A Comparison of Deep Learning Architectures for Semantic Mapping of Very High Resolution Images

2018 ◽  
Author(s):  
Qinghui Liu ◽  
Arnt-Borre Salberg ◽  
Robert Jenssen
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Semantic Mapping ◽  
High Resolution Images ◽  
Learning Architectures ◽  
Very High

scholarly journals Mask R-CNN and OBIA Fusion Improves the Segmentation of Scattered Vegetation in Very High-Resolution Optical Sensors

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 320
Author(s):  
Emilio Guirado ◽  
Javier Blanco-Sacristán ◽  
Emilio Rodríguez-Caballero ◽  
Siham Tabik ◽  
Domingo Alcaraz-Segura ◽  
...  
Keyword(s):  
High Resolution ◽  
Optical Sensors ◽  
Biotic Interactions ◽  
Relevant Information ◽  
Vegetation Monitoring ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Segmentation Methods ◽  
High Resolution Images ◽  
Very High

Vegetation generally appears scattered in drylands. Its structure, composition and spatial patterns are key controls of biotic interactions, water, and nutrient cycles. Applying segmentation methods to very high-resolution images for monitoring changes in vegetation cover can provide relevant information for dryland conservation ecology. For this reason, improving segmentation methods and understanding the effect of spatial resolution on segmentation results is key to improve dryland vegetation monitoring. We explored and analyzed the accuracy of Object-Based Image Analysis (OBIA) and Mask Region-based Convolutional Neural Networks (Mask R-CNN) and the fusion of both methods in the segmentation of scattered vegetation in a dryland ecosystem. As a case study, we mapped Ziziphus lotus, the dominant shrub of a habitat of conservation priority in one of the driest areas of Europe. Our results show for the first time that the fusion of the results from OBIA and Mask R-CNN increases the accuracy of the segmentation of scattered shrubs up to 25% compared to both methods separately. Hence, by fusing OBIA and Mask R-CNNs on very high-resolution images, the improved segmentation accuracy of vegetation mapping would lead to more precise and sensitive monitoring of changes in biodiversity and ecosystem services in drylands.

Hands Stencils in El Castillo Cave (Puente Viesgo, Cantabria, Spain). An Interdisciplinary Study

2021 ◽  
pp. 1-21
Author(s):  
Sergio Ripoll ◽  
Vicente Bayarri ◽  
Francisco J. Muñoz ◽  
Ricardo Ortega ◽  
Elena Castillo ◽  
...  
Keyword(s):  
High Resolution ◽  
Real Data ◽  
Digital Processing ◽  
The Other ◽  
Major Step ◽  
The People ◽  
High Resolution Images ◽  
Real Picture ◽  
Interdisciplinary Study ◽  
Very High

Our Palaeolithic ancestors did not make good representations of themselves on the rocky surfaces of caves and barring certain exceptions – such as the case of La Marche (found on small slabs of stone or plaquettes) or the Cueva de Ambrosio – the few known examples can only be referred to as anthropomorphs. As such, only hand stencils give us a real picture of the people who came before us. Hand stencils and imprints provide us with a large amount of information that allows us to approach not only their physical appearance but also to infer less tangible details, such as the preferential use of one hand over the other (i.e., handedness). Both new and/or mature technologies as well as digital processing of images, computers with the ability to process very high resolution images, and a more extensive knowledge of the Palaeolithic figures all help us to analyse thoroughly the hands in El Castillo cave. The interdisciplinary study presented here contributes many novel developments based on real data, representing a major step forward in knowledge about our predecessors.

scholarly journals Accelerating Super-Resolution and Visual Task Analysis in Medical Images

2020 ◽  
Vol 10 (12) ◽  
pp. 4282
Author(s):  
Ghada Zamzmi ◽  
Sivaramakrishnan Rajaraman ◽  
Sameer Antani
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Task Analysis ◽  
Multiple Scales ◽  
Medical Images ◽  
Computational Cost ◽  
Super Resolution ◽  
Visual Task ◽  
Learning Networks ◽  
High Resolution Images

Medical images are acquired at different resolutions based on clinical goals or available technology. In general, however, high-resolution images with fine structural details are preferred for visual task analysis. Recognizing this significance, several deep learning networks have been proposed to enhance medical images for reliable automated interpretation. These deep networks are often computationally complex and require a massive number of parameters, which restrict them to highly capable computing platforms with large memory banks. In this paper, we propose an efficient deep learning approach, called Hydra, which simultaneously reduces computational complexity and improves performance. The Hydra consists of a trunk and several computing heads. The trunk is a super-resolution model that learns the mapping from low-resolution to high-resolution images. It has a simple architecture that is trained using multiple scales at once to minimize a proposed learning-loss function. We also propose to append multiple task-specific heads to the trained Hydra trunk for simultaneous learning of multiple visual tasks in medical images. The Hydra is evaluated on publicly available chest X-ray image collections to perform image enhancement, lung segmentation, and abnormality classification. Our experimental results support our claims and demonstrate that the proposed approach can improve the performance of super-resolution and visual task analysis in medical images at a remarkably reduced computational cost.

Sign in / Sign up

Export Citation Format

Share Document