Grid self-attention mechanism 3D object detection method based on raw point cloud
To enhance the feature representation of region of interest (RoI), which incorporated a spatial context encoding module and soft regression loss, a grid self-attention mechanism 3D object detection method based on raw point cloud, named GT3D, was proposed.The spatial context encoding module was desi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023189/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540049711136768 |
|---|---|
| author | Bin LU Yang SUN Zhenyu YANG |
| author_facet | Bin LU Yang SUN Zhenyu YANG |
| author_sort | Bin LU |
| collection | DOAJ |
| description | To enhance the feature representation of region of interest (RoI), which incorporated a spatial context encoding module and soft regression loss, a grid self-attention mechanism 3D object detection method based on raw point cloud, named GT3D, was proposed.The spatial context encoding module was designed to effectively weight the local and spatial features of points through the attention mechanism, considering the contribution of different point cloud features for a more accurate feature representation.The soft regression loss was introduced to address label ambiguity arising during the data annotation phase.Experiments conducted on the public KITTI 3D object detection dataset demonstrate that the proposed method achieves significant improvements in detection accuracy compared to other publicly available point cloud-based 3D object detection methods.The detection results of the test set are submitted to the official KITTI server for public evaluation, achieving detection accuracies of 91.45%, 82.76%, and 79.74% for easy, moderate, and hard difficulty levels in car detection, respectively. |
| format | Article |
| id | doaj-art-77e6e48292ba4323beef8c48d7576c83 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-77e6e48292ba4323beef8c48d7576c832025-01-14T06:23:30ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-10-0144728459388261Grid self-attention mechanism 3D object detection method based on raw point cloudBin LUYang SUNZhenyu YANGTo enhance the feature representation of region of interest (RoI), which incorporated a spatial context encoding module and soft regression loss, a grid self-attention mechanism 3D object detection method based on raw point cloud, named GT3D, was proposed.The spatial context encoding module was designed to effectively weight the local and spatial features of points through the attention mechanism, considering the contribution of different point cloud features for a more accurate feature representation.The soft regression loss was introduced to address label ambiguity arising during the data annotation phase.Experiments conducted on the public KITTI 3D object detection dataset demonstrate that the proposed method achieves significant improvements in detection accuracy compared to other publicly available point cloud-based 3D object detection methods.The detection results of the test set are submitted to the official KITTI server for public evaluation, achieving detection accuracies of 91.45%, 82.76%, and 79.74% for easy, moderate, and hard difficulty levels in car detection, respectively.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023189/3D object detectionpoint cloudself-attention mechanismspatial coordinate encodingsoft regression loss |
| spellingShingle | Bin LU Yang SUN Zhenyu YANG Grid self-attention mechanism 3D object detection method based on raw point cloud Tongxin xuebao 3D object detection point cloud self-attention mechanism spatial coordinate encoding soft regression loss |
| title | Grid self-attention mechanism 3D object detection method based on raw point cloud |
| title_full | Grid self-attention mechanism 3D object detection method based on raw point cloud |
| title_fullStr | Grid self-attention mechanism 3D object detection method based on raw point cloud |
| title_full_unstemmed | Grid self-attention mechanism 3D object detection method based on raw point cloud |
| title_short | Grid self-attention mechanism 3D object detection method based on raw point cloud |
| title_sort | grid self attention mechanism 3d object detection method based on raw point cloud |
| topic | 3D object detection point cloud self-attention mechanism spatial coordinate encoding soft regression loss |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023189/ |
| work_keys_str_mv | AT binlu gridselfattentionmechanism3dobjectdetectionmethodbasedonrawpointcloud AT yangsun gridselfattentionmechanism3dobjectdetectionmethodbasedonrawpointcloud AT zhenyuyang gridselfattentionmechanism3dobjectdetectionmethodbasedonrawpointcloud |