基于CAFPN和细化双头解耦的遥感图像目标检测

doi:10.3969/j.issn.0255-8297.2023.06.007

摘要/Abstract

摘要： 针对遥感图像背景的复杂性和图中目标尺寸小、方向任意性导致漏检或错检的问题,提出了一种新颖的目标检测算法。首先,提出一种基于上下文信息增强的特征金字塔网络。在特征提取阶段,自适应融合不同感受野,获得具有丰富语义信息的特征,减少小目标的信息流失。然后,在回归网络中,使用中心点偏移回归机制实现旋转框的检测,降低冗余锚框带来的计算复杂度。最后,结合双头网络将分类和回归特征解耦,通过注意力机制和极化函数引导的特征细化模块构建适应各自任务的重要特征,使网络能准确地检测目标。在遥感数据集DOTA、HRSC2016和UCAS_AOD上验证网络的有效性,对比于Faster RCNN算法,该算法在3个数据集上获得了8.48%、7.60%和3.10%的精度提升,实现了高性能的遥感图像目标检测。

关键词: 遥感图像, 上下文信息增强, 注意力机制, 极化函数, 特征细化

Abstract: In order to address the challenges posed by complex backgrounds, small object sizes, and arbitrary directions in remote sensing images, this paper presents a novel object detection algorithm. The proposed algorithm consists of several key components.Firstly, a context augmentation feature pyramid network（CAFPN） is introduced. In the feature extraction stage, it integrates adaptively with the dilated convolution to obtain features with rich semantic information and reduce information loss of small objects. Then,midpoint-offset regression（MOR） is employed to detect oriented box in the regression network to reduce the computational complexity caused by redundant anchors. Finally, a double-head network decouples classification and regression features, and incorporates a feature refinement module guided by attention mechanism and polarization functions, enabling the construction of task-specific features that facilitate accurate object detection.Experimental results on public remote sensing datasets, including DOTA, HRSC2016, and UCAS＿AOD, demonstrate the effectiveness of the proposed algorithm. Compared to the Faster RCNN algorithm, the proposed method achieves accuracy improvements of 8.48%,7.60%, and 3.10% on the three datasets, respectively. The proposed method enables high-performance object detection in remote sensing images.

Key words: remote sensing image, context augmentation, attention mechanism, polarization function, feature refinement

中图分类号:

TP391.41

熊娟, 张孙杰, 阚亚亚, 陈家豪. 基于CAFPN和细化双头解耦的遥感图像目标检测[J]. 应用科学学报, 2023, 41(6): 989-1003.

XIONG Juan, ZHANG Sunjie, KAN Yaya, CHEN Jiahao. Remote Sensing Image Object Detection Based on CAFPN and Refinement Double-Head Decoupling[J]. Journal of Applied Sciences, 2023, 41(6): 989-1003.

参考文献

[1] 陈磊,张孙杰,王永雄.基于改进的YOLOv3及其在遥感图像中的检测[J].小型微型计算机系统,2020, 41(11):2321-2324.ChEn L, ZhAnG S J, WAnG Y X. Based on improved YOLOv3 and its detection in remote sensing images[J]. Journal of Chinese Computer Systems, 2020, 41(11):2321-2324.(in Chinese)
[2] REn S Q, HE K M, 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.
[3] HE K M, GkioxARi G, DoLLáR P, et al. Mask R-CNN[C]//2017 IEEE/CVF International Conference on Computer Vision(ICCV), 2017:2980-2988.
[4] REDMon J, DivvALA S, GiRshick R, et al. You only look once:unified, real-time object detection[C]//2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),2016:779-788.
[5] Liu W, AnGuELov D, ERhAn D, et al. SSD:single shot multibox detector[C]//European Conference on Computer Vision. Cham:Springer, 2016:21-37.
[6] MA J Q, ShAo W Y, YE H, et al. Arbitrary-oriented scene text detection via rotation proposals[J]. IEEE Transactions on Multimedia, 2018, 20(11):3111-3122.
[7] 汪鹏,郑文凤,史进,等.基于MFANet和上下文特征融合的遥感影像目标检测[J].应用科学学报,2022, 40(1):131-144.WAnG P, ZhEnG W F, Shi J, et al. Remote sensing image object detection based on MFANet and contextual features fusion[J]. Journal of Applied Sciences, 2022, 40(1):131-144(in Chinese)
[8] DinG J, XuE N, LonG Y, et al. Learning RoI transformer for oriented object detection in aerial images[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2020:2844-2853.
[9] Xu Y C, Fu M T, WAnG Q M, et al. Gliding vertex on the horizontal bounding box for multioriented object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2021, 43(4):1452-1459.
[10] Lin T Y, DoLLáR P, GiRshick R, et al. Feature pyramid networks for object detection[C]//2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2017:936-944.
[11] 朱节中,陈永,柯福阳,等.基于Siam-UNet++的高分辨率遥感影像建筑物变化检测[J].计算机应用研究, 2021, 38(11):3460-3465.Zhu J Z, ChEn Y, KE F Y, et al. Building change detection from high resolution remote sensing imagery based on Siam-UNet++[J]. Application Research of Computers, 2021, 38(11):3460-3465.(in Chinese)
[12] LiAo M H, Zhu Z, Shi B G, et al. Rotation-sensitive regression for oriented scene text detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2018:5909-5918.
[13] SonG G L, Liu Y, WAnG X G. Revisiting the sibling head in object detector[C]//2020IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2020:11560-11569.
[14] Wu Y, ChEn Y P, YuAn L, et al. Rethinking classification and localization for object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2020:10183-10192.
[15] Qin R, Liu Q J, GAo G S, et al. MRDet:a multihead network for accurate rotated object detection in aerial images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-12.
[16] Guo C X, FAn B, ZhAnG Q, et al. AugFPN:improving multi-scale feature learning for object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2020:12592-12601.
[17] XiE X X, ChEnG G, WAnG J B, et al. Oriented R-CNN for object detection[C]//2021IEEE/CVF International Conference on Computer Vision(ICCV), 2022:3500-3509.
[18] MinG Q, MiAo L J, Zhou Z Q, et al. CFC-net:a critical feature capturing network for arbitrary-oriented object detection in remote-sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-14.
[19] XiA G S, BAi X, DinG J, et al. DOTA:a large-scale dataset for object detection in aerial images[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2018:3974-3983.
[20] Liu Z K, WAnG H Z, WEnG L B, et al. Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(8):1074-1078.
[21] Zhu H G, ChEn X G, DAi W Q, et al. Orientation robust object detection in aerial images using deep convolutional neural network[C]//2015 IEEE International Conference on Image Processing(ICIP), 2015:3735-3739.
[22] MinG Q, Zhou Z Q, MiAo L J, et al. Dynamic anchor learning for arbitrary-oriented object detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(3):2355-2363.
[23] HAn J M, DinG J, Li J, et al. Align deep features for oriented object detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-11.