LULC Classification Performance of Supervised and Unsupervised Algorithms on UAV-Orthomosaics

Saponaro, Mirko; Tarantino, Eufemia

doi:10.1007/978-3-031-10545-6_22

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early works in quantifying landscape similarity in the optical remote sensing field relied on landscape metrics, and much of the work in this direction was conducted in the context of land use/land change (LULC) research [8][9][10][11]. Initially, partly because the resolution of available satellite images was very low and since feature extraction techniques based on advanced image processing and computer vision methods such as deep learning (DL) had yet to be developed and refined, several works [12][13][14] used distribution statistics (first-and second-order statistical summaries) as landscape similarity metrics (LMs).…”

Section: Introductionmentioning

confidence: 99%

Scalable Retrieval of Similar Landscapes in Optical Satellite Imagery Using Unsupervised Representation Learning

Karatsiolis,

Padubidri,

Kamilaris

2023

Remote Sensing

View full text Add to dashboard Cite

Global Earth observation is becoming increasingly important in understanding and addressing critical aspects of life on our planet, including environmental issues, natural disasters, sustainable development, and others. Finding similarities in landscapes may provide useful information regarding applying contiguous policies, by making similar decisions or learning from best practices for events and occurrences that previously occurred in similar landscapes in the past. However, current applications of similar landscape retrieval are limited by a moderate performance and the need for time-consuming and costly annotations. We propose splitting the similar landscape retrieval task into a set of smaller tasks that aim to identify individual concepts inherent to satellite images. Our approach relies on several models trained using unsupervised representation learning on Google Earth images to identify these concepts. We show the efficacy of matching individual concepts for retrieving landscape(s) similar to a user-selected satellite image of the geographical territory of the Republic of Cyprus. Our results demonstrate the benefits of breaking up the landscape similarity task into individual concepts closely related to remote sensing, instead of applying a single model targeting all underlying concepts.

show abstract