28. September - 2. Oktober 2020

Werner, Martin; Dax, Gabriel; Laass, Moritz

doi:10.18420/inf2020_95

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a more general approach of harvesting OSM data as training data for specific and even sparse geospatial objects (e.g., WWTP) is still needed. As for the latter challenge, given the rapid advances of geospatial artificial intelligence (GeoAI) models and methods ( Zhu et al, 2017 , Werner et al, 2021 ), object detection from RS data with deep learning has attracted substantial attention in both academia ( Wu et al, 2021 ) and industrial communities ( Sirko et al, 2021 ). Despite current achievements, however, determining how best to extend the state-of-the-art deep learning models for effective joint learning from multimodal RS data sources in an end-to-end manner remains an open topic.…”

Section: Introductionmentioning

confidence: 99%

Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection

Zech

Hong

et al. 2022

International Journal of Applied Earth Observation and Geoinfor

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection

Zech

Hong

et al. 2022

International Journal of Applied Earth Observation and Geoinfor

View full text Add to dashboard Cite

Compression Supports Spatial Deep Learning

Dax

Nagarajan

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In the last decades, the domain of spatial computing became more and more data-driven, especially when using remote sensing-based images. Furthermore, the satellites provide huge amounts of images, so the number of available datasets is increasing. This leads to the need for large storage requirements and high computational costs when estimating the label scene classification problem using deep learning. This consumes and blocks important hardware recourses, energy, and time. In this paper, the use of aggressive compression algorithms will be discussed to cut the wasted transmission and resources for selected land cover classification problems. To compare the different compression methods and the classification performance, the satellite image patches are compressed by two methods. The first method is the image quantization of the data to reduce the bit depth. Second is the lossy and lossless compression of images with the use of image file formats, such as JPEG and TIFF. The performance of the classification is evaluated with the use of convolutional neural networks like VGG16. The experiments indicated that not all remote sensing image classification problems improve their performance when taking the full available information into account. Moreover, compression can set the focus on specific image features, leading to fewer storage needs and a reduction of computing time with comparably small costs in terms of quality and accuracy. All in all, quantization and embedding into file formats do support convolutional neural networks to estimate the labels of images, by strengthening the features. The code is available at https://github.com/tum-bgd/compression-in-dl

show abstract

28. September - 2. Oktober 2020

Cited by 2 publications

References 0 publications

Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection

Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection

Compression Supports Spatial Deep Learning

Contact Info

Product

Resources

About