Object detection and image segmentation with deep learning on Earth Observation data: a review — part II: applications
Zitieren Sie bitte immer diese URN: urn:nbn:de:bvb:20-opus-213152
- In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensiveIn Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.…
Autor(en): | Thorsten Hoeser, Felix Bachofer, Claudia Kuenzer |
---|---|
URN: | urn:nbn:de:bvb:20-opus-213152 |
Dokumentart: | Artikel / Aufsatz in einer Zeitschrift |
Institute der Universität: | Philosophische Fakultät (Histor., philolog., Kultur- und geograph. Wissensch.) / Institut für Geographie und Geologie |
Sprache der Veröffentlichung: | Englisch |
Titel des übergeordneten Werkes / der Zeitschrift (Englisch): | Remote Sensing |
ISSN: | 2072-4292 |
Erscheinungsjahr: | 2020 |
Band / Jahrgang: | 12 |
Heft / Ausgabe: | 18 |
Aufsatznummer: | 3053 |
Originalveröffentlichung / Quelle: | Remote Sensing (2020) 12:18, 3053. https://doi.org/10.3390/rs12183053 |
DOI: | https://doi.org/10.3390/rs12183053 |
Allgemeine fachliche Zuordnung (DDC-Klassifikation): | 5 Naturwissenschaften und Mathematik / 52 Astronomie / 526 Mathematische Geografie |
Freie Schlagwort(e): | AI; CNN; artificial intelligence; convolutional neural networks; deep learning; earth observation; image segmentation; machine learning; neural networks; object detection |
Datum der Freischaltung: | 28.06.2022 |
Datum der Erstveröffentlichung: | 18.09.2020 |
Lizenz (Deutsch): | CC BY: Creative-Commons-Lizenz: Namensnennung 4.0 International |