Visual object recognition and pose estimation based on a deep semantic segmentation network

doi:10.1109/JSEN.2018.2870957

機構典藏 > College of Engineering > Graduate Institute & Department of Electrical Engineering > Journal Article > Item 987654321/115395

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/115395

Title:	Visual object recognition and pose estimation based on a deep semantic segmentation network
Authors:	Chien-Ming Lin;Chi-Yi Tsai;Yu-Cheng Lai;Shin-An Li;Ching-Chang Wong
Keywords:	Pose estimation;Three-dimensional displays;Robots;Visual perception;Image segmentation;Object recognition;Semantics
Date:	2018-11-15
Issue Date:	2018-10-25 12:10:22 (UTC+8)
Publisher:	IEEE Sensors Journal
Abstract:	In recent years, deep learning-based object recognition algorithms become emerging in robotic vision applications. This paper addresses the design of a novel deep learning-based visual object recognition and pose estimation system for a robot manipulator to handle random object picking tasks. The proposed visual control system consists of a visual perception module, an object pose estimation module, a data argumentation module, and a robot manipulator controller. The visual perception module combines deep convolution neural networks (CNNs) and a fully connected conditional random field layer to realize an image semantic segmentation function, which can provide stable and accurate object classification results in cluttered environments. The object pose estimation module implements a model-based pose estimation method to estimate the 3D pose of the target for picking control. In addition, the proposed data argumentation module automatically generates training data for training the deep CNN. Experimental results show that the proposed scene segmentation method used in the data argumentation module reaches a high accuracy rate of 97.10% on average, which is higher than other state-of-the-art segment methods. Moreover, with the proposed data argumentation module, the visual perception module reaches an accuracy rate over than 80% and 72% in the case of detecting and recognizing one object and three objects, respectively. In addition, the proposed model-based pose estimation method provides accurate 3D pose estimation results. The average translation and rotation errors in the three axes are all smaller than 0.52 cm and 3.95 degrees, respectively. These advantages make the proposed visual control system suitable for applications of random object picking and manipulation.
Relation:	IEEE Sensors Journal 18(22), p.1-11
DOI:	10.1109/JSEN.2018.2870957
Appears in Collections:	[Graduate Institute & Department of Electrical Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	164	View/Open
Visual object recognition and pose estimation based on a deep semantic segmentation network.pdf		2520Kb	Adobe PDF	1	View/Open

Loading...