Journal
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
Volume 14, Issue -, Pages 9884-9898Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3112209
Keywords
Vegetation mapping; Spatial resolution; Feature extraction; Sensors; Satellites; Task analysis; Soil; Interband retrieval; multilabel classification; multilabel cross triplet loss; multimodal classification; Sentinel-2; land-cover classification
Categories
Funding
- Conservatoire National des Arts et Metiers (CNAM), Paris, France
Ask authors/readers for more resources
This article explores the capabilities of deep neural networks in capturing contextual information and investigating multispectral band properties from Sentinel-2 image patches. It groups bands based on spatial resolutions and proposes a classification and retrieval framework. By utilizing representation learning and a novel triplet-loss function, the framework shows marked improvements on the benchmarked BigEarthNet dataset.
Conventional remote sensing data analysistechniques have a significant bottleneck of operating on a selectively chosen small-scale dataset. Availability of an enormous volume of data demands handling large-scale, diverse data, which have been made possible with neural network-based architectures. This article exploits the contextual information capturing ability of deep neural networks, particularly investigating multispectral band properties from Sentinel-2 image patches. Besides, an increase in the spatial resolution often leads to nonlinear mixing of land-cover types within a target resolution cell. We recognize this fact and group the bands according to their spatial resolutions, and propose a classification and retrieval framework. We design a representation learning framework for classifying the multispectral data by first utilizing all the bands and then using the grouped bands according to their spatial resolutions. We also propose a novel triplet-loss function for multilabeled images and use it to design an interband group retrieval framework. We demonstrate its effectiveness over the conventional triplet-loss function. Finally, we present a comprehensive discussion of the obtained results. We thoroughly analyze the performance of the band groups on various land-cover and land-use areas from agro-forestry regions, water bodies, and human-made structures. Experimental results for the classification and retrieval framework on the benchmarked BigEarthNet dataset exhibit marked improvements over existing studies.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available