Semantic Segmentation Algorithm Combined with Edge Detection

doi:10.19678/j.issn.1000-3428.0058167

Abstract

Abstract: To address the fuzzy and inaccurate target edges in semantic segmentation,a semantic segmentation network combined with edge detection is proposed.The network consists of an edge detection network and a semantic segmentation network.The edge detection network is used to extract the edge features of the image,while the semantic segmentation network is used to extract the preliminary semantic segmentation features.The edge features and the semantic segmentation features are fused through the feature fusion module to obtain the final semantic segmentation result.The experimental results show that compared with the SegNet algorithm,the proposed algorithm improves the mIoU by 1.5 percentage points on the CamVid dataset and 1.8 percentage points on the Cityscapes dataset.The effectiveness of the proposed algorithm is verified.

Key words: convolutional neural network, Fully Convolutional Network(FCN), semantic segmentation, edge detection, feature fusion

摘要： 针对语义分割中目标边缘模糊与分割不准确的问题，提出一种结合边缘检测的语义分割网络。整个网络由边缘检测网络和语义分割网络并行组成。利用边缘检测网络与语义分割网络分别提取图像的边缘特征和初步的语义分割特征，通过特征融合模块将边缘特征和语义分割特征进行融合，得到最终的语义分割结果。在CamVid数据集和Cityscapes数据集上的实验结果表明，与SegNet算法相比，该算法平均交并比分别提升了1.5和1.8个百分点，验证了所提算法的有效性。

关键词: 卷积神经网络, 全卷积网络, 语义分割, 边缘检测, 特征融合

CLC Number:

TP391.41

WANG Nan, HOU Zhiqiang, ZHAO Mengqi, YU Wangsheng, MA Sugang. Semantic Segmentation Algorithm Combined with Edge Detection[J]. Computer Engineering, 2021, 47(7): 257-265.

王囡, 侯志强, 赵梦琦, 余旺盛, 马素刚. 结合边缘检测的语义分割算法[J]. 计算机工程, 2021, 47(7): 257-265.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0058167

http://www.ecice06.com/EN/Y2021/V47/I7/257

Figures/Tables 14

References

[1] 魏云超,赵耀.基于DCNN的图像语义分割综述[J].北京交通大学学报,2016,40(4):82-91. WEI Y C,ZHAO Y.A review on image semantic segmentation based on DCNN[J].Journal of Beijing Jiaotong University,2016,40(4):82-91.(in Chinese)
[2] 易盟,隋立春.基于改进全卷积神经网络的航拍图像语义分类方法[J].计算机工程,2017,43(10):216-221. YI M,SUI L C.Aerial image semantic classification method based on improved full convolution neural network[J].Computer Engineering,2017,43(10):216-221.(in Chinese)
[3] SIAM M,ELKERDAWY S,JAGERSAND M,et al.Deep semantic segmentation for automated driving:taxonomy,roadmap and challenges[C]//Proceedings of the 20th IEEE International Conference on Intelligent Transportation Systems.Washington D.C.,USA:IEEE Press,2017:1-8.
[4] 曾碧,黄文.一种融合多特征聚类集成的室内点云分割方法[J].计算机工程,2018,44(3):281-286. ZENG B,HUANG W.An indoor point cloud segmentation method combining multi-feature clustering integration[J].Computer Engineering,2018,44(3):281-286.(in Chinese)
[5] 于旭宅,王瑞瑞,陈伟杰.改进分水岭算法在无人机遥感影像树冠分割中的应用[J].福建农林大学学报(自然科学版),2018,47(4):428-434. YU X Z,WANG R R,CHEN W J.Forest canopy segmentation of UAV remote sensing images using improved watershed algorithm[J].Journal of Fujian Agriculture and Forestry University(Natural Science Edition),2018,47(4):428-434.(in Chinese)
[6] SHI J,MALIK J.Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[7] VINCENT L,SOILLE P.Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1991,13(6):583-598.
[8] ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[9] 罗嗣卿,张志超,岳琪.基于改进SEGNET模型的图像语义分割[J].计算机工程,2021,47(4):256-261. LUO Siqing,ZHANG Zhichao,YUE Qi.Semantic image segmentation based on improved SEGNET model[J].Computer Engineering,2021,47(4):256-261.(in Chinese)
[10] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[11] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[12] PASZKE A,CHAURASIA A,KIM S,et al.ENet:a deep neural network architecture for real-time semantic segmentation[EB/OL].[2020-03-20].https://arxiv.org/abs/1606.02147.
[13] YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions[EB/OL].[2020-03-20].https://arxiv.org/abs/1511.07122.
[14] ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2881-2890.
[15] 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,2017,40(4):834-848.
[16] CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation[EB/OL].[2020-03-20].https://arxiv.org/abs/1706.05587.
[17] CHEN L C,ZHU Y K,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of IEEE ECCV'18.Washington D.C.,USA:IEEE Press,2018:801-808.
[18] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL].[2020-03-20].https://arxiv.org/abs/1412.7062.
[19] HUANG Q,XIA C,ZHENG W,et al.Object boundary guided semantic segmentation[C]//Proceedings of IEEE ACCV'16.Washington D.C.,USA:IEEE Press,2016:197-212.
[20] KITTLER J.On the accuracy of the Sobel edge detector[J].Image and Vision Computing,1983,1(1):37-42.
[21] CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[22] GANIN Y,LEMPITSKY V.N4-Fields:neural network nearest neighbor fields for image transforms[EB/OL].[2020-03-20].https://arxiv.org/abs/1406.6558.
[23] 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.
[24] 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.
[25] XIE S,TU Z.Holistically-nested edge detection[C]//Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:1395-1403.
[26] 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.
[27] LYU H,FU H,HU X,et al.ESNet:edge-based segmentation network for real-time semantic segmentation in traffic scenes[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2019:1855-1859.
[28] 杨威,张建林,徐智勇,等.一种改进的FocalLos在语义分割上的应用[J].半导体光电,2019,40(4):555-559. YANG E,ZHANG J L,XU Z Y,et al.An improved Focal Loss function for semantic segmentation[J]. Semiconductor Optoelectronics,2019,40(4):555-559.(in Chinese)
[29] CAO G,XIE X,YANG W,et al.Feature-fused SSD:fast detection for small objects[C]//Proceedings of the 9th International Conference on Graphic and Image Processing.Washington D.C.,USA:IEEE Press,2018:106-151.
[30] SACHIN M.ESPNetv2:Light-weighta,efficientpower, and general purpose convolutional neural network[EB/OL].[2020-03-20].https://arxiv.org/abs/1811.11431.
[31] SANDLER M,HOWARD A,ZHU M L,et al.MobileNetV2:inverted residuals and linear bottlenecks[EB/OL].[2020-03-20].https://arxiv.org/abs/1801.04381.

Please choose a citation manager

Content to export