TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications

Superpixel segmentation aims to produce a consistent grouping of pixels. In recent years, the importance of superpixel segmentation has increased in computer vision since it offers useful primitives for extracting image features and simplifies the complexity of other image processing steps. In this...

Full description

Saved in:
Bibliographic Details
Main Authors: Abiel Aguilar-González, Alejandro Medina Santiago, Jorge Antonio Orozco Torres, J. A. de Jesús Osuna-Coutiño, Madaín Pérez Patricio, Néstor A. Morales-Navarro
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/24/11912
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106027317002240
author Abiel Aguilar-González
Alejandro Medina Santiago
Jorge Antonio Orozco Torres
J. A. de Jesús Osuna-Coutiño
Madaín Pérez Patricio
Néstor A. Morales-Navarro
author_facet Abiel Aguilar-González
Alejandro Medina Santiago
Jorge Antonio Orozco Torres
J. A. de Jesús Osuna-Coutiño
Madaín Pérez Patricio
Néstor A. Morales-Navarro
author_sort Abiel Aguilar-González
collection DOAJ
description Superpixel segmentation aims to produce a consistent grouping of pixels. In recent years, the importance of superpixel segmentation has increased in computer vision since it offers useful primitives for extracting image features and simplifies the complexity of other image processing steps. In this work, we propose the TurboPixels algorithm, whose main contribution is a hardware architecture for superpixel segmentation. Compared with previous approaches, our superpixels are computed without the need for iterative loops. This makes it possible to reduce algorithmic complexity and increases processing speed. The experimental results indicate that our approach enables a small-scale FPGA-based implementation suitable for embedded applications. In addition, the results demonstrate that robust superpixel segmentation can be achieved with processing speeds up to 86 times faster than in previous works in the current literature.
format Article
id doaj-art-e60c9f53b4374865870249facf64e988
institution Kabale University
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e60c9f53b4374865870249facf64e9882024-12-27T14:08:45ZengMDPI AGApplied Sciences2076-34172024-12-0114241191210.3390/app142411912TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded ApplicationsAbiel Aguilar-González0Alejandro Medina Santiago1Jorge Antonio Orozco Torres2J. A. de Jesús Osuna-Coutiño3Madaín Pérez Patricio4Néstor A. Morales-Navarro5Computer Science Department, Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), San Andrés Cholula 72840, MexicoComputer Science Department, Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), San Andrés Cholula 72840, MexicoIndustrial Engineering Department, Tecnológico Nacional de México, Instituto Tecnológico de Tuxtla Gutiérrez (ITTG), Tuxtla Gutiérrez 29050, MexicoMechatronics Engineering Department, Tecnológico Nacional de México, Instituto Tecnológico de Tuxtla Gutiérrez (ITTG), Tuxtla Gutiérrez 29050, MexicoMechatronics Engineering Department, Tecnológico Nacional de México, Instituto Tecnológico de Tuxtla Gutiérrez (ITTG), Tuxtla Gutiérrez 29050, MexicoMechatronics Engineering Department, Tecnológico Nacional de México, Instituto Tecnológico de Tuxtla Gutiérrez (ITTG), Tuxtla Gutiérrez 29050, MexicoSuperpixel segmentation aims to produce a consistent grouping of pixels. In recent years, the importance of superpixel segmentation has increased in computer vision since it offers useful primitives for extracting image features and simplifies the complexity of other image processing steps. In this work, we propose the TurboPixels algorithm, whose main contribution is a hardware architecture for superpixel segmentation. Compared with previous approaches, our superpixels are computed without the need for iterative loops. This makes it possible to reduce algorithmic complexity and increases processing speed. The experimental results indicate that our approach enables a small-scale FPGA-based implementation suitable for embedded applications. In addition, the results demonstrate that robust superpixel segmentation can be achieved with processing speeds up to 86 times faster than in previous works in the current literature.https://www.mdpi.com/2076-3417/14/24/11912image processingimage segmentationreal-time processingFPGAVHDL
spellingShingle Abiel Aguilar-González
Alejandro Medina Santiago
Jorge Antonio Orozco Torres
J. A. de Jesús Osuna-Coutiño
Madaín Pérez Patricio
Néstor A. Morales-Navarro
TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
Applied Sciences
image processing
image segmentation
real-time processing
FPGA
VHDL
title TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
title_full TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
title_fullStr TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
title_full_unstemmed TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
title_short TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
title_sort turbopixels a superpixel segmentation algorithm suitable for real time embedded applications
topic image processing
image segmentation
real-time processing
FPGA
VHDL
url https://www.mdpi.com/2076-3417/14/24/11912
work_keys_str_mv AT abielaguilargonzalez turbopixelsasuperpixelsegmentationalgorithmsuitableforrealtimeembeddedapplications
AT alejandromedinasantiago turbopixelsasuperpixelsegmentationalgorithmsuitableforrealtimeembeddedapplications
AT jorgeantonioorozcotorres turbopixelsasuperpixelsegmentationalgorithmsuitableforrealtimeembeddedapplications
AT jadejesusosunacoutino turbopixelsasuperpixelsegmentationalgorithmsuitableforrealtimeembeddedapplications
AT madainperezpatricio turbopixelsasuperpixelsegmentationalgorithmsuitableforrealtimeembeddedapplications
AT nestoramoralesnavarro turbopixelsasuperpixelsegmentationalgorithmsuitableforrealtimeembeddedapplications