基于改进YOLO v7的血细胞识别计数研究
Research on Blood Cell Recognitionand Counting Based on ImprovedYOLO v7
DOI: 10.12677/AAM.2023.123110, PDF,  被引量    科研立项经费支持
作者: 钟 天：成都信息工程大学，应用数学学院，四川 成都
关键词: 血细胞；目标检测；YOLO v7；Blood Cells； Target Detection； YOLO v7
摘要: 血细胞计数具有重要医学意义。而由于传统计数方法存在一定局限性，本文引入改进YOLO v7，对血细胞可实行快速且准确的识别计数。改进点为以下三方面：1) 更改SPPCSPC中Maxpool的尺寸。2) 将第24、37层的卷积层替换为CA注意力。3) 设计了一种上采样整体结构。改进YOLO v7在mAP方面优于原版YOLO v7，为工程应用带来一定研究意义。
Abstract: Blood cell count has important medical significance. However, due to the limitations of traditional counting methods, this paper introduces the improved YOLO v7, which can quickly and accurately identify and count blood cells. The improvement points are as follows: 1) Change the size of Maxpool in SPPCSPC. 2) Replace the convolution layer of layers 24 and 37 with CA attention. 3) An upsam-pling architecture is designed. The improved YOLO v7 is better than the original YOLO v7 in terms of mAP, which brings certain research significance for engineering application.
文章引用：钟天. 基于改进YOLO v7的血细胞识别计数研究[J]. 应用数学进展, 2023, 12(3): 1083-1089. https://doi.org/10.12677/AAM.2023.123110

参考文献

[1] 徐晓涛, 孙亚东, 章军. 基于YOLO框架的血细胞自动计数研究[J]. 计算机工程与应用, 2020, 56(14): 98-103.
[2] 易见兵, 黄苏泉, 曹锋, 李俊. 基于改进的YOLOX血细胞检测算法研究[J]. 电子测量技术, 2022, 45(22): 177-184.
[3] 李晓宁, 许克东, 张晶, 邢斌瑜, 申存毅, 王欢. 血清铁蛋白和血小板相关参数与高脂血症性急性胰腺炎患者病情及预后的关系分析[J]. 中国医刊, 2023, 58(2): 160-163.
[4] LeCun, Y., Bottou, L., Bengio, Y. and Haner, P. (1998) Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86, 2278-2324. [Google Scholar] [CrossRef] 
[5] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90.
[6] Simonyan, K. and Zisserman, A. (2015) Very Deep Convolutional Networks for Large-Scale Image Recog-nition. 3rd International Conference on Learning Representations (ICLR 2015), San Diego, 7-9 May 2015, 1-14.
[7] Szegedy, C., Liu, W., Jia, Y.Q., et al. (2015) Going Deeper with Convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 1-9. [Google Scholar] [CrossRef] 
[8] He, K.M., Zhang, X.Y., Ren, S.Q. and Sun, J. (2016) Deep Re-sidual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778.
[9] Girshick, R., Donahue, J., Darrell, T., et al. (2014) Rich Feature Hierar-chies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 580-587. [Google Scholar] [CrossRef] 
[10] Ren, S.Q., He, K.M., Girshick, R. and Sun, J. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Net-works. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149.
[11] Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Com-puter Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[12] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Im-provement. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-22 June 2018, 2311-2314.
[13] Lin, T.-Y., Dollár, P. and Girshick, R. (2016) Feature Pyramid Networks for Object Detec-tion.
[14] Joseph Redmon.
https://pjreddie.com/darknet/yolo
[15] He, K.M., Zhang, X.Y., Ren, S.Q. and Sun, J. (2014) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. ECCV, 13th European Con-ference, Zurich, 6-12 September 2014, 346-361.
[16] Wang, C.-Y., Liao, H.-Y.M., Yeh, I.-H., et al. (2019) CSPNET: A New Backbone That Canenhance Learning Capability of CNN.
[17] Wang, C.-Y., Bochkovskiy, A. and Liao, H.-Y. (2022) YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors.
[18] Lee, Y., Hwang, J.-W., Lee, S. and Bae, Y. (2019) An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, 16-17 June 2019, 752-760.
[19] Huang, G., Liu, Z. and van der Maaten, L. (2017) Densely Connected Convolu-tional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 2261-2269. [Google Scholar] [CrossRef] 
[20] Zhu, L.G., Deng, R.Z., Maire, M., et al. (2018) Sparsely Aggregated Convolutional Networks. ECCV, 15th European Conference, Munich, 8-14 September 2018, 192-208. [Google Scholar] [CrossRef] 
[21] Ding, X.H., Zhang, X.Y., Ma, N.N., et al. (2021) RepVGG: Making VGG-style ConvNets Great Again. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 13728-13737. [Google Scholar] [CrossRef] 
[22] Ge, Z., Liu, S.T., Wang, F., et al. (2021) YOLOX: Exceed-ing YOLO Series in 2021.
[23] Li, C.Y., Li, L.L., Jiang, H.L., et al. (2022) YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications.
[24] Hou, Q.B., Zhou, D.Q. and Feng, J.S. (2021) Coordinate Attention for Ef-ficient Mobile Network Design. 2021 IEEE/ CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 13708-13717. [Google Scholar] [CrossRef] 
[25] Woo, S.H., Park, J., Lee, J.-Y. and Kweon, I.S. (2018) CBAM: Convolutional Block Attention Module. ECCV, 15th European Conference, Munich, 8-14 September 2018, 3-19.
[26] Wang, J.Q., Chen, K., Xu, R., et al. (2019) CARAFE: Content-Aware Reassembly of Features. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 3007-3016. [Google Scholar] [CrossRef] 
[27] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al. (2020) Gen-erative Adversarial Networks. Communications of the ACM, 63, 139-144.

为你推荐