Real‐time multi‐window stereo matching algorithm with fuzzy logic
Abstract Stereo matching obtains a depth map called a disparity map that indicates or shows the positions of the objects in a scene. To estimate a disparity map, the most popular trend consists of comparing two images (left‐right) from two different points from the same scene. Unfortunately, small w...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-04-01
|
| Series: | IET Computer Vision |
| Online Access: | https://doi.org/10.1049/cvi2.12031 |
| _version_ | 1798037184376209408 |
|---|---|
| author | Héctor‐Daniel Vázquez‐Delgado Madaín Pérez‐Patricio Abiel Aguilar‐González Miguel‐Octavio Arias‐Estrada Marco‐Antonio Palacios‐Ramos Jorge Luis Camas‐Anzueto Antonio Pérez‐Cruz Sabino Velázquez‐Trujillo |
| author_facet | Héctor‐Daniel Vázquez‐Delgado Madaín Pérez‐Patricio Abiel Aguilar‐González Miguel‐Octavio Arias‐Estrada Marco‐Antonio Palacios‐Ramos Jorge Luis Camas‐Anzueto Antonio Pérez‐Cruz Sabino Velázquez‐Trujillo |
| author_sort | Héctor‐Daniel Vázquez‐Delgado |
| collection | DOAJ |
| description | Abstract Stereo matching obtains a depth map called a disparity map that indicates or shows the positions of the objects in a scene. To estimate a disparity map, the most popular trend consists of comparing two images (left‐right) from two different points from the same scene. Unfortunately, small window sizes are suitable to preserve the edges, while large window sizes are required in homogeneous areas. To solve this problem, in this article, a novel real‐time stereo matching algorithm embedded in an FPGA is proposed. The approach consists of estimating disparity maps with different window sizes by using the sum of absolute differences (SAD) as a local correlation metric. Once the disparity maps are obtained, the left‐right consistency for each window size is computed. At the end of this stage, the centre pixel deviation is estimated through a 5 × 5 window and the Sobel gradient is extracted from the left image. Finally, both parameters are processed by a Fuzzy Inference System (FIS), which combines the calculated disparities and generates a final disparity map. An architecture embedded in FPGA is established and hardware acceleration strategies are discussed. Experimental results demonstrated that this algorithmic formulation provides promising results compared with the current state of the art. |
| first_indexed | 2024-04-11T21:23:07Z |
| format | Article |
| id | doaj.art-84e5a7af9ca049d29448c76ed7bb7792 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-04-11T21:23:07Z |
| publishDate | 2021-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-84e5a7af9ca049d29448c76ed7bb77922022-12-22T04:02:32ZengWileyIET Computer Vision1751-96321751-96402021-04-0115320822310.1049/cvi2.12031Real‐time multi‐window stereo matching algorithm with fuzzy logicHéctor‐Daniel Vázquez‐Delgado0Madaín Pérez‐Patricio1Abiel Aguilar‐González2Miguel‐Octavio Arias‐Estrada3Marco‐Antonio Palacios‐Ramos4Jorge Luis Camas‐Anzueto5Antonio Pérez‐Cruz6Sabino Velázquez‐Trujillo7Tecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoTecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoTecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoInstituto Nacional de Astrofísica Óptica y Electrónica Puebla MéxicoTecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoTecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoTecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoTecnológico Nacional de México/IT de Tuxtla Gutiérrez Tuxtla Gutiérrez Chiapas MéxicoAbstract Stereo matching obtains a depth map called a disparity map that indicates or shows the positions of the objects in a scene. To estimate a disparity map, the most popular trend consists of comparing two images (left‐right) from two different points from the same scene. Unfortunately, small window sizes are suitable to preserve the edges, while large window sizes are required in homogeneous areas. To solve this problem, in this article, a novel real‐time stereo matching algorithm embedded in an FPGA is proposed. The approach consists of estimating disparity maps with different window sizes by using the sum of absolute differences (SAD) as a local correlation metric. Once the disparity maps are obtained, the left‐right consistency for each window size is computed. At the end of this stage, the centre pixel deviation is estimated through a 5 × 5 window and the Sobel gradient is extracted from the left image. Finally, both parameters are processed by a Fuzzy Inference System (FIS), which combines the calculated disparities and generates a final disparity map. An architecture embedded in FPGA is established and hardware acceleration strategies are discussed. Experimental results demonstrated that this algorithmic formulation provides promising results compared with the current state of the art.https://doi.org/10.1049/cvi2.12031 |
| spellingShingle | Héctor‐Daniel Vázquez‐Delgado Madaín Pérez‐Patricio Abiel Aguilar‐González Miguel‐Octavio Arias‐Estrada Marco‐Antonio Palacios‐Ramos Jorge Luis Camas‐Anzueto Antonio Pérez‐Cruz Sabino Velázquez‐Trujillo Real‐time multi‐window stereo matching algorithm with fuzzy logic IET Computer Vision |
| title | Real‐time multi‐window stereo matching algorithm with fuzzy logic |
| title_full | Real‐time multi‐window stereo matching algorithm with fuzzy logic |
| title_fullStr | Real‐time multi‐window stereo matching algorithm with fuzzy logic |
| title_full_unstemmed | Real‐time multi‐window stereo matching algorithm with fuzzy logic |
| title_short | Real‐time multi‐window stereo matching algorithm with fuzzy logic |
| title_sort | real time multi window stereo matching algorithm with fuzzy logic |
| url | https://doi.org/10.1049/cvi2.12031 |
| work_keys_str_mv | AT hectordanielvazquezdelgado realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT madainperezpatricio realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT abielaguilargonzalez realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT migueloctavioariasestrada realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT marcoantoniopalaciosramos realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT jorgeluiscamasanzueto realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT antonioperezcruz realtimemultiwindowstereomatchingalgorithmwithfuzzylogic AT sabinovelazqueztrujillo realtimemultiwindowstereomatchingalgorithmwithfuzzylogic |