浏览全部资源
扫码关注微信
大连民族大学 机电工程学院,辽宁 大连 116600
[ "毛 琳(1977-),女,山东荣成人,副教授,博士,硕士生导师,2005年于黑龙江大学获得硕士学位,2011年于哈尔滨工程大学获得博士学位,主要从事机器视觉目标跟踪与多传感器信息融合的研究。E-mail: maolin@dlnu.edu.cn" ]
[ "任凤至(1995-),女,辽宁葫芦岛人,硕士研究生,2019年于大连民族大学获得学士学位,主要从事是机器视觉和目标分割算法的研究。E-mail: renfz2019@163.com" ]
收稿日期:2020-04-17,
修回日期:2020-06-12,
纸质出版日期:2020-12-15
移动端阅览
毛琳,任凤至,杨大伟等.实例特征深度链式学习全景分割网络[J].光学精密工程,2020,28(12):2665-2673.
MAO Lin,REN Feng-zhi,YANG Da-wei,et al.INFNet :Deep instance feature chain learning network for panoptic segmentation[J].Optics and Precision Engineering,2020,28(12):2665-2673.
毛琳,任凤至,杨大伟等.实例特征深度链式学习全景分割网络[J].光学精密工程,2020,28(12):2665-2673. DOI: 10.37188/OPE.20202812.2665.
MAO Lin,REN Feng-zhi,YANG Da-wei,et al.INFNet :Deep instance feature chain learning network for panoptic segmentation[J].Optics and Precision Engineering,2020,28(12):2665-2673. DOI: 10.37188/OPE.20202812.2665.
针对全景分割中实例目标边缘特征提取不足导致目标边界分割失效的问题,提出一种创新的实例特征深度链式学习全景分割网络。该网络由基本的链式单元组合而成,根据单元结构对特征信息处理方法的不同,链式单元分为特征保持链和特征增强链两种。特征保持链是链式网络特征提取过程的输入级,保证输入信息的完整性,而后将特征传递到特征增强链结构;特征增强链通过自身的拓展来加深网络深度,提升特征提取能力。链式学习网络由于具有良好的深度堆叠特性,可以获取丰富的边缘特征信息,提高分割精度。在MS COCO和Cityscapes数据集上的实验结果表明,本文提出的实例特征深度链式学习全景分割网络在分割精度上优于现存同类方法,与全景分割网络常用的Mask RCNN实例分割结构相比,分割准确率最高提升了0.94%。
A novel deep instance feature chain learning network for panoptic segmentation (INFNet) was developed to solve the problem of failure of target boundary segmentation caused by insufficient instant feature extraction in panoptic segmentation. This network consisted of a basic chain unit, whose functions were divided into two types, feature holding chain and feature enhancement chain, based on the different methods of processing feature information by the unit structure. The feature-holding chain represented the input stage of the extraction of a chain network feature, in which the integrity of the input information was guaranteed, and then this feature was transmitted to the feature-enhancement chain structure. The feature-enhancement chain increased the network depth and improved the feature extraction ability through its extension. INFNet could obtain adequate edge feature information and improve segmentation accuracy, owing to the robust depth-stacking characteristics. The experiment results for the MS COCO and Cityscapes datasets showed that our INFNet was superior to similar existing methods in terms of segmentation accuracy. Compared to the Mask RCNN instance segmentation structure widely used in panoptic segmentation networks, the segmentation accuracy of INFNet increased by up to 0.94%.
HE K , GKIOXARI G , DOLLAR P , et al .. Mask R-CNN [C]. IEEE International Conference on Computer Vision . Piscataway, USA : IEEE , 2017 : 2980 - 2988 .
HE K , ZHANG X , REN S , et al .. Deep Residual Learning for Image Recognition [C]. IEEE Conference on Computer Vision and Pattern Recognition . Piscataway, USA : IEEE , 2016 : 770 - 778 .
KIRILLOV A , GIRSHICK R , HE K , et al .. Panoptic Feature Pyramid Networks [C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA : IEEE , 2019 : 6392 - 6401 .
