基于语义信息的精细化边缘检测方法

doi:10.19678/j.issn.1000-3428.0060230

摘要/Abstract

摘要： 边缘检测是在图像中准确地提取视觉上显著的边缘像素，以得到图像的边缘信息，然而传统基于全卷积网络的边缘检测方法通常存在预测边缘粗糙、模糊等问题。提出一种语义信息指导的精细化边缘检测方法。通过图像分割子网络将学习到的图像语义信息传递给边缘检测子网络，同时利用图像语义信息指导边缘检测子网络，其引入具有注意力机制与残差结构的特征融合模块，以生成精细的图像边缘，增强不同尺度的特征融合。在此基础上，结合图像分割任务和图像边缘检测任务中的代价函数定义新的模型代价函数并进行训练，进一步提高网络边缘检测质量。在BSDS500数据集上的实验结果验证了该方法的有效性，结果表明，该方法的固定轮廓阈值与图像最佳阈值分别达到0.818和0.841，相比HED、RCF等主流边缘检测方法，能够预测更精细的边缘图像，且鲁棒性更优。

关键词: 边缘检测, 图像分割, 语义指导, 全卷积网络, 注意力机制

Abstract: Edge detection is to accurately extract visually significant edge pixels from the image to obtain the edge information of the image.Traditional edge detection methods based on Full Convolution Network(FCN) usually require rough and fuzzy edge prediction.This paper proposes a refined edge detection method guided by semantic information.The learned image semantic information is transmitted to the edge detection subnetwork through the image segmentation subnetwork.The image semantic information is used to guide the edge detection subnetwork.A feature fusion module with attention mechanism and residual structure is also introduced to generate fine image edges to enhance feature fusion at different scales.On this basis, the cost function in image segmentation task is combined with the image edge detection task, to define a new model cost function, which is further trained to improve the quality of network edge detection.The experimental results on the BSDS500 dataset verify the effectiveness of the proposed method.The optimal dataset scale and image optimal scale attained by this method are 0.818 and 0.841, respectively.Compared with mainstream edge detection methods, such as HED and RCF, the proposed method can predict finer edge images with improved robustness.

Key words: edge detection, image segmentation, semantic guidance, Full Convolution Network(FCN), attention mechanism

中图分类号:

TP391.4

黄胜, 冉浩杉. 基于语义信息的精细化边缘检测方法[J]. 计算机工程, 2022, 48(3): 204-210.

HUANG Sheng, RAN Haoshan. Refined Edge Detection Method Based on Semantic Information[J]. Computer Engineering, 2022, 48(3): 204-210.

https://www.ecice06.com/CN/Y2022/V48/I3/204

图/表 7

20220331202551

20220331202554

20220331202558

20220331202601

20220331202604

20220331202607

20220331202610

参考文献

[1] TORRE V, POGGIO T A.On edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(2):147-63.
[2] FELDMAN J A, FELDMAN G M, FALK G, et al.The stanford hand-eye project[C]//Proceedings of the 1st International Joint Conference on Artificial Intelligence. New York, USA:ACM Press, 1969:521-526.
[3] CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6):679-698.
[4] ARBELAEZ P, MAIRE M, FOWLKES C, et al.Contour detection and hierarc-hical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(5):898-916.
[5] MARTIN D R, FOWLKES C, MALIK J.Learning to detect natural image boundaries using local brightness, color, and texture cues[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(5):530-549.
[6] DOLLAR P, TU Z, BELONGIE S.Supervised learning of edges and object boundaries[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2006:1964-1971.
[7] REN X.Multi-scale improves boundary detection in natural images[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2008:533-545.
[8] DOLLAR P, ZITNICK C L.Fast edge detection using structured forests[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 13(7):120-135.
[9] SHEN W, WANG X, WANG Y, et al.Deepcontour:a deep convolutional feature learned by positive-sharing loss for contour detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:3982-3991.
[10] XIE S, TU Z.Holistically-nested edge detection[J].International Journal of Computer Vision, 2017, 125(5):1-16.
[11] LIU Y, CHENG M M, HU X, et al.Richer convolutional features for edge detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:3000-3009.
[12] NAIR V, HINTON G E.Rectified linear units improve restricted Boltzmann machines[C]//Proceedings of the 27th International Conference on Machine Learning.New York, USA:ACM Press, 2010:807-814.
[13] HU J, SHEN L, ALBANIE S, et al.Squeeze-and-excitation networks[EB/OL].[2020-11-05].https://arxiv.org/pdf/1709.01507.pdf.
[14] SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2020-11-05].https://arxi-v.prg/pdf/1409.1556.pdf.
[15] RONNEBERGER O, FISCHER P, BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin, Germany:Springer, 2015:234-241.
[16] WANG P, CHEN P, YUAN Y, et al.Understanding convolution for semantic segmentation[C]//Proceedings of IEEE Winter Conference on Applications of Computer Vision.Washington D.C., USA:IEEE Press, 2018:1451-1460.
[17] XIE S, GIRSHICK R, DOLLÁR P, et al.Aggregated residual transformations for deep neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:1492-1500.
[18] GLOROT X, BENGIO Y.Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the 13th International Conference on Artificial Intelligence and Statistics.New York, USA:[s.n.], 2010:249-256.
[19] 刘胜男, 宁纪锋.基于超像素的点互信息边界检测算法[J].计算机应用, 2016, 36(8):2296-2300. LIU S N, NING J F.Super-pixel based pointwise mutual information boundary detection algorithm[J].Journal of Computer Applications, 2016, 36(8):2296-2300.(in Chinese)
[20] DOLLAR P, ZITNICK C L.Fast edge detection using structured forests[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(8):1558-1570.
[21] ZITNICK C L, DOLLAR P.Edge boxes:locating object proposals from edges[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2014:391-405.
[22] BERTASIUS G, SHI J, TORRESANI L.Deepedge:a multi-scale bifurcated deep network for top-down contour detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2015:4380-4389.

选择文件类型/文献管理软件名称

选择包含的内容