Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network
Robots have become integral to modern society, taking over both complex and routine human tasks. Recent advancements in depth camera technology have propelled computer vision-based robotics into a prominent field of research. Many robotic tasks—such as picking up, carrying, and utilizing tools or ob...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iran University of Science and Technology
2024-11-01
|
| Series: | Iranian Journal of Electrical and Electronic Engineering |
| Subjects: | |
| Online Access: | http://ijeee.iust.ac.ir/article-1-3472-en.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550973085941760 |
|---|---|
| author | Haniye Merrikhi Hossein Ebrahimnezhad |
| author_facet | Haniye Merrikhi Hossein Ebrahimnezhad |
| author_sort | Haniye Merrikhi |
| collection | DOAJ |
| description | Robots have become integral to modern society, taking over both complex and routine human tasks. Recent advancements in depth camera technology have propelled computer vision-based robotics into a prominent field of research. Many robotic tasks—such as picking up, carrying, and utilizing tools or objects—begin with an initial grasping step. Vision-based grasping requires the precise identification of grasp locations on objects, making the segmentation of objects into meaningful components a crucial stage in robotic grasping. In this paper, we present a system designed to detect the graspable parts of objects for a specific task. Recognizing that everyday household items are typically grasped at certain sections for carrying, we created a database of these objects and their corresponding graspable parts. Building on the success of the Dynamic Graph CNN (DGCNN) network in segmenting object components, we enhanced this network to detect the graspable areas of objects. The enhanced network was trained on the compiled database, and the visual results, along with the obtained Intersection over Union (IoU) metrics, demonstrate its success in detecting graspable regions. It achieved a grand mean IoU (gmIoU) of 92.57% across all classes, outperforming established networks such as PointNet++ in part segmentation for this dataset. Furthermore, statistical analysis using analysis of variance (ANOVA) and T-test validates the superiority of our method. |
| format | Article |
| id | doaj-art-1a5d5868dd2a44aa8465a151bbd2f78d |
| institution | Kabale University |
| issn | 1735-2827 2383-3890 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Iran University of Science and Technology |
| record_format | Article |
| series | Iranian Journal of Electrical and Electronic Engineering |
| spelling | doaj-art-1a5d5868dd2a44aa8465a151bbd2f78d2025-01-09T18:47:15ZengIran University of Science and TechnologyIranian Journal of Electrical and Electronic Engineering1735-28272383-38902024-11-01204134146Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural NetworkHaniye Merrikhi0Hossein Ebrahimnezhad1 Computer Vision Res. Lab., Electrical Engineering Faculty, Sahand University of Technology, Tabriz, Iran. Computer Vision Res. Lab., Electrical Engineering Faculty, Sahand University of Technology, Tabriz, Iran. Robots have become integral to modern society, taking over both complex and routine human tasks. Recent advancements in depth camera technology have propelled computer vision-based robotics into a prominent field of research. Many robotic tasks—such as picking up, carrying, and utilizing tools or objects—begin with an initial grasping step. Vision-based grasping requires the precise identification of grasp locations on objects, making the segmentation of objects into meaningful components a crucial stage in robotic grasping. In this paper, we present a system designed to detect the graspable parts of objects for a specific task. Recognizing that everyday household items are typically grasped at certain sections for carrying, we created a database of these objects and their corresponding graspable parts. Building on the success of the Dynamic Graph CNN (DGCNN) network in segmenting object components, we enhanced this network to detect the graspable areas of objects. The enhanced network was trained on the compiled database, and the visual results, along with the obtained Intersection over Union (IoU) metrics, demonstrate its success in detecting graspable regions. It achieved a grand mean IoU (gmIoU) of 92.57% across all classes, outperforming established networks such as PointNet++ in part segmentation for this dataset. Furthermore, statistical analysis using analysis of variance (ANOVA) and T-test validates the superiority of our method.http://ijeee.iust.ac.ir/article-1-3472-en.pdfrobotic graspgrasp areapoint cloudpart segmentationdynamic graph cnn |
| spellingShingle | Haniye Merrikhi Hossein Ebrahimnezhad Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network Iranian Journal of Electrical and Electronic Engineering robotic grasp grasp area point cloud part segmentation dynamic graph cnn |
| title | Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network |
| title_full | Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network |
| title_fullStr | Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network |
| title_full_unstemmed | Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network |
| title_short | Grasp Area Detection for 3D Object using Enhanced Dynamic Graph Convolutional Neural Network |
| title_sort | grasp area detection for 3d object using enhanced dynamic graph convolutional neural network |
| topic | robotic grasp grasp area point cloud part segmentation dynamic graph cnn |
| url | http://ijeee.iust.ac.ir/article-1-3472-en.pdf |
| work_keys_str_mv | AT haniyemerrikhi graspareadetectionfor3dobjectusingenhanceddynamicgraphconvolutionalneuralnetwork AT hosseinebrahimnezhad graspareadetectionfor3dobjectusingenhanceddynamicgraphconvolutionalneuralnetwork |