Object Detection Based on Dual Attention Mechanism Combined with Discriminant Correlation Analysis

doi:10.3778/j.issn.1002-8331.2109-0452

Abstract

Abstract: For the problems of low target recognition rate and missing detection of some small targets in the model of two-stage target detection algorithm, a target detection algorithm with dual attention mechanism based on discriminant correlation analysis is proposed in this paper. In order to maximize correlation between the corresponding features in two feature sets and differences between different types of features, the Faster R-CNN backbone network is improved and discriminant correlation analysis technology is introduced. It can ensure the interaction of information and effectively alleviate the problem of insufficient feature extraction ability in the conventional feature fusion method. At the same time, a residual dual attention mechanism combined with the residual structure is constructed, which aims to extract the deep-level feature so as to compensate for the weakening of high-resolution information after deep CNN. Meantime, the mixed convolutional layer is adopted to expand receptive field while reducing information loss to maximize the feature extraction performance of network. PASCAL VOC2007, KITTI and Portrait are adopted to train the network, and the proposed algorithm model is compared with multiple classic target detection algorithms. Experimental results demonstrate that the proposed algorithm has high detection accuracy.

Key words: discriminant correlation analysis, residual dual attention mechanism, mixed convolution layer, object detection

摘要： 针对两阶段目标检测算法中模型存在目标识别率低、部分小目标物漏检等问题，提出了一种基于判别相关分析的双注意力机制的目标检测算法。该算法通过改进Faster R-CNN主干网络，引入判别相关分析技术最大化两个特征集中对应特征的相关关系，同时最大化不同类之间的差异，来保证信息间的交互，有效缓解常规特征融合方式存在的特征提取能力不足问题。同时，结合残差结构构建残差双注意力机制，进行深层次的特征提取，来弥补深度CNN后高分辨率信息弱化问题，采用混合卷积层的设计在扩大感受野的同时又减少了信息损失，最大限度地保证了网络的特征提取性能。采用PASCAL VOC2007、KITTI以及Portrait三类数据集对网络进行训练，并将提出的算法模型与多个经典目标检测算法进行对比。实验结果表明，提出的算法具有较高的检测精度。

关键词: 判别相关分析, 残差双注意力机制, 混合卷积层, 目标检测

ZHAO Shan, ZHENG Ailing. Object Detection Based on Dual Attention Mechanism Combined with Discriminant Correlation Analysis[J]. Computer Engineering and Applications, 2022, 58(17): 120-129.

赵珊, 郑爱玲. 判别相关分析双注意力机制的目标检测算法[J]. 计算机工程与应用, 2022, 58(17): 120-129.

References

[1] REN S，HE K，GIRSHICK R，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2015：580-587.
[2] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2015.
[3] LIU W，DRAGOMIR ANGUELOV D E，SZEGEDY C，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision，2015：21-37.
[4] SHEN Y，LI H，YI S，et al.Person re-identification with deep similarity-guided graph neural network[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：486-504.
[5] HE Y Q，XIA G H，LUO Y K，et al.DVFENet：dual-branch voxel feature extraction network for 3D object detection[J].Neurocomputing，2021，459：201-211.
[6] 熊伟华，吴华.集成蒸馏策略和反卷积的微小目标检测片上实现方法：CN111179212A[P].2020-05-19.
XIONG W H，WU H.On-chip implementation of small target detection integrated distillation strategy and deconvolution：CN111179212A[P].2020-05-19.
[7] ZHAO H，SHI J，QI X，et al.Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017.
[8] 陈灏然，彭力.感受野下的小目标检测算法[J].计算机科学与探索，2021，15（2）：346-353.
CHEN H R，PENG L.Detection algorithm of small target in receptive field block[J].Journal of Frontiers of Computer Science and Technology，2021，15（2）：346-353.
[9] FELZENSZWALB P F，GIRSHICK R B，MCALLESTER D，et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2010，32（9）：1627-1645.
[10] 孙权森，曾生根，杨茂龙，等.基于典型相关分析的组合特征抽取及脸像鉴别[J].计算机研究与发展，2005，42（4）：614-621.
SUN Q S，ZENG S G，YANG M L，et al.Combined feature extraction based on canonical correlation analysis and face recognition[J].Journal of Computer Research and Development，2005，42（4）：614-621.
[11] HAGHIGHAT M，ABDEL-MOTTALEB M，ALHALABI W.Discriminant correlation analysis：real-time feature level fusion for multimodal biometric recognition[J]. IEEE Transactions on Information Forensics and Security，2016，11（9）：1984-1996.
[12] SHU X，YUAN P，JIANG H，et al.Multi-view uncorrelated discriminant analysis via dependence maximization[J].Applied Intelligence，2019，49（2）：650-660.
[13] WANG Z，WANG L，HUANG H.Sparse additive discriminant canonical correlation analysis for multiple features fusion[J].Neurocomputing，2021，463：185-197.
[14] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[15] LI X，WANG W，HU X，et al.Selective kernel networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2019：510-519.
[16] WANG Q，WU B，ZHU P，et al.ECA-net：efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：11534-11542.
[17] 梁延禹，李金宝.多尺度非局部注意力网络的小目标检测算法[J].计算机科学与探索，2020，14（10）：1744-1753.
LIANG Y Y，LI J B.Small objects detection method based on multi-scale non-local attention network[J].Journal of Frontiers of Computer Science and Technology，2020，14（10）：1744-1753.
[18] 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，2016，39（6）：1137-1149.
[19] WOO S，PARK J，LEE J Y，et al.Cbam：convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：3-19.
[20] GIRSHICK R.Fast R-CNN[C]//International Conference on Computer Vision，2015.
[21] 吴天舒，张志佳，刘云鹏，等.基于改进SSD的轻量化小目标检测算法[J].红外与激光工程，2018，47（7）：37-43.
WU T S，ZHANG Z J，LIU Y P，et al.A lightweight small object detection algorithm based on improved SSD[J].Infrared and Laser Engineering，2018，47（7）：37-43.
[22] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[23] 鞠默然，罗江宁，王仲博，等.融合注意力机制的多尺度目标检测算法[J].光学学报，2020，40（13）：126-134.
JU M R，LUO J N，WANG Z B，et al.Multi-scale target detection algorithm based on attention mechanism[J].Acta Optica Sinica，2020，40（13）：126-134.