基于可分离残差模块的精确实时语义分割
|
摘要
针对当前智能驾驶领域场景理解中的语义分割算法无法同时满足高精度和高效率要求的问题,提出了精确高效的语义分割算法。基于可分离残差模块和降采样模块,设计了充分利用其学习能力和学习效率的高效精确语义分割网络结构。利用Cityscapes数据集,在图像处理效率12 frame/s的基础上达到分割精度67.86%。研究结果表明,所提方法在精度和效率上均能达到较好的效果,实现了精度和效率的平衡。
Aiming at the problem that the current approaches of semantic segmentation cannot meet the simultaneous demands on accuracy and efficiency in scene parsing in the intelligent vehicles,an accurate and efficient algorithm for semantic segmentation is proposed.Based on the proposed separable residual module and the downsampling module,a real-time and accurate semantic segmentation network is designed.With the Cityscapes dataset,the segmentation accuracy can reach 67.86% on the basis of the 12 frame/s efficiency.The research results demonstrate that the proposed method can achieve a good performance both in accuracy and efficiency,and makes a balance between accuracy and efficiency.
Aiming at the problem that the current approaches of semantic segmentation cannot meet the simultaneous demands on accuracy and efficiency in scene parsing in the intelligent vehicles,an accurate and efficient algorithm for semantic segmentation is proposed.Based on the proposed separable residual module and the downsampling module,a real-time and accurate semantic segmentation network is designed.With the Cityscapes dataset,the segmentation accuracy can reach 67.86% on the basis of the 12 frame/s efficiency.The research results demonstrate that the proposed method can achieve a good performance both in accuracy and efficiency,and makes a balance between accuracy and efficiency.
引文
[1]Romera E,Bergasa L M,Arroyo R.Can we unify monocular detectors for autonomous driving by using the pixel-wise semantic segmentation of CNNs?[EB/OL].(2016-07-04)[2018-08-10].https://arxiv.org/abs/1607.00971.
[2]Li L H,Qian B,Lian J,et al.Study on traffic scene semantic segmentation method based on convolutional neural network[J].Journal on Communications,2018,39(4):123-130.李琳辉,钱波,连静,等.基于卷积神经网络的交通场景语义分割方法研究[J].通信学报,2018,39(4):123-130.
[3]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[4]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[5]Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
[6]Fang X,Wang G H,Yang H C,et al.High resolution remote sensing image classification combining with mean-shift segmentation and fully convolution neural network[J].Laser&Optoelectronics Progress,2018,55(2):022802.方旭,王光辉,杨化超,等.结合均值漂移分割与全卷积神经网络的高分辨遥感影像分类[J].激光与光电子学进展,2018,55(2):022802.
[7]Wang L,Liu Q.A multi-object image segmentation algorithm based on local features[J].Laser&Optoelectronics Progress,2018,55(6):061002.王琳,刘强.基于局部特征的多目标图像分割算法[J].激光与光电子学进展,2018,55(6):061002.
[8]Ji M Y,Xi X M,Yu Z L.A review of semantic segmentation based on deep learning[J].Information Technology and Informatization,2017(10):137-140.计梦予,袭肖明,于治楼.基于深度学习的语义分割方法综述[J].信息技术与信息化,2017(10):137-140.
[9]Zhao H S,Shi J P,Qi X J,et al.Pyramid scene parsing network[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2017:6230-6239.
[10]Chen L C,Papandreou G,Kokkinos I,et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL].(2014-12-22)[2018-08-10].https://arxiv.org/abs/1412.7062
[11]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.
[12]Lin G S,Milan A,Shen C H,et al.RefineNet:multi-path refinement networks for high-resolution semantic segmentation[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2017:5168-5177.
[13]Paszke A,Chaurasia A,Kim S,et al.Enet:a deep neural network architecture for real-time semantic segmentation[EB/OL].(2016-06-07)[2018-08-10].https://arxiv.org/abs/1606.02147.
[14]Yu C,Wang J,Peng C,et al.Bisenet:bilateral segmentation network for real-time semantic segmentation[J].[EB/OL].(2018-08-02)[2018-08-13].https://arxiv.org/abs/1808.00897.