LONG J , SHELHAMER E , DARRELL T . Fully convolutional networks for semantic segmentation [C]. IEEE Conference on Computer Vision and Pattern Recognition . Piscataway, USA : IEEE , 2015 : 3431 - 3440 .
CHEN L C , GEORGE PAPANDREOU , IASONAS KOKKINOS , 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 .
任凤雷 , 何昕 , 魏仲慧 , 等 . 基于DeepLabV3+与超像素优化的语义分割 [J]. 光学 精密工程 , 2019 , 27 ( 12 ): 2722 - 2729 .
REN F L , HE X , WEI ZH H , et al . . Semantic segmentation based on DeepLabV3+ and superpixel optimization [J]. Opt. Precision Eng. , 2019 , 27 ( 12 ): 2722 - 2729 . (in Chinese)
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 .
XIONG Y , LIAO R , ZHAO H , et al .. UPSNet: A Unified Panoptic Segmentation Network [C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA : IEEE , 2019 : 8810 - 8818 .
LIU H , PENG C , YU C , et al . An End-To-End Network for Panoptic Segmentation [C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA : IEEE , 2019 : 6165 - 6174 .
LI J , RAVENTOS A , BHARGAVA A , et al . . Learning to fuse things and stuff [J]. arXiv preprint arXiv: 1812 . 01192 v 2 .
LI Y , CHEN X , ZHU Z , et al .. Attention-Guided Unified Network for Panoptic Segmentation [C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA : IEEE , 2019 : 7019 - 7028 .
ZEILER M D , FERGUS R . Visualizing and Understanding Convolutional Neural Networks [C]. European Conference on Computer Vision . Berlin , Germany: Srpringer , 2014 : 818 - 833 .
TAN M , LE Q V . EfficientNet: Rethinking model scaling for convolutional neural networks [C]. International Conference on Machine Learning , 2019 : 6105 - 6114 .
RIPLEY B D . Pattern Recognition and Neural Networks [M]. Cambridge, UK : Cambridge university press , 1996 .
NAIR V , HINTON G E . Rectified Linear Units Improve Restricted Boltzmann Machines [C]. International Conference on Machine Learning , 2010 : 807 - 814 .
LIN T Y , MAIRE M , ELONGIE SB , et al .. Microsoft COCO: Common Objects in Context [C]. European Conference on Computer Vision . Berlin, Germany : Springer , 2014 : 740 - 755 .
CORDTS M , OMRAN M , RANOS S , et al .. The Cityscapes Dataset for Semantic Urban Scene Understanding [C]. IEEE Conference on Computer Vision and Pattern Recognition . Piscataway, USA : IEEE , 2016 : 3213 - 3223 .
王建林 , 付雪松 , 黄展超 , 等 . 改进YOLOv2卷积神经网络的多类型合作目标检测 [J]. 光学 精密工程 , 2020 , 28 ( 1 ): 251 - 260 .
WANG J L , FU X S , HUANG ZH CH , et al . . Multi-type cooperative targets detection using improved YOLOv2 convolutional neural network [J]. Opt. Precision Eng. , 2020 , 28 ( 1 ): 251 - 260 . (in Chinese)
董潇潇 , 何小海 , 吴晓红 , 等 . 基于注意力掩模融合的目标检测算法 [J]. 液晶与显示 , 2019 , 34 ( 8 ): 825 - 833 .
DONG X X , HE X H , WU X H , et al . . Object detection algorithm based on attention mask fusion [J]. Chinese Journal of Liquid Crystals and Displays , 2019 , 34 ( 8 ): 825 - 833 . (in Chinese)
KIRILLOV A , HE K , GIRSHICK R , et al .. Panoptic Segmentation [C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA : IEEE , 2019 : 9396 - 9405 .
YANG T J , COLLINS M D , ZHU Y , et al . . DeeperLab: Single-shot image parser [J]. arXiv preprint arXiv: 1902 . 05093 v 2 .
0
浏览量
634
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构