基于边缘计算的图像语义分割应用与研究

doi:10.11896/jsjkx.200900046

摘要/Abstract

摘要： 随着深度学习在医学影像分割、药品检测等医学领域的广泛应用,语义分割技术承载了举足轻重的地位。语义分割融合了目标检测和图像识别两大技术,旨在将图像分割成多组具有特定语义的区域,属于像素级别的密集分类问题。然而为了推动移动视觉识别技术的有效发展,传统深度学习模型在功耗、内存管理、实时性等方面都无法满足移动设备的要求。边缘计算是一种有效将计算、网络、存储、带宽等能力从主机端延伸到移动边缘端的新型架构模式,从而实现在有限计算资源环境下的模型推理运行。因此,文中尝试在基于边缘TPU协处理器的开发板上完成FCN,SegNet,U-Net等经典图像语义分割模型的转换、部署及推理运行,并在采集的真实药品数据集上验证提出的语义分割模型的正确性及性能。

关键词: 边缘TPU, 边缘计算, 深度学习, 语义分割

Abstract: With the extensive application of deep learning in medical imaging segmentation,drug detection and other medical fields,semantic segmentation technology plays a pivotal role.Semantic segmentation combines two techniques of target detection and image recognition.It aims to segment the image into multiple groups of regions with specific semantics,which is a dense classification problem at the pixel level.However,in order to promote the effective development of mobile visual recognition technology,the traditional deep learning model cannot meet the requirements of mobile devices in terms of power consumption,memory management,and real-time performance.Edge computing is a new architecture mode that effectively extends the computing,network,storage,and bandwidth capabilities from the host to the mobile edge to implement model inference operations in a limited computing resource environment.Therefore,this paper attempts to complete the transformation,deployment and inference operation of the classic image semantic segmentation model,such as FCN,SegNet,U-Net,etc,on the development board based on the edge TPU coprocessor,and verifies the correctness and performanceof the proposed semantic segmentation model on the collec-ted real drug dataset.

Key words: Deep learning, Edge Computing, Edge TPU, Semantic Segmentation

中图分类号:

TP181

王赛男, 郑雄风. 基于边缘计算的图像语义分割应用与研究[J]. 计算机科学, 2020, 47(11A): 276-280. https://doi.org/10.11896/jsjkx.200900046

WANG Sai-nan, ZHENG Xiong-feng. Application and Research of Image Semantic Segmentation Based on Edge Computing[J]. Computer Science, 2020, 47(11A): 276-280. https://doi.org/10.11896/jsjkx.200900046

参考文献

[1] GARCIA-GARCIA A,ORTS-ESCOLANO S,OPREA S O,et al.A Review on Deep Learning Techniques Applied to Semantic Segmentation[J].arXiv:1704.06857v1,2018.
[2] JONATHAN L,EVAN S,TREVOR D.Fully ConvolutionalNetworks for Semantic Segmentation[C]//The 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2015:3431-3440.
[3] VIJAY B,ALEX K,ROBERTO C,et al.SegNet:A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [C]//The 2017 IEEE Transactions on Pattern Analysis and Machine Intelligence.IEEE,2017:2481-2495.
[4] OLAF R,PHILIPP F,THOMAS B.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//The 2015 Medical Image Computing and Computer-Assisted Intervention(MICCAI).Springer,2015:234-241.
[5] CHEN L C,GEORGE P,IASONAS K.DeepLab:Semantic Image Segmentation with Deep Convolutional Nets,Atrous Convolution,and Fully Connected CRFs[C]//The 2018 IEEE Transactions on Pattern Analysis and Machine Intelligence.IEEE,2018:834-848.
[6] SHI W S,CAO J,LI Y H,et al.Edge Computing:Vision and Challenges[C]//The 2015 IEEE Internet of Things Journal.IEEE,2015:637-646.
[7] Google.Learn how to build AI products with Coral devices[EB/OL].https://coral.withgoogle.com/docs/dev-board/get-started/.
[8] JACOB B,KLIGYS S,CHEN B,et al.Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference[C]//The 2018 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2018:2704-2713.
[9] Google.Welcome to Colaboratory[EB/OL].https://coral.withgoo-gle.com/docs/dev-board/get-started/.
[10] ABADI M,AGARWAL A,BARHAM P,et al.TensorFlow:Large-Scale Machine Learning on Heterogeneous Distributed Systems[J].arxiv:1603.04467,2016.
[11] OpenAI.Tengine[EB/OL].https://github.com/OAID/Teng-ine.
[12] Alibaba.MNN[EB/OL].https://github.com/alibaba/MNN.
[13] Xiaomi.MACE[EB/OL].https://github.com/Xiaomi/mace.

相关文章 15

[1]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[2]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[3]	孙慧婷, 范艳芳, 马孟晓, 陈若愚, 蔡英. VEC中基于动态定价的车辆协同计算卸载方案 Dynamic Pricing-based Vehicle Collaborative Computation Offloading Scheme in VEC 计算机科学, 2022, 49(9): 242-248. https://doi.org/10.11896/jsjkx.210700166
[4]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[5]	王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[6]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[7]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[8]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[9]	胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[10]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[11]	侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[12]	周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[13]	苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[14]	于滨, 李学华, 潘春雨, 李娜. 基于深度强化学习的边云协同资源分配算法 Edge-Cloud Collaborative Resource Allocation Algorithm Based on Deep Reinforcement Learning 计算机科学, 2022, 49(7): 248-253. https://doi.org/10.11896/jsjkx.210400219
[15]	李梦菲, 毛莺池, 屠子健, 王瑄, 徐淑芳. 基于深度确定性策略梯度的服务器可靠性任务卸载策略 Server-reliability Task Offloading Strategy Based on Deep Deterministic Policy Gradient 计算机科学, 2022, 49(7): 271-279. https://doi.org/10.11896/jsjkx.210600040

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed