计算机科学

计算机科学 ›› 2020, Vol. 47 ›› Issue (6): 144-150.doi: 10.11896/jsjkx.190700121

• 计算机图形学&多媒体 • 上一篇    下一篇

基于多尺度残差网络的对象级边缘检测算法

朱威1,2, 王图强1, 陈悦峰1, 何德峰1,2   

  1. 1 浙江工业大学信息工程学院 杭州310023
    2 浙江省嵌入式系统联合重点实验室 杭州310023
  • 收稿日期:2019-07-17 出版日期:2020-06-15 发布日期:2020-06-10
  • 通讯作者: 朱威(weizhu@zjut.edu.cn)
  • 基金资助:
    浙江省自然科学基金(LY17F010013);国家自然科学基金(61401398)

Object-level Edge Detection Algorithm Based on Multi-scale Residual Network

ZHU Wei1,2, WANG Tu-qiang1, CHEN Yue-feng1, HE De-feng1,2   

  1. 1 College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China
    2 United Key Laboratory of Embedded System of Zhejiang Province,Hangzhou 310023,China
  • Received:2019-07-17 Online:2020-06-15 Published:2020-06-10
  • About author:ZHU Wei,born in 1982,Ph.D,associate professor.His main research interests include pattern recognition and intelligent system.
  • Supported by:
    This work was supported by the Natural Science Foundation of Zhejiang Province (LY17F010013) and National Natural Science Foundation of China (61401398)

PDF (PC)

976

摘要： 面向对象的边缘检测技术是智能视觉处理领域的关键基础技术,然而目前基于卷积神经网络的边缘检测结果存在分辨率低、噪声较多等问题。因此,文中提出了一种基于多尺度残差网络的对象级边缘检测算法。首先,设计了混合空洞卷积残差块,来替换原始残差网络中的普通卷积核,以放大网络的感受野;然后,设计了多尺度特征增强模块,对边缘信息进行多尺度特征提取,以放大网络的信息接受域;最后,设计了结合顶层语义特征的金字塔多尺度特征融合模块,将不同尺度下的特征信息进行融合,以输出边缘检测后的图像。为了验证所提算法的有效性,在公开数据集BSDS500上进行实验。实验结果表明,与现有算法相比,所提算法具有更好的边缘检测效果,客观指标ODS,OIS 和AP分别达到了0.819,0.838和0.849,主观检测效果也更接近真实值,噪声更少。

关键词: 残差网络, 多尺度特征增强, 金字塔特征融合结构, 空洞卷积

Abstract: Object-level edge detection technology is a key basic technology in the field of intelligent vision processing.However,there are some problems in the edge detection results based on convolutional neural network,such as low resolution and high noise.Therefore,an object-level edge detection algorithm based on multi-scale residual network is proposed.Firstly,a hybrid dilated convolution residual block is designed to replace the ordinary convolution kernel in the original residual network to enlarge the receptive field of the network.Secondly,a multi-scale feature enhancement module is designed to extract multi-scale features from edge information to enlarge the information receiving domain of the network.Finally,a pyramid multi-scale feature fusion module combining top-level semantic features is designed to fuse the feature information at different scales and output the image after edge detection.In order to verify the effectiveness of the proposed algorithm,experimental analysis is performed on the public dataset BSDS500.The experimental results show that compared with existing algorithms,the proposed algorithm has better edge detection effect,and the objective indicators ODS,OIS and AP are increased to 0.819,0.838 and 0.849,respectively,meanwhile the subjective detection effect is closer to the real value with less noise.

Key words: Dilated convolution, Multi-scale feature enhancement, Pyramid feature fusion structure, Residual network

中图分类号: 

  • TP391
[1]CANNY J F.A Computation Approach to Edge Detection [M].A Computational Approach to Edge Detection,1986.
[2]KONISHI S,YUILLE A L,COUGHLAN J M,et al.Statistical Edge Detection:Learning and Evaluating Edge Cues[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(1):57-74.
[3]ARBELÁEZ P,MAIRE M,FOWLKES C,et al.Contour Detection and Hierarchical Image Segmentation[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(5):898-916.
[4]DOLLÁR,PIOTR,ZITNICK C L.Fast Edge Detection Using Structured Forests[J].IEEE Transactions on Pattern Analysis &Machine Intelligence,2014,37(8):1558-1570.
[5]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet Classification with Deep Convolutional Neural Networks[C]//Advances in Neural Information Processing Systems.2012:1097-1105.
[6]GANIN Y,LEMPITSKY V.N4-Fields:Neural Network Nearest Neighbor Fields for Image Transforms[C]//Asian Confe-rence on Computer Vision.Springer,Cham,2014:536-551.
[7]BERTASIUS G,SHI J,TORRESANI L.DeepEdge:A Multi-scale Bifurcated Deep Network for Top-down Contour Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:4380-4389.
[8]XIE S,TU Z.Holistically-Nested Edge Detection[C]//Procee-dings of the IEEE International Conference on Computer Vision.2015:1395-1403.
[9]LIU Y,CHENG M M,HU X,et al.Richer Convolutional Features for Edge Detection[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2017:3000-3009.
[10]YU F,KOLTUN V.Multi-scale Context Aggregation by Dilated Convolutions[J].arXiv:1511.07122.
[11]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Ima-ge Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[12]WANG P,CHEN P,YUAN Y,et al.Understanding Convolution for Semantic Segmentation[C]//IEEE Winter Conference on Applications of Computer Vision.2018:1451-1460.
[13]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature Pyramid Networks for Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125.
[14]MOTTAGHI R,CHEN X,LIU X,et al.The Role of Context for Object Detection and Semantic Segmentation in the Wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:891-898.
[15]KOKKINOS I.Pushing the Boundaries of Boundary Detection using Deep Learning[J].arXiv:1511.07386.
[16]YANG J,PRICE B,COHEN S,et al.Object Contour Detection with a Fully Convolutional Encoder-Decoder Network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:193-202.
[17]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,42(2):318-327.
[18]ZITNICK C L,DOLLÁR P.Edge Boxes:Locating Object Proposals from Edges[C]//European Conference on Computer Vision.Springer,Cham,2014:391-405.
[19]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].arXiv:1409.1556.
[20]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2015:1-9.
[21]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE 2017:4700-4708.
[22]KIVINEN J,WILLIAMS C,HEESS N.Visual Boundary Prediction:A Deep Neural Prediction Network and Quality Dissection[C]//International Conference on Artificial Intelligence and Statistics.PMLR,2014:512-521.
[1] 王馨彤, 王璇, 孙知信.
基于多尺度记忆残差网络的网络流量异常检测模型
Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network
计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[2] 高荣华, 白强, 王荣, 吴华瑞, 孙想.
改进注意力机制的多叉树网络多作物早期病害识别方法
Multi-tree Network Multi-crop Early Disease Recognition Method Based on Improved Attention Mechanism
计算机科学, 2022, 49(6A): 363-369. https://doi.org/10.11896/jsjkx.210500044
[3] 赵人行, 徐频捷, 刘瑶.
基于深度卷积残差网络的心电单导联房颤检测方法
ECG-based Atrial Fibrillation Detection Based on Deep Convolutional Residual Neural Network
计算机科学, 2022, 49(5): 186-193. https://doi.org/10.11896/jsjkx.220200002
[4] 韩红旗, 冉亚鑫, 张运良, 桂婕, 高雄, 易梦琳.
基于共同子空间分类学习的跨媒体检索研究
Study on Cross-media Information Retrieval Based on Common Subspace Classification Learning
计算机科学, 2022, 49(5): 33-42. https://doi.org/10.11896/jsjkx.210200157
[5] 高心悦, 田汉民.
基于改进U-Net网络的液滴分割方法
Droplet Segmentation Method Based on Improved U-Net Network
计算机科学, 2022, 49(4): 227-232. https://doi.org/10.11896/jsjkx.210300193
[6] 张红民, 李萍萍, 房晓冰, 刘宏.
改进YOLOv3网络模型的人体异常行为检测方法
Human Abnormal Behavior Detection Method Based on Improved YOLOv3 Network Model
计算机科学, 2022, 49(4): 233-238. https://doi.org/10.11896/jsjkx.210300251
[7] 瞿中, 陈雯.
基于空洞卷积和多特征融合的混凝土路面裂缝检测
Concrete Pavement Crack Detection Based on Dilated Convolution and Multi-features Fusion
计算机科学, 2022, 49(3): 192-196. https://doi.org/10.11896/jsjkx.210100164
[8] 郭琳, 李晨, 陈晨, 赵睿, 范仕霖, 徐星雨.
基于通道注意递归残差网络的图像超分辨率重建
Image Super-resolution Reconstruction Using Recursive ResidualNetwork Based on ChannelAttention
计算机科学, 2021, 48(8): 139-144. https://doi.org/10.11896/jsjkx.200500150
[9] 王施云, 杨帆.
基于U-Net特征融合优化策略的遥感影像语义分割方法
Remote Sensing Image Semantic Segmentation Method Based on U-Net Feature Fusion Optimization Strategy
计算机科学, 2021, 48(8): 162-168. https://doi.org/10.11896/jsjkx.200700182
[10] 许华杰, 张晨强, 苏国韶.
基于深层卷积残差网络的航拍图建筑物精确分割方法
Accurate Segmentation Method of Aerial Photography Buildings Based on Deep Convolutional Residual Network
计算机科学, 2021, 48(8): 169-174. https://doi.org/10.11896/jsjkx.200500096
[11] 暴雨轩, 芦天亮, 杜彦辉, 石达.
基于i_ResNet34模型和数据增强的深度伪造视频检测方法
Deepfake Videos Detection Method Based on i_ResNet34 Model and Data Augmentation
计算机科学, 2021, 48(7): 77-85. https://doi.org/10.11896/jsjkx.210300258
[12] 牛康力, 谌雨章, 张龚平, 谭前程, 王绎冲, 罗美琪.
基于深度学习的无人机航拍车流量监测
Vehicle Flow Measuring of UVA Based on Deep Learning
计算机科学, 2021, 48(6A): 275-280. https://doi.org/10.11896/jsjkx.200900149
[13] 王建明, 黎向锋, 叶磊, 左敦稳, 张丽萍.
基于信道注意结构的生成对抗网络医学图像去模糊
Medical Image Deblur Using Generative Adversarial Networks with Channel Attention
计算机科学, 2021, 48(6A): 101-106. https://doi.org/10.11896/jsjkx.200600144
[14] 李佳倩, 严华.
基于跨列特征融合的人群计数方法
Crowd Counting Method Based on Cross-column Features Fusion
计算机科学, 2021, 48(6): 118-124. https://doi.org/10.11896/jsjkx.200700107
[15] 龚航, 刘培顺.
夜间行驶车辆远光灯检测方法
Detection Method of High Beam in Night Driving Vehicle
计算机科学, 2021, 48(12): 256-263. https://doi.org/10.11896/jsjkx.200700026
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发