2019
DOI: 10.3390/app9112357
|View full text |Cite
|
Sign up to set email alerts
|

Image Classification for Automated Image Cross-Correlation Applications in the Geosciences

Abstract: In Earth Science, image cross-correlation (ICC) can be used to identify the evolution of active processes. However, this technology can be ineffective, because it is sometimes difficult to visualize certain phenomena, and surface roughness can cause shadows. In such instances, manual image selection is required to select images that are suitably illuminated, and in which visibility is adequate. This impedes the development of an autonomous system applied to ICC in monitoring applications. In this paper, the un… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
12
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
1

Relationship

3
5

Authors

Journals

citations
Cited by 13 publications
(13 citation statements)
references
References 42 publications
1
12
0
Order By: Relevance
“…We used one image per day, when available, acquired in conditions of diffuse illumination to minimise the noise introduced by the shadows produced by direct light (Ahn and Box, 2010; Giordan and others, 2016). The shadow-related noise impeded the use of sub-daily time-lapses because it lowered the signal-to-noise ratio and increased the error (Dematteis and others, 2019). We estimated the ICC uncertainty by analysing the displacement measured on the stable surfaces (i.e., exposed bedrock).…”
Section: Methodsmentioning
confidence: 99%
“…We used one image per day, when available, acquired in conditions of diffuse illumination to minimise the noise introduced by the shadows produced by direct light (Ahn and Box, 2010; Giordan and others, 2016). The shadow-related noise impeded the use of sub-daily time-lapses because it lowered the signal-to-noise ratio and increased the error (Dematteis and others, 2019). We estimated the ICC uncertainty by analysing the displacement measured on the stable surfaces (i.e., exposed bedrock).…”
Section: Methodsmentioning
confidence: 99%
“…1. Image selection: We used images acquired within the same period of the year and at similar hours to guarantee a similar sun elevation and azimuth to minimize shadow changes that might introduce ZNCC artefacts (Dematteis et al 2019). Moreover, we discarded images with snow coverage or clouds, especially those nearby the landslide areas; we also discarded images with different orthorectifications.…”
Section: Digital Image Correlation For Coevent Displacement Estimationmentioning
confidence: 99%
“…In the last decades, the Planpincieux-Grandes Jorasses Glacier complex has become an open-air laboratory where innovative remote sensing techniques have been developed to monitor the glacier activity [6][7][8][9][10][11][12].…”
Section: Monitoring Campaignsmentioning
confidence: 99%
“…Section 3 is devoted to the Planpincieux and Grandes Jorasses glaciers (Mont Blanc massif) case study (Figure 1). In recent years, such a glacial complex has become an open-air laboratory where innovative and experimental monitoring systems have been developed [6][7][8][9][10][11][12]. Several practical examples of close-range remote sensing surveys will be described therein.…”
Section: Introductionmentioning
confidence: 99%