Semantic segmentation of 3D point cloud based on contextual attention CNN
Aiming at the under-segmentation of 3D point cloud semantic segmentation caused by the lack of contextual fine-grained information of the point cloud,an algorithm based on contextual attention CNN was proposed for 3D point cloud semantic segmentation.Firstly,the fine-grained features in local area o...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2020-07-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020128/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539267295182848 |
|---|---|
| author | Jun YANG Jisheng DANG |
| author_facet | Jun YANG Jisheng DANG |
| author_sort | Jun YANG |
| collection | DOAJ |
| description | Aiming at the under-segmentation of 3D point cloud semantic segmentation caused by the lack of contextual fine-grained information of the point cloud,an algorithm based on contextual attention CNN was proposed for 3D point cloud semantic segmentation.Firstly,the fine-grained features in local area of the point cloud were mined through the attention coding mechanism.Secondly,the contextual features between multi-scale local areas were captured by the contextual recurrent neural network coding mechanism and compensated with the fine-grained local features.Finally,the multi-head mechanism was used to enhance the generalization ability of the network.Experiments show that the mIoU of the proposed algorithm on the three standard datasets of ShapeNet Parts,S3DIS and vKITTI are 85.4%,56.7% and 38.1% respectively,which has good segmentation performance and good generalization ability. |
| format | Article |
| id | doaj-art-322e97e3bf0d40d5a81b0afeba3bc1e4 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2020-07-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-322e97e3bf0d40d5a81b0afeba3bc1e42025-01-14T07:19:45ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2020-07-014119520359736902Semantic segmentation of 3D point cloud based on contextual attention CNNJun YANGJisheng DANGAiming at the under-segmentation of 3D point cloud semantic segmentation caused by the lack of contextual fine-grained information of the point cloud,an algorithm based on contextual attention CNN was proposed for 3D point cloud semantic segmentation.Firstly,the fine-grained features in local area of the point cloud were mined through the attention coding mechanism.Secondly,the contextual features between multi-scale local areas were captured by the contextual recurrent neural network coding mechanism and compensated with the fine-grained local features.Finally,the multi-head mechanism was used to enhance the generalization ability of the network.Experiments show that the mIoU of the proposed algorithm on the three standard datasets of ShapeNet Parts,S3DIS and vKITTI are 85.4%,56.7% and 38.1% respectively,which has good segmentation performance and good generalization ability.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020128/3D point cloudsemantic segmentationcontextual attention convolution layerconvolutional neural networkdeep learning |
| spellingShingle | Jun YANG Jisheng DANG Semantic segmentation of 3D point cloud based on contextual attention CNN Tongxin xuebao 3D point cloud semantic segmentation contextual attention convolution layer convolutional neural network deep learning |
| title | Semantic segmentation of 3D point cloud based on contextual attention CNN |
| title_full | Semantic segmentation of 3D point cloud based on contextual attention CNN |
| title_fullStr | Semantic segmentation of 3D point cloud based on contextual attention CNN |
| title_full_unstemmed | Semantic segmentation of 3D point cloud based on contextual attention CNN |
| title_short | Semantic segmentation of 3D point cloud based on contextual attention CNN |
| title_sort | semantic segmentation of 3d point cloud based on contextual attention cnn |
| topic | 3D point cloud semantic segmentation contextual attention convolution layer convolutional neural network deep learning |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020128/ |
| work_keys_str_mv | AT junyang semanticsegmentationof3dpointcloudbasedoncontextualattentioncnn AT jishengdang semanticsegmentationof3dpointcloudbasedoncontextualattentioncnn |