2022
DOI: 10.1016/j.isprsjprs.2022.08.018
|View full text |Cite
|
Sign up to set email alerts
|

A robust registration method for UAV thermal infrared and visible images taken by dual-cameras

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(3 citation statements)
references
References 62 publications
0
3
0
Order By: Relevance
“…The area-based approach fails to achieve location accuracy and robustness simultaneously, whereas the machine-learning-based method requires excessive computation [35][36][37]. To solve these problems, we referred to Meng et al (2022), who used the template matching with weights, multilevel local max-pooling and max index backtracking (TWMM) method to register the TIR & V images taken by the UAV equipped with a TIR & V sensor [38]. As a result, the correct matching rate for 1000 image groups was 96%.…”
Section: Registration and Automatic Identificationsmentioning
confidence: 99%
“…The area-based approach fails to achieve location accuracy and robustness simultaneously, whereas the machine-learning-based method requires excessive computation [35][36][37]. To solve these problems, we referred to Meng et al (2022), who used the template matching with weights, multilevel local max-pooling and max index backtracking (TWMM) method to register the TIR & V images taken by the UAV equipped with a TIR & V sensor [38]. As a result, the correct matching rate for 1000 image groups was 96%.…”
Section: Registration and Automatic Identificationsmentioning
confidence: 99%
“…The number of 1 represents the Hamming distance between two strings. The calculation formula is shown in Equation (10).…”
Section: Matching Of Feature Point Descriptorsmentioning
confidence: 99%
“…Among them, the SURF algorithm is an improved version of the SIFT (Scale Invariant Features Transform) algorithm; it has a better registration effect and improves the detection speed of feature points [8,9]. However, when processing largescale remote sensing images, its calculation time can reach the order of minutes, so reducing the calculation requirements is a very urgent task in aerial image processing [10,11].…”
Section: Introductionmentioning
confidence: 99%