融合改进FPN与关联网络的Faster R-CNN目标检测

doi:10.19678/j.issn.1000-3428.0059979

摘要/Abstract

摘要： 在无人机场景下，目标检测存在样本数量不足、成像视角不同的问题，导致检测精度低。提出一种结合改进特征金字塔网络（FPN）与关联网络的Faster R-CNN目标检测算法。通过在传统FPN结构中以自下而上的特征融合方式提取特征图的语义信息和位置信息，最大程度地保留特征图的多尺度信息。同时利用候选区域之间的形状特征和位置特征构造区域之间的关联特征，并与深度特征相融合进行分类回归，从而充分提取特征图的整体信息，实现目标检测。在PASCAL VOC 2007和NWPU VHR-10数据集上的实验结果表明，相比FPN+Faster R-CNN算法，该算法的交并比和平均检测精度分别提高了10和2.7个百分点，具有较优的目标检测性能。

关键词: 目标检测, 尺度, 特征金字塔网络, 关联网络, 特征融合

Abstract: The existing target detection usually suffers from insufficient sample number and different image angles, resulting in low detection accuracy. This paper proposes a target detection algorithm using Faster R-CNN by combining improved Feature Pyramid Network(FPN) structure with a relation network.Base on the traditional FPN structure, the bottom-up feature fusion process is added to extract rich semantic information and location information of the feature map of targets.Then the location information and shape features between candidate regions are used to construct relation features, which are subsequently fused with deep features, so fully extract the overall information of the feature map and realize target detection.The experimental results on PASCAL VOC 2007 and NWPU VHR-10 datasets show that compared with the FPN+Faster R-CNN algorithm, the proposed algorithm increases the Intersection over Union (IoU) by about 10 percentage points and detection accuracy by about 2.7 percentage points, displaying excellent performance in target detection.

Key words: object detection, scale, Feature Pyramid Network(FPN), relation network, feature fusion

中图分类号:

TP391

汪常建, 丁勇, 卢盼成. 融合改进FPN与关联网络的Faster R-CNN目标检测[J]. 计算机工程, 2022, 48(2): 173-179.

WANG Changjian, DING Yong, LU Pancheng. Object Detection Using Faster R-CNN Combining Improved FPN and Relation Network[J]. Computer Engineering, 2022, 48(2): 173-179.

http://www.ecice06.com/CN/Y2022/V48/I2/173

图/表 12

20220301123917

20220301123921

20220301123925

20220301123932

20220301123935

20220301123939

20220301123943

20220301123947

20220301123951

20220301123956

20220301124000

20220301124003

参考文献

[1] KANELLAKIS C, NIKOLAKOPOULOS G.Survey on computer vision for UAVs[J].Journal of Intelligent and Robotic Systems, 2017, 87:141-168.
[2] VINCENZI D A, TERWILLIGER B A, ISON D C.Unmanned Aerial System(UAS) human-machine interfaces:new paradigms in command and control[J].Procedia Manufacturing, 2015, 3:920-927.
[3] ZHANG K, ZHANG Z, LI Z, et al.Joint face detection and alignment using multitask cascaded convolutional networks[J].IEEE Signal Processing Letters, 2016, 23(10):1499-1503.
[4] RAGHUNANDAN A, MOHANA M, RAGHAV P, et al.Object detection algorithms for video surveillance applications[C]//Proceedings of International Conference on Communication and Signal Processing.Washington D.C., USA:IEEE Press, 2018:563-568.
[5] VADDI S, KUMAR C, JANNESARI A.Efficient object detection model for real-time UAV applications[EB/OL].[2020-10-10].https://arxiv.org/abs/1906.00786.
[6] GIRSHICK R, DONAHUE J, DARRELL T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2014:580-587.
[7] GIRSHICK R.Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2015:1440-1448.
[8] REN S, HE K, 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, 2015, 39(6):1137-1149.
[9] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once:unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:779-788.
[10] REDMON J, FARHADI A.YOLO9000:better, faster, stronger[C]//Proceedings of IEEE Conference on Computer Vision & Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:6517-6525.
[11] REDMON J, FARHADI A.YOLOv3:an incremental improvement[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recongnition.Washington D.C., USA:IEEE Press, 2018:1-6.
[12] LIU W, ANGUELOV D, ERHAN D, et al.SSD:single shot multibox detector[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:21-37.
[13] LIN T, DOLLAR P, GIRSHICK R, et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:936-944.
[14] 邹逸群, 肖志红, 赖普坚, 等.Anchor-free的尺度自适应行人检测算法[J].控制与决策, 2021, 36(2):295-302. ZHOU Y Q, XIAO Z H, LAI P J, et al.Anchor-free scale adaptive pedestrian detection algorithm[J].Control and Decision, 2021, 36(2):295-302.(in Chinese)
[15] DIVVALA S K, HOIEM D, HAYS J H, et al.An empirical study of context in object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2009:1-2.
[16] TU Z.Auto-context and its application to high-level vision tasks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2008:1-2.
[17] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.New York, USA:ACM Press, 2017:6000-6010.
[18] CAO J X, CHEN Q, GUO J, et al.Attention-guided context feature pyramid network for object detection[EB/OL].[2020-10-09].http://arxiv.org/abs/2005.11475v1.
[19] HU H, GU J, ZHANG Z, et al.Relation networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:3588-3597.
[20] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2020-10-10].https://arxiv.org/pdf/1409.1556.pdf.
[21] HE K, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:770-778.

选择文件类型/文献管理软件名称

选择包含的内容