Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network
One of the most commonly faced tasks in industrial robots is bin picking. Much work has been done in this related topic is about grasping and picking an object from the piled bin but ignoring the recognition step in their pipeline. In this paper, a recognition pipeline for industrial bin picking i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Politeknik Elektronika Negeri Surabaya
2022-06-01
|
| Series: | Emitter: International Journal of Engineering Technology |
| Subjects: | |
| Online Access: | https://emitter.pens.ac.id/index.php/emitter/article/view/704 |
| _version_ | 1811332167562690560 |
|---|---|
| author | Alfan Rizaldy Pratama Pratama Bima Sena Bayu Dewantara Dewi Mutiara Sari Dadet Pramadihanto |
| author_facet | Alfan Rizaldy Pratama Pratama Bima Sena Bayu Dewantara Dewi Mutiara Sari Dadet Pramadihanto |
| author_sort | Alfan Rizaldy Pratama Pratama |
| collection | DOAJ |
| description |
One of the most commonly faced tasks in industrial robots is bin picking. Much work has been done in this related topic is about grasping and picking an object from the piled bin but ignoring the recognition step in their pipeline. In this paper, a recognition pipeline for industrial bin picking is proposed. Begin with obtaining point cloud data from different manner of stacking objects there are well separated, well piled, and arbitrary piled. Then followed by segmentation using Density-based Spatial Clustering Application with Noise (DBSCAN) to obtain individual object data. The systems then use Convolutional Neural Network (CNN) that consume raw point cloud data. Performance of the segmentation reaches an impressive result in separating objects and network is evaluated under the varying style of stacking objects and give the result with average Accuracy, Recall, Precision, and F1-Score on 98.72%, 95.45%, 99.39%, and 97.33% respectively. Then the obtained model can be used for multiple objects recognition in one scene.
|
| first_indexed | 2024-04-13T16:32:42Z |
| format | Article |
| id | doaj.art-a97986e7958647b69134954898008b82 |
| institution | Directory Open Access Journal |
| issn | 2355-391X 2443-1168 |
| language | English |
| last_indexed | 2024-04-13T16:32:42Z |
| publishDate | 2022-06-01 |
| publisher | Politeknik Elektronika Negeri Surabaya |
| record_format | Article |
| series | Emitter: International Journal of Engineering Technology |
| spelling | doaj.art-a97986e7958647b69134954898008b822022-12-22T02:39:32ZengPoliteknik Elektronika Negeri SurabayaEmitter: International Journal of Engineering Technology2355-391X2443-11682022-06-0110110.24003/emitter.v10i1.704Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural NetworkAlfan Rizaldy Pratama Pratama0Bima Sena Bayu Dewantara1Dewi Mutiara Sari2Dadet Pramadihanto3Politeknik Elektronika Negeri SurabayaPoliteknik Elektronika Negeri SurabayaPoliteknik Elektronika Negeri SurabayaPoliteknik Elektronika Negeri Surabaya One of the most commonly faced tasks in industrial robots is bin picking. Much work has been done in this related topic is about grasping and picking an object from the piled bin but ignoring the recognition step in their pipeline. In this paper, a recognition pipeline for industrial bin picking is proposed. Begin with obtaining point cloud data from different manner of stacking objects there are well separated, well piled, and arbitrary piled. Then followed by segmentation using Density-based Spatial Clustering Application with Noise (DBSCAN) to obtain individual object data. The systems then use Convolutional Neural Network (CNN) that consume raw point cloud data. Performance of the segmentation reaches an impressive result in separating objects and network is evaluated under the varying style of stacking objects and give the result with average Accuracy, Recall, Precision, and F1-Score on 98.72%, 95.45%, 99.39%, and 97.33% respectively. Then the obtained model can be used for multiple objects recognition in one scene. https://emitter.pens.ac.id/index.php/emitter/article/view/704Industrial objectDensity-based clustering3D object recognitionConvolutional neural network |
| spellingShingle | Alfan Rizaldy Pratama Pratama Bima Sena Bayu Dewantara Dewi Mutiara Sari Dadet Pramadihanto Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network Emitter: International Journal of Engineering Technology Industrial object Density-based clustering 3D object recognition Convolutional neural network |
| title | Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network |
| title_full | Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network |
| title_fullStr | Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network |
| title_full_unstemmed | Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network |
| title_short | Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network |
| title_sort | density based clustering for 3d stacked pipe object recognition using directly given point cloud data on convolutional neural network |
| topic | Industrial object Density-based clustering 3D object recognition Convolutional neural network |
| url | https://emitter.pens.ac.id/index.php/emitter/article/view/704 |
| work_keys_str_mv | AT alfanrizaldypratamapratama densitybasedclusteringfor3dstackedpipeobjectrecognitionusingdirectlygivenpointclouddataonconvolutionalneuralnetwork AT bimasenabayudewantara densitybasedclusteringfor3dstackedpipeobjectrecognitionusingdirectlygivenpointclouddataonconvolutionalneuralnetwork AT dewimutiarasari densitybasedclusteringfor3dstackedpipeobjectrecognitionusingdirectlygivenpointclouddataonconvolutionalneuralnetwork AT dadetpramadihanto densitybasedclusteringfor3dstackedpipeobjectrecognitionusingdirectlygivenpointclouddataonconvolutionalneuralnetwork |