Edge-Supervised Linear Object Skeletonization for High-Speed Camera

This paper presents a high-speed skeletonization algorithm for detecting the skeletons of linear objects from their binary images. The primary objective of our research is to achieve rapid extraction of the skeletons from binary images while maintaining accuracy for high-speed cameras. The proposed...

Full description

Bibliographic Details
Main Authors: Taohan Wang, Yuji Yamakawa
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/23/12/5721
_version_ 1797592617665429504
author Taohan Wang
Yuji Yamakawa
author_facet Taohan Wang
Yuji Yamakawa
author_sort Taohan Wang
collection DOAJ
description This paper presents a high-speed skeletonization algorithm for detecting the skeletons of linear objects from their binary images. The primary objective of our research is to achieve rapid extraction of the skeletons from binary images while maintaining accuracy for high-speed cameras. The proposed algorithm uses edge supervision and a branch detector to efficiently search inside the object, avoiding unnecessary computation on irrelevant pixels outside the object. Additionally, our algorithm addresses the challenge of self-intersections in linear objects with a branch detection module, which detects existing intersections and initializes new searches on emerging branches when necessary. Experiments on various binary images, such as numbers, ropes, and iron wires, demonstrated the reliability, accuracy, and efficiency of our approach. We compared the performance of our method with existing skeletonization techniques, showing its superiority in terms of speed, especially for larger image sizes.
first_indexed 2024-03-11T01:56:40Z
format Article
id doaj.art-15e6e901d19543068bf8f2b9352d948a
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-03-11T01:56:40Z
publishDate 2023-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-15e6e901d19543068bf8f2b9352d948a2023-11-18T12:35:11ZengMDPI AGSensors1424-82202023-06-012312572110.3390/s23125721Edge-Supervised Linear Object Skeletonization for High-Speed CameraTaohan Wang0Yuji Yamakawa1Graduate School of Engineering, The University of Tokyo, Tokyo 113-8654, JapanInterfaculty Initiative in Information Studies, The University of Tokyo, Tokyo 113-8654, JapanThis paper presents a high-speed skeletonization algorithm for detecting the skeletons of linear objects from their binary images. The primary objective of our research is to achieve rapid extraction of the skeletons from binary images while maintaining accuracy for high-speed cameras. The proposed algorithm uses edge supervision and a branch detector to efficiently search inside the object, avoiding unnecessary computation on irrelevant pixels outside the object. Additionally, our algorithm addresses the challenge of self-intersections in linear objects with a branch detection module, which detects existing intersections and initializes new searches on emerging branches when necessary. Experiments on various binary images, such as numbers, ropes, and iron wires, demonstrated the reliability, accuracy, and efficiency of our approach. We compared the performance of our method with existing skeletonization techniques, showing its superiority in terms of speed, especially for larger image sizes.https://www.mdpi.com/1424-8220/23/12/5721high-speedskeletonizationcamerabinary imagelinear object
spellingShingle Taohan Wang
Yuji Yamakawa
Edge-Supervised Linear Object Skeletonization for High-Speed Camera
Sensors
high-speed
skeletonization
camera
binary image
linear object
title Edge-Supervised Linear Object Skeletonization for High-Speed Camera
title_full Edge-Supervised Linear Object Skeletonization for High-Speed Camera
title_fullStr Edge-Supervised Linear Object Skeletonization for High-Speed Camera
title_full_unstemmed Edge-Supervised Linear Object Skeletonization for High-Speed Camera
title_short Edge-Supervised Linear Object Skeletonization for High-Speed Camera
title_sort edge supervised linear object skeletonization for high speed camera
topic high-speed
skeletonization
camera
binary image
linear object
url https://www.mdpi.com/1424-8220/23/12/5721
work_keys_str_mv AT taohanwang edgesupervisedlinearobjectskeletonizationforhighspeedcamera
AT yujiyamakawa edgesupervisedlinearobjectskeletonizationforhighspeedcamera