Interactive Target Segmentation Algorithm Based on Two-Stage Network

doi:10.19678/j.issn.1000-3428.0057071

Abstract

Abstract: Most of the existing interaction segmentation methods are faced with the single interaction mode and inaccurate prediction results.To address the problem,this paper proposes a target segmentation model called ScribNet based on two-stage network to realize more complete and precise interactive target segmentation.The model adopts the scribbling interaction mode,and encodes the information to form interaction guidance.A skeleton randomness simulation algorithm is designed to perform simulated interactions under big data.Then a prediction optimization module is introduced into the traditional segmentation model to form a two-stage network architecture to fully use the interaction guidance information.Experimental results on COCO and PASCAL datasets show that compared with DEXTR,GrabCut and other methods,the proposed ScribNet has a higher segmentation accuracy.

Key words: pattern recognition, deep learning, interactive target segmentation, scribbling interaction, two-stage network

摘要： 针对已有多数交互式分割方法交互方式单一、预测结果精度较低的问题，构建一种基于双阶段网络的目标分割模型ScribNet，以实现更完整和精细的交互式目标分割。采用灵活涂画的交互方式，通过编码形成交互指导信息。设计骨架随机性仿真算法，实现大数据下的模拟交互操作。在传统分割模型中引入预测优化模块，形成双阶段网络结构，以充分利用交互指导信息。在COCO和PASCAL数据集上的实验结果表明，与DEXTR、GrabCut等方法相比，ScribNet模型的分割精度较高。

关键词: 模式识别, 深度学习, 交互式目标分割, 涂画式交互, 双阶段网络

CLC Number:

TP391

ZHANG Huayue, ZHANG Shunli, ZHANG Li. Interactive Target Segmentation Algorithm Based on Two-Stage Network[J]. Computer Engineering, 2021, 47(2): 300-306.

张华悦, 张顺利, 张利. 基于双阶段网络的交互式目标分割算法[J]. 计算机工程, 2021, 47(2): 300-306.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0057071

http://www.ecice06.com/EN/Y2021/V47/I2/300

Figures/Tables 10

References 22

[1]	LONG J,SHELHAMER E,DARRELL T.Fully convo-lutional networks for semantic segmentation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[2]	NOH H,HONG S,HAN B.Learning deconvolution network for semantic segmentation[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:1520-1528.
[3]	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.
[4]	LI Yi,QI Haozhi,DAI Jifeng,et al.Fully convolutional instance-aware semantic segmentation[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2359-2367.
[5]	LIU Shu,QI Lu,QIN Haifeng,et al.Path aggregation network for instance segmentation[EB/OL].[2019-11-20].https://arxiv.org/abs/1803.01534.
[6]	HE K M,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:2961-2969.
[7]	KIRILLOV A,HE K M,GIRSHICK R,et al.Panoptic segmentation[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:9404-9413.
[8]	KIRILLOV A,GIRSHICK R,HE K M,et al.Panoptic feature pyramid networks[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:6399-6408.
[9]	ZHOU Lifang,WANG Lu,LI Weisheng,et al.An automatic segmentation method of liver with optimized tree model[J].Computer Engineering,2019,45(2):226-232.(in Chinese)周丽芳,王璐,李伟生,等.一种优化树状模型的肝脏自动分割方法[J].计算机工程,2019,45(2):226-232.
[10]	BENENSON R,POPOV S,FERRARI V.Large-scale interactive object segmentation with human annotators[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:11700-11709.
[11]	ROTHER C,KOLMOGOROV V,BLAKE A.GrabCut:interactive foreground extraction using iterated graph cuts[J].ACM Transactions on Graphics,2004,23(3):309-314.
[12]	PAK C H,ZHAO H,ZHU H B,et al.Interactive object segmentation based on level set method[J].Computer Engineering,2016,42(2):229-235.(in Chinese)朴春赫,赵海,朱宏博,等.基于水平集方法的交互式目标分割算法[J].计算机工程,2016,42(2):229-235.
[13]	MANINIS K K,CAELLES S,PONT-TUSET J,et al.Deep extreme cut:from extreme points to object segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:616-625.
[14]	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,2018,40(4):834-848.
[15]	CHEN L C,PAPANDREOU G,SCHROFF F,et al. Rethinking atrous convolution for semantic image segmentation[EB/OL].[2019-11-20].https://arxiv.org/pdf/1706.05587.pdf.
[16]	CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2018:801-818.
[17]	CAELLES S,PONT-TUSET J,PERAZZI F,et al.The 2019 DAVIS challenge on VOS:unsupervised multi-object segmentation[EB/OL].[2019-11-20].https://arxiv.org/abs/1905.00737.
[18]	PONT-TUSET J,PERAZZI F,CAELLES S,et al.The 2017 DAVIS challenge on video object segmentation[EB/OL].[2019-11-20].https://arxiv.org/abs/1704.00675.
[19]	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.
[20]	LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:common objects in context[M]//SZELISKI R.Computer vision.Berlin,Germany:Springer,2014.
[21]	EVERINGHAM M,ESLAMI S M A,VAN GOOL L,et al.The pascal visual object classes challenge:a retrospective[J].International Journal of Computer Vision,2015,111(1):98-136.
[22]	HARIHARAN B,ARBELAEZ P,BOURDEV L,et al.Semantic contours from inverse detectors[C]//Proceedings of 2011 International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:991-998.

Please choose a citation manager

Content to export