Stacked objects segmentation based on depth image

Mingkang Zhou; Wei Song; Linyong Shen; Yanan Zhang

doi:10.1117/12.2501311

24 July 2018 Stacked objects segmentation based on depth image

Mingkang Zhou, Wei Song, Linyong Shen, Yanan Zhang

Proceedings Volume 10827, Sixth International Conference on Optical and Photonic Engineering (icOPEN 2018); 108271N (2018) https://doi.org/10.1117/12.2501311
Event: Sixth International Conference on Optical and Photonic Engineering (icOPEN 2018), 2018, Shanghai, China

Abstract

This paper presents an image segmentation method for stacked objects using Region-Scalable Fitting (RSF) and Spatial Kernel Fuzzy-C-Means (SKFCM) based on depth images. Firstly, RSF is used to detect contours of the objects’ area. Then, it can be judged whether there are stacked objects in each contour area by image histogram . For stacked objects, SKFCM algorithm is utilized for segmenting the stacked objects. Unlike the method based on RGB images, the proposed method is insensitive to background, texture and illumination due to the property of depth images that only contains depth information. Besides, the proposed method can effectively segment each object in the case of objects stacked, and determine the order of stacking which can be used for picking up by manipulator arm. The proposed method has been tested on different scenes with objects stacked. Experimental results have shown the effectiveness of the proposed method in segmenting stacked objects.

Citation Download Citation

Mingkang Zhou, Wei Song, Linyong Shen, and Yanan Zhang "Stacked objects segmentation based on depth image ", Proc. SPIE 10827, Sixth International Conference on Optical and Photonic Engineering (icOPEN 2018), 108271N (24 July 2018); https://doi.org/10.1117/12.2501311

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available