Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends
Deep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO). Nevertheless, the entry barriers for EO researchers are high due to the dense and rapidly developing field mainly driv...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/10/1667 |
| _version_ | 1797567199932579840 |
|---|---|
| author | Thorsten Hoeser Claudia Kuenzer |
| author_facet | Thorsten Hoeser Claudia Kuenzer |
| author_sort | Thorsten Hoeser |
| collection | DOAJ |
| description | Deep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO). Nevertheless, the entry barriers for EO researchers are high due to the dense and rapidly developing field mainly driven by advances in computer vision (CV). To lower the barriers for researchers in EO, this review gives an overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN). The survey starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019. Thereby, we highlight the connections between the most important CNN architectures and cornerstones coming from CV in order to alleviate the evaluation of modern DL models. Furthermore, we briefly outline the evolution of the most popular DL frameworks and provide a summary of datasets in EO. By discussing well performing DL architectures on these datasets as well as reflecting on advances made in CV and their impact on future research in EO, we narrow the gap between the reviewed, theoretical concepts from CV and practical application in EO. |
| first_indexed | 2024-03-10T19:39:15Z |
| format | Article |
| id | doaj.art-0819112878e1428ea73537d5582c2a24 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T19:39:15Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0819112878e1428ea73537d5582c2a242023-11-20T01:24:46ZengMDPI AGRemote Sensing2072-42922020-05-011210166710.3390/rs12101667Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent TrendsThorsten Hoeser0Claudia Kuenzer1German Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Münchner Straße 20, D-82234 Wessling, GermanyGerman Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Münchner Straße 20, D-82234 Wessling, GermanyDeep learning (DL) has great influence on large parts of science and increasingly established itself as an adaptive method for new challenges in the field of Earth observation (EO). Nevertheless, the entry barriers for EO researchers are high due to the dense and rapidly developing field mainly driven by advances in computer vision (CV). To lower the barriers for researchers in EO, this review gives an overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN). The survey starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019. Thereby, we highlight the connections between the most important CNN architectures and cornerstones coming from CV in order to alleviate the evaluation of modern DL models. Furthermore, we briefly outline the evolution of the most popular DL frameworks and provide a summary of datasets in EO. By discussing well performing DL architectures on these datasets as well as reflecting on advances made in CV and their impact on future research in EO, we narrow the gap between the reviewed, theoretical concepts from CV and practical application in EO.https://www.mdpi.com/2072-4292/12/10/1667artificial intelligenceAImachine learningdeep learningneural networksconvolutional neural networks |
| spellingShingle | Thorsten Hoeser Claudia Kuenzer Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends Remote Sensing artificial intelligence AI machine learning deep learning neural networks convolutional neural networks |
| title | Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends |
| title_full | Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends |
| title_fullStr | Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends |
| title_full_unstemmed | Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends |
| title_short | Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends |
| title_sort | object detection and image segmentation with deep learning on earth observation data a review part i evolution and recent trends |
| topic | artificial intelligence AI machine learning deep learning neural networks convolutional neural networks |
| url | https://www.mdpi.com/2072-4292/12/10/1667 |
| work_keys_str_mv | AT thorstenhoeser objectdetectionandimagesegmentationwithdeeplearningonearthobservationdataareviewpartievolutionandrecenttrends AT claudiakuenzer objectdetectionandimagesegmentationwithdeeplearningonearthobservationdataareviewpartievolutionandrecenttrends |