振兵, 等. 改进YOLOv5s的遥感图像目标检测[J]. 智能系统学报, 2023, 18(1): 86-95.
ZHAO Wenqing, KANG Yijin, ZHAO Zhenbing, et al. Remote sensing image object detection based on improved YOLOv5s[J]. CAAI transactions on intelligent systems, 2023, 18(1): 86-95.
[24] ZHAO Wenqing, KANG Yixin, CHEN Hao, et al. Adaptively attentional feature fusion oriented to multiscale object detection in remote sensing images[J]. IEEE transactions on instrumentation and measurement, 2023, 72: 1-11.
[25] YUE Chenke, YAN Junhua, ZHANG Yin, et al. SCFNet: Semantic correction and focus network for remote sensing image object detection[J]. Expert systems with applications, 2023, 224: 119980.
[26] LI Wentong, CHEN Yijie, HU Kaixuan, et al. Oriented reppoints for aerial object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 1829-1838.
[27] REN Shougang, FANG Zhiruo, GU Xingjian. A cross stage partial network with strengthen matching detector for remote sensing object detection[J]. Remote sensing, 2023, 15(6): 1574.
[28] CHEN Yixia, LIN Mingwei, HE Zhu, et al. Consistency-and dependence-guided knowledge distillation for object detection in remote sensing images[J]. Expert systems with applications, 2023, 229: 120519.
[29] NASCIMENTO M G, FAWCETT R, PRISACARIU V A Dsconv: efficient convolution operator[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 5148-5157.
- 相似文献/References:
-
[1]刘富,于鹏,刘坤.采用独立分量分析Zernike矩的遥感图像飞机目标识别[J].智能系统学报,2011,6(1):51.
LIU Fu,YU Peng,LIU Kun.Research concerning aircraft recognition of remote sensing images based on ICA Zernike invariant moments[J].CAAI Transactions on Intelligent Systems,2011,6():51.
[2]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.
[3]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]
[4]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]
[5]龙海侠,吴淑雷,吕雁.基于多样性变异的QPSO算法的遥感图像分类[J].智能系统学报,2015,10(6):938.[doi:10.11992/tis.201507045]
LONG Haixia,WU Shulei,LYU Yan.Classification of multispectral remote sensing image based on QPSO and diversity-mutation[J].CAAI Transactions on Intelligent Systems,2015,10():938.[doi:10.11992/tis.201507045]
[6]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]
[7]吴诗婳,吴一全,周建江.直线截距直方图城区遥感图像多阈值分割[J].智能系统学报,2018,13(2):227.[doi:10.11992/tis.201609012]
WU Shihua,WU Yiquan,ZHOU Jianjiang.Multi-level thresholding for remote sensing image of urban area based on line intercept histogram[J].CAAI Transactions on Intelligent Systems,2018,13():227.[doi:10.11992/tis.201609012]
[8]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]
[9]李亚飞,董红斌.基于卷积神经网络的遥感图像分类研究[J].智能系统学报,2018,13(4):550.[doi:10.11992/tis.201706078]
LI Yafei,DONG Hongbin.Classification of remote-sensing image based on convolutional neural network[J].CAAI Transactions on Intelligent Systems,2018,13():550.[doi:10.11992/tis.201706078]
[10]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]
[11]赵文清,康怿瑾,赵振兵,等.改进YOLOv5s的遥感图像目标检测[J].智能系统学报,2023,18(1):86.[doi:10.11992/tis.202203013]
ZHAO Wenqing,KANG Yijin,ZHAO Zhenbing,et al.A remote sensing image object detection algorithm with improved YOLOv5s[J].CAAI Transactions on Intelligent Systems,2023,18():86.[doi:10.11992/tis.202203013]
[12]梁礼明,冯耀,龙鹏威,等.基于MobileViT和多尺度特征聚合的遥感图像目标检测[J].智能系统学报,2024,19(5):1168.[doi:10.11992/tis.202310022]
LIANG Liming,FENG Yao,LONG Pengwei,et al.Remote sensing image object detection based on MobileViT and multiscale feature aggregation[J].CAAI Transactions on Intelligent Systems,2024,19():1168.[doi:10.11992/tis.202310022]
备注/Memo
收稿日期:2023-12-1。
基金项目:国家自然科学基金项目(62371188)；河北省自然科学基金项目(F2021502013)；中央高校基本科研业务费面上项目(2020MS153，2021PT018).
作者简介:赵文清，教授，博士，主要研究方向为人工智能与图像处理。获河北省科技进步二等奖、三等奖各1项。发表学术论文50余篇。E-mail：zhaowenqing@ncepu.edu.cn。;赵振寰，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：zhenhuan_zhao@ncepu.edu.cn。;巩佳潇，硕士研究生，主要研究方向为人工智能与图像处理。E-mail：jiaxiao_gong@ncepu.edu.cn。
通讯作者:赵文清. E-mail：zhaowenqing@ncepu.edu.cn
更新日期/Last Update:
2025-01-05