Best Scanline Determination of Pushbroom Images for a Direct Object to Image Space Transformation Using Multilayer Perceptron
Ahooei Nezhad, Seyede Shahrzad ; Valadan Zoej, Mohammad Javad ; Khoshelham, Kourosh ; Ghorbanian, Arsalan LU ; Farnaghi, Mahdi ; Jamali, Sadegh LU
; Youssefi, Fahimeh
and Gheisari, Mehdi
(2024)
In Remote Sensing
16(15).
- Abstract
Working with pushbroom imagery in photogrammetry and remote sensing presents a fundamental challenge in object-to-image space transformation. For this transformation, accurate estimation of Exterior Orientation Parameters (EOPs) for each scanline is required. To tackle this challenge, Best Scanline Search or Determination (BSS/BSD) methods have been developed. However, the current BSS/BSD methods are not efficient for real-time applications due to their complex procedures and interpolations. This paper introduces a new non-iterative BSD method specifically designed for line-type pushbroom images. The method involves simulating a pair of sets of points, Simulated Control Points (SCOPs), and Simulated Check Points (SCPs), to train and... (More)
Working with pushbroom imagery in photogrammetry and remote sensing presents a fundamental challenge in object-to-image space transformation. For this transformation, accurate estimation of Exterior Orientation Parameters (EOPs) for each scanline is required. To tackle this challenge, Best Scanline Search or Determination (BSS/BSD) methods have been developed. However, the current BSS/BSD methods are not efficient for real-time applications due to their complex procedures and interpolations. This paper introduces a new non-iterative BSD method specifically designed for line-type pushbroom images. The method involves simulating a pair of sets of points, Simulated Control Points (SCOPs), and Simulated Check Points (SCPs), to train and test a Multilayer Perceptron (MLP) model. The model establishes a strong relationship between object and image spaces, enabling a direct transformation and determination of best scanlines. This proposed method does not rely on the Collinearity Equation (CE) or iterative search. After training, the MLP model is applied to the SCPs for accuracy assessment. The proposed method is tested on ten images with diverse landscapes captured by eight sensors, exploiting five million SCPs per image for statistical assessments. The Root Mean Square Error (RMSE) values range between 0.001 and 0.015 pixels across ten images, demonstrating the capability of achieving the desired sub-pixel accuracy within a few seconds. The proposed method is compared with conventional and state-of-the-art BSS/BSD methods, indicating its higher applicability regarding accuracy and computational efficiency. These results position the proposed BSD method as a practical solution for transforming object-to-image space, especially for real-time applications.
(Less)
- author
- Ahooei Nezhad, Seyede Shahrzad
; Valadan Zoej, Mohammad Javad
; Khoshelham, Kourosh
; Ghorbanian, Arsalan
LU
; Farnaghi, Mahdi
; Jamali, Sadegh
LU
; Youssefi, Fahimeh
and Gheisari, Mehdi
- organization
- publishing date
- 2024-08
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- best scanline determination (BSD), multilayer perceptron (MLP), object-to-image transformation, photogrammetry, pushbroom imagery
- in
- Remote Sensing
- volume
- 16
- issue
- 15
- article number
- 2787
- publisher
- MDPI AG
- external identifiers
-
- scopus:85200835992
- ISSN
- 2072-4292
- DOI
- 10.3390/rs16152787
- language
- English
- LU publication?
- yes
- id
- 3b3d7e9d-3364-4b9d-ba33-9cc31a0d061d
- date added to LUP
- 2024-09-09 14:27:04
- date last changed
- 2024-09-09 14:28:24
@article{3b3d7e9d-3364-4b9d-ba33-9cc31a0d061d,
abstract = {{<p>Working with pushbroom imagery in photogrammetry and remote sensing presents a fundamental challenge in object-to-image space transformation. For this transformation, accurate estimation of Exterior Orientation Parameters (EOPs) for each scanline is required. To tackle this challenge, Best Scanline Search or Determination (BSS/BSD) methods have been developed. However, the current BSS/BSD methods are not efficient for real-time applications due to their complex procedures and interpolations. This paper introduces a new non-iterative BSD method specifically designed for line-type pushbroom images. The method involves simulating a pair of sets of points, Simulated Control Points (SCOPs), and Simulated Check Points (SCPs), to train and test a Multilayer Perceptron (MLP) model. The model establishes a strong relationship between object and image spaces, enabling a direct transformation and determination of best scanlines. This proposed method does not rely on the Collinearity Equation (CE) or iterative search. After training, the MLP model is applied to the SCPs for accuracy assessment. The proposed method is tested on ten images with diverse landscapes captured by eight sensors, exploiting five million SCPs per image for statistical assessments. The Root Mean Square Error (RMSE) values range between 0.001 and 0.015 pixels across ten images, demonstrating the capability of achieving the desired sub-pixel accuracy within a few seconds. The proposed method is compared with conventional and state-of-the-art BSS/BSD methods, indicating its higher applicability regarding accuracy and computational efficiency. These results position the proposed BSD method as a practical solution for transforming object-to-image space, especially for real-time applications.</p>}},
author = {{Ahooei Nezhad, Seyede Shahrzad and Valadan Zoej, Mohammad Javad and Khoshelham, Kourosh and Ghorbanian, Arsalan and Farnaghi, Mahdi and Jamali, Sadegh and Youssefi, Fahimeh and Gheisari, Mehdi}},
issn = {{2072-4292}},
keywords = {{best scanline determination (BSD); multilayer perceptron (MLP); object-to-image transformation; photogrammetry; pushbroom imagery}},
language = {{eng}},
number = {{15}},
publisher = {{MDPI AG}},
series = {{Remote Sensing}},
title = {{Best Scanline Determination of Pushbroom Images for a Direct Object to Image Space Transformation Using Multilayer Perceptron}},
url = {{http://dx.doi.org/10.3390/rs16152787}},
doi = {{10.3390/rs16152787}},
volume = {{16}},
year = {{2024}},
}