ARTICLE
TITLE

Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network

SUMMARY

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.

PAGES
pp. 153 - 169

 Articles related

Dibya Ranjan Das Adhikary,Dheeresh Kumar Mallick    

In wireless sensor networks, clustering provides an effective way of organising the sensor nodes to achieve load balancing and increasing the lifetime of the network. Unequal clustering is an extension of common clustering that exhibits even better load ... see more


Guangchun Chen,Juan Hu,Hong Peng,Jun Wang,Xiangnian Huang    

Using spectral clustering algorithm is diffcult to find the clusters in the cases that dataset has a large difference in density and its clustering effect depends on the selection of initial centers. To overcome the shortcomings, we propose a novel spec... see more


Toga Aldila Cinderatama,Rinanza Zulmy Alhamri,Yoppy Yunhasnawa    

The implementation of network security infrastructure has been carried out, including the Intrusion Detection System (IDS). However, in its implementation there are still many who have not combined with Data Technology (Data Science) to get a more compre... see more


Fella Ulandari, Robert Kurniawan    

Kebakaran hutan merupakan salah satu kejadian bencana alam di Indonesia yang menyebabkan deforestasi dan berbagai kerugian pada aspek ekologi, ekonomi, dan sosial. Pencegahan kebakaran hutan dan lahan dapat dilakukan dengan menyediakan data dan informasi... see more


Hamzah Noori Fejer,Mohanaed Ajmi Falih    

In this paper, a new method has been proposed to eliminate the weaknesses in the previous algorithms. The proposed method for data density clustering is reduced in the mapping programming model. Our analysis result shows that misleading data was presente... see more