Looking Farther in Parametric Scene Parsing with Ground and Aerial Imagery

Author(s):  
Raghava Modhugu ◽  
Harish Rithish Sethuram ◽  
Manmohan Chandraker ◽  
C.V. Jawahar
Keyword(s):  
Shore & Beach ◽  
2020 ◽  
pp. 3-13
Author(s):  
Richard Buzard ◽  
Christopher Maio ◽  
David Verbyla ◽  
Nicole Kinsman ◽  
Jacquelyn Overbeck

Coastal hazards are of increasing concern to many of Alaska’s rural communities, yet quantitative assessments remain absent over much of the coast. To demonstrate how to fill this critical information gap, an erosion and flood analysis was conducted for Goodnews Bay using an assortment of datasets that are commonly available to Alaska coastal communities. Measurements made from orthorectified aerial imagery from 1957 to 2016 show the shoreline eroded 0 to 15.6 m at a rate that posed no immediate risk to current infrastructure. Storm surge flood risk was assessed using a combination of written accounts, photographs of storm impacts, GNSS measurements, hindcast weather models, and a digital surface model. Eight past storms caused minor to major flooding. Wave impact hour calculations showed that the record storm in 2011 doubled the typical annual wave impact hours. Areas at risk of erosion and flooding in Goodnews Bay were identified using publicly available datasets common to Alaska coastal communities; this work demonstrates that the data and tools exist to perform quantitative analyses of coastal hazards across Alaska.


2020 ◽  
Vol 8 (8) ◽  
Author(s):  
Rumana Aktar ◽  
Dewi Endah Kharismawati ◽  
Kannappan Palaniappan ◽  
Hadi Aliakbarpour ◽  
Filiz Bunyak ◽  
...  
Keyword(s):  

2021 ◽  
Vol 564 ◽  
pp. 116906
Author(s):  
Yves Moussallam ◽  
Talfan Barnie ◽  
Álvaro Amigo ◽  
Karim Kelfoun ◽  
Felipe Flores ◽  
...  

2021 ◽  
Vol 13 (12) ◽  
pp. 2417
Author(s):  
Savvas Karatsiolis ◽  
Andreas Kamilaris ◽  
Ian Cole

Estimating the height of buildings and vegetation in single aerial images is a challenging problem. A task-focused Deep Learning (DL) model that combines architectural features from successful DL models (U-NET and Residual Networks) and learns the mapping from a single aerial imagery to a normalized Digital Surface Model (nDSM) was proposed. The model was trained on aerial images whose corresponding DSM and Digital Terrain Models (DTM) were available and was then used to infer the nDSM of images with no elevation information. The model was evaluated with a dataset covering a large area of Manchester, UK, as well as the 2018 IEEE GRSS Data Fusion Contest LiDAR dataset. The results suggest that the proposed DL architecture is suitable for the task and surpasses other state-of-the-art DL approaches by a large margin.


2020 ◽  
pp. 1-1
Author(s):  
Ke Gao ◽  
Hadi Ali Akbarpour ◽  
Joshua Fraser ◽  
Koundinya Nouduri ◽  
Filiz Bunyak ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document