[15]Iandola F N,Han S,Moskewicz M W,et al.Squeezenet:alexnet-level accuracy with 50×fewer parameters and<0.5 MB model size[EB/OL].(2016-11-04)[2018-08-10].https://arxiv.org/pdf/1602.07360v4.pdf.
[16]Guo C C,Yu F Q,Chen Y.Image semantic segmentation based on convolutional neural network feature and improved superpixel matching[J].Laser&Optoelectronics Progress,2018,55(8):081005.郭呈呈,于凤芹,陈莹.基于卷积神经网络特征和改进超像素匹配的图像语义分割[J].激光与光电子学进展,2018,55(8):081005.
[17]Yao H B,Bian J W,Cong J W,et al.Medical image segmentation model based on local sparse shape representation[J].Laser&Optoelectronics Progress,2018,55(5):051011.姚红兵,卞锦文,丛嘉伟,等.基于局部稀疏形状表示的医学图像分割模型[J].激光与光电子学进展,2018,55(5):051011.
[18]Cordts M,Omran M,Ramos S,et al.The cityscapes dataset[C]//CVPR Workshop on the Future of Datasets in Vision,2015,1(2):3.
[19]Cordts M,Omran M,Ramos S,et al.The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:3213-3223.
[20]Howard A G,Zhu M,Chen B,et al.Mobilenets:efficient convolutional neural networks for mobile vision applications[EB/OL].(2017-04-17)[2018-08-11].https://arxiv.org/abs/1704.04861.
[21]Szegedy C,Liu W,Jia Y Q,et al.Going deeper with convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2015:1-9.
[22]He K M,Zhang X Y,Ren S Q,et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
[23]Wu Z,Shen C,Hengel A.High-performance semantic segmentation using very deep fully convolutional networks[EB/OL].(2016-04-15)[2018-08-11].https://arxiv.org/abs/1604.04339.
[24]Giusti A,Cire?an D C,Masci J,et al.Fast image scanning with deep max-pooling convolutional neural networks[C]//Proceedings of IEEE International Conference on Image Processing,2013:4034-4038.
[25]Holschneider M,Kronland-Martinet R,Morlet J,et al.A real-time algorithm for signal analysis with the help of the wavelet transform[M].Berlin,Heidelberg:Springer,1990:286-297.
[26]Sermanet P,Eigen D,Zhang X,et al.Overfeat:integrated recognition,localization and detection using convolutional networks[EB/OL].(2014-02-24)[2018-08-12].https://arxiv.org/abs/1312.6229.
[27]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.
[28]Kendall A,Badrinarayanan V,Cipolla R.Bayesian SegNet:model uncertainty in deep convolutional encoder-decoder architectures for scene understanding[EB/OL].(2016-10-10)[2018-08-12].https://arxiv.org/abs/1511.02680.
[2]Li L H,Qian B,Lian J,et al.Study on traffic scene semantic segmentation method based on convolutional neural network[J].Journal on Communications,2018,39(4):123-130.李琳辉,钱波,连静,等.基于卷积神经网络的交通场景语义分割方法研究[J].通信学报,2018,39(4):123-130.
[3]Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[4]Krizhevsky A,Sutskever I,Hinton G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[5]Long J,Shelhamer E,Darrell T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2015:3431-3440.
[6]Fang X,Wang G H,Yang H C,et al.High resolution remote sensing image classification combining with mean-shift segmentation and fully convolution neural network[J].Laser&Optoelectronics Progress,2018,55(2):022802.方旭,王光辉,杨化超,等.结合均值漂移分割与全卷积神经网络的高分辨遥感影像分类[J].激光与光电子学进展,2018,55(2):022802.
[7]Wang L,Liu Q.A multi-object image segmentation algorithm based on local features[J].Laser&Optoelectronics Progress,2018,55(6):061002.王琳,刘强.基于局部特征的多目标图像分割算法[J].激光与光电子学进展,2018,55(6):061002.
