改进YOLO框架的血细胞检测算法

doi:10.3778/j.issn.1002-8331.2110-0224

摘要/Abstract

摘要： 为解决传统目标检测算法在血细胞检测任务中出现的检测精度偏低、错检及漏检等问题，提出了一种基于YOLO框架的改进目标检测算法YOLO-Att，该算法在YOLO框架结构的基础上，在骨干网络中增加了一种多尺度残差增强模块，结合低层信息丰富网络的特征层次，进而提高特征信息利用率；并设计了一种注意力门控结构嵌入模型，以获取更多高质量的主要特征信息；同时使用Focal loss代替原损失函数中的交叉熵，提高正负样本权重，加快模型收敛速度；采用[K]-means++聚类算法对目标进行锚框优化，进一步提升检测准确率。相较于现有的Faster-RCNN、SSD以及YOLOv4等目标检测算法，YOLO-Att在通用血细胞数据集BCCD检测任务中，将mAP提高至66.32%，检测速率达到了85.4?ms，更符合血细胞检测任务的实时性。

关键词: 血细胞检测, YOLO, 多尺度残差块, 注意力机制

Abstract: In order to solve the problems of low accuracy, wrong detection and missing detection of traditional target detection algorithms in blood cell detection task, a target detection algorithm YOLO-Att based on improved YOLO framework is proposed. Based on the YOLO framework, a multi-scale residual enhancement module is added to the backbone network to improve the utilization rate of feature information by combining with the feature level of low-level information-rich network. An attentional gating structure embedding model is designed to obtain more high quality information of main features. At the same time, Focal loss is used to replace the cross entropy in the original loss function to improve the weight of positive and negative samples and accelerate the convergence rate of the model. Finally, [K]-means++ clustering algorithm is used to optimize the anchor frame of the target to further improve the detection accuracy. Compared with the existing target detection algorithms such as Faster-RCNN, SSD and YOLOv4, YOLO-Att increased mAP to 66.32% in the BCCD detection task of the universal blood cell data set, and the detection rate reaches 85.4 ms, which is more in line with the real-time detection task of blood cell.

Key words: blood cell test, YOLO, multiscale residuals block, attentional mechanism

王榆锋, 李大海. 改进YOLO框架的血细胞检测算法[J]. 计算机工程与应用, 2022, 58(12): 191-198.

WANG Yufeng, LI Dahai. Improved YOLO Framework Blood Cell Detection Algorithm[J]. Computer Engineering and Applications, 2022, 58(12): 191-198.

参考文献

[1] 陈岩.血常规检验中血涂片分析的价值研究[J].中国医药指南，2018，16（1）：118-119.
CHEN Y.Study on the value of blood smear analysis in routine blood examination[J].Guide of China Medicine，2018，16（1）：118-119.
[2] CHAN L Y，LAVERTY D J，SMITH T，et al.Accurate measurement of peripheral blood mononuclear cell concentration using image cytometry to eliminate RBC-induced counting error[J].Journal of Immunological Methods，2013，388（1/2）：25-32.
[3] LEHMANN T M，GOLD M O，THIES C，et al.Content-based image retrieval in medical applications[J].Methods of Information in Medicine，2004，43（4）：354-361.
[4] GIRSHICK R，DONAHUE J，DARREL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.Washington，DC：IEEE Computer Society，2014：580-587.
[5] 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，2017，39（6）：1137-1149.
[6] HE K，GKIOXARI G，DOLLAR P，et al.Mask R-CNN[C]//IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2018.
[7] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[8] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//IEEE Conference on Computer Vision & Pattern Recognition，2017：6517-6525.
[9] REDMON J，FARHADI A.YOLOv3：an incremental improvement[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition，2018.
[10] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision.Cham：Springer，2016：21-37.
[11] PEI D，JING M，LIU H.A fast RetinaNet fusion framework for multi-spectral pedestrian detection[J].Infrared Physics & Technology，2020，105：103178.
[12] 王玲.李厚博.王鹏.等.基于DeR-FCN模型的车辆检测算法[J].计算机工程与设计，2020，41（10）：2927-2933.
WANG L，LI H B，WANG P，et al.Vehicle detection algorithm using DeR-FCN model[J].Computer Engineering and Design，2020，41（10）：2927-2933.
[13] 刘树杰.基于卷积神经网络的红细胞检测和计数方法[D].广州：华南理工大学，2017.
LIU S J.Red blood cell detection and counting based on convolutional neural network[D].Guangzhou：South China University of Technology，2017.
[14] 蒋镕圻，彭月平，谢文宣，等.嵌入scSE模块的改进YOLOv4小目标检测算法[J].图学学报，2021，42（4）：546-555.
JIANG R Q，PENG Y P，XIE W X，et al.Improved YOLOV4 small target detection algorithm with embedded in scSE module[J].Journal of Graphics，2021，42（4）：546-555.
[15] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[16] WANG C Y，MARK LIAO H Y，WU Y H，et al.CSPNet：a new backbone that can enhance learning capability of cnn[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2020：390-391.
[17] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：8759-8768.
[18] 张冬冬，章鹏飞，王力生.一种基于YOLOv3和密度估计的细胞计数方法：CN201910620082.2[P].2019-07-10.
ZHANG D D，ZHANG P F，WANG L S.A cell counting method based on YOLOV3 and density estimation：CN201910620082.2[P].2019-07-10.
[19] 罗会兰，黎宵.基于上下文和浅层空间编解码网络的图像语义分割方法[J/OL].自动化学报：1-18.（2019-12-30）[2021-07-07].https：//doi.org/10.16383/j.aas.c190372.
LUO H L，LI X.Image semantic segmentation based on context and shallow space codec networks[J/OL].Acta Automatica Sinica：1-18.（2019-12-30）[2021-07-07].https：//doi.org/10.16383/j.aas.c190372.
[20] ZHAO H，SHI J，QI X，et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Honolulu，Hawaii，USA：IEEE，2017：2881-2890.
[21] CHEN L C，PAPANDREOU G，KOKKINOS I，et al.Deeplab：semantic image segmentation with deep convolutional nets，atrous convolution，and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40（4）：834-848.
[22] CHEN L C，PAPANDREOU G，SCHROFF F，et al.Rethinking atrous convolution for semantic image segmentation[J/OL].（2017-1-17）[2021-07-07].https：//arxiv.org/abs/1706.05587v1.
[23] MNIH V，HEESS N，GRAVES A，et al.Recurrent models of visual attention[C]//Advances in Neural Information Processing Systems，2014：2204-2212.
[24] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[25] JETLEY S，LORD N A，LEE N，et al.Learn to pay attention[C]//International Conference on Learning Reprsenttions，2018.
[26] LIN T Y，DOLLAR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2017.
[27] OKTAY O，SCHLEMPER J，FOLGOC L L，et al.Attention U-Net：learning where to look for the pancreas[C]//1st Conference on Medical Imaging with Deep Learning，Amsterdam，Netherlands，2018.
[28] SHEN T，ZHOU T，LONG G，et al.DiSAN：directional self-attention network for RNN/CNN-free language understanding[J].arXiv：1709.04696，2017.
[29] LUONG M T，PHAM H，MANNING C D.Effective approaches to attention-based neural machine translation[J].arXiv：1508.04025，2015.
[30] 吴天舒，张志佳，刘云鹏，等.结合YOLO检测和语义分割的驾驶员安全带检测[J].计算机辅助设计与图形学学报，2019，31（1）：126-131.
WU T S，ZHANG Z J，LIU Y P，et al.Driver seat belt detection based on YOLO detection and semantic segmentation[J].Journal of Computer-Aided Design and Graphics，2019，31（1）：126-131.
[31] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（2）：318-327.
[32] 罗小权，潘善亮.改进YOLOV3的火灾检测方法[J].计算机工程与应用，2020，56（17）：187-196.
LUO X Q，PAN S L.Improved YOLOV3 fire detection method[J].Computer Engineering and Applications，2020，56（17）：187-196.