[8]Ji M Y,Xi X M,Yu Z L.A review of semantic segmentation based on deep learning[J].Information Technology and Informatization,2017(10):137-140.计梦予,袭肖明,于治楼.基于深度学习的语义分割方法综述[J].信息技术与信息化,2017(10):137-140.
[9]Zhao H S,Shi J P,Qi X J,et al.Pyramid scene parsing network[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2017:6230-6239.
[10]Chen L C,Papandreou G,Kokkinos I,et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL].(2014-12-22)[2018-08-10].https://arxiv.org/abs/1412.7062
[11]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.
[12]Lin G S,Milan A,Shen C H,et al.RefineNet:multi-path refinement networks for high-resolution semantic segmentation[C]//Proceedings of IEEEConference on Computer Vision and Pattern Recognition,2017:5168-5177.
[13]Paszke A,Chaurasia A,Kim S,et al.Enet:a deep neural network architecture for real-time semantic segmentation[EB/OL].(2016-06-07)[2018-08-10].https://arxiv.org/abs/1606.02147.
[14]Yu C,Wang J,Peng C,et al.Bisenet:bilateral segmentation network for real-time semantic segmentation[J].[EB/OL].(2018-08-02)[2018-08-13].https://arxiv.org/abs/1808.00897.
[15]Iandola F N,Han S,Moskewicz M W,et al.Squeezenet:alexnet-level accuracy with 50×fewer parameters and<0.5 MB model size[EB/OL].(2016-11-04)[2018-08-10].https://arxiv.org/pdf/1602.07360v4.pdf.
[16]Guo C C,Yu F Q,Chen Y.Image semantic segmentation based on convolutional neural network feature and improved superpixel matching[J].Laser&Optoelectronics Progress,2018,55(8):081005.郭呈呈,于凤芹,陈莹.基于卷积神经网络特征和改进超像素匹配的图像语义分割[J].激光与光电子学进展,2018,55(8):081005.
[17]Yao H B,Bian J W,Cong J W,et al.Medical image segmentation model based on local sparse shape representation[J].Laser&Optoelectronics Progress,2018,55(5):051011.姚红兵,卞锦文,丛嘉伟,等.基于局部稀疏形状表示的医学图像分割模型[J].激光与光电子学进展,2018,55(5):051011.
[18]Cordts M,Omran M,Ramos S,et al.The cityscapes dataset[C]//CVPR Workshop on the Future of Datasets in Vision,2015,1(2):3.
[19]Cordts M,Omran M,Ramos S,et al.The cityscapes dataset for semantic urban scene understanding[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:3213-3223.
[20]Howard A G,Zhu M,Chen B,et al.Mobilenets:efficient convolutional neural networks for mobile vision applications[EB/OL].(2017-04-17)[2018-08-11].https://arxiv.org/abs/1704.04861.
[21]Szegedy C,Liu W,Jia Y Q,et al.Going deeper with convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2015:1-9.
[22]He K M,Zhang X Y,Ren S Q,et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778.
[23]Wu Z,Shen C,Hengel A.High-performance semantic segmentation using very deep fully convolutional networks[EB/OL].(2016-04-15)[2018-08-11].https://arxiv.org/abs/1604.04339.
[24]Giusti A,Cire?an D C,Masci J,et al.Fast image scanning with deep max-pooling convolutional neural networks[C]//Proceedings of IEEE International Conference on Image Processing,2013:4034-4038.
[25]Holschneider M,Kronland-Martinet R,Morlet J,et al.A real-time algorithm for signal analysis with the help of the wavelet transform[M].Berlin,Heidelberg:Springer,1990:286-297.
[26]Sermanet P,Eigen D,Zhang X,et al.Overfeat:integrated recognition,localization and detection using convolutional networks[EB/OL].(2014-02-24)[2018-08-12].https://arxiv.org/abs/1312.6229.
[27]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.
[28]Kendall A,Badrinarayanan V,Cipolla R.Bayesian SegNet:model uncertainty in deep convolutional encoder-decoder architectures for scene understanding[EB/OL].(2016-10-10)[2018-08-12].https://arxiv.org/abs/1511.02680.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |