Deep learning video analysis as measurement technique in physical models

Bieman, Joost P. den; Ridder, Menno P. de; Gent, Marcel R.A. van

doi:10.1016/j.coastaleng.2020.103689

Cited by 30 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The learning process can be more meaningful when integrating video into online learning (Kramer, König, Strauß, & Kaspar, 2020;Ye et al, 2020). The use of video in online learning is closely related to meeting the objective of improving student skills, especially in 21st century skills (Bieman, Ridder, & Gent, 2020). One of the skills that can be developed in improving the quality of human resources is the ability which consists of communication, critical thinking skills, collaboration, and creativity (Ahmed, 2020;Kim et al, 2019;Wang, Antonenko, & Dawson, 2020).…”

Section: The Effect Of Archiving Video Media and Online Learning On Students' Learning And Innovation Skills Simultaneouslymentioning

confidence: 99%

The Effectiveness of Archiving Videos and Online Learning on Student’s Learning and Innovation Skills

Indrawati¹

2021

INT J INSTRUCTION

View full text Add to dashboard Cite

This study to analyze the level of relationship and the effect of archiving video media and online learning on students' learning and innovation skills. The research method used was a quantitative approach with a questionnaire instrument. The questionnaire was distributed to vocational students who attended the archiving subject using archiving video media that had been previously developed by the researcher. The data analysis involved prerequisite test analysis including validity and reliability tests. Furthermore, the data had to meet one of the assumption tests, which was normality. The data were analyzed using a multiple linear regression model. The results showed that (1) the use of archiving video media and online learning had a positive and significant effect on students' learning and innovation skills simultaneously, (2) the use of archiving video media had a positive and significant effect on students' learning and innovation skills, and (3) online learning had a positive and significant impact on students' learning and innovation skills. These results showed that the use of archiving video media and online learning was proven to be able to affect students' learning and innovation skills so that they can become a reference for further research.

show abstract

Section: The Effect Of Archiving Video Media and Online Learning On Students' Learning And Innovation Skills Simultaneouslymentioning

confidence: 99%

The Effectiveness of Archiving Videos and Online Learning on Student’s Learning and Innovation Skills

Indrawati¹

2021

INT J INSTRUCTION

View full text Add to dashboard Cite

show abstract

“…Consequently, a state-of-the-art deep learning classification method was adopted, a CNN [7] which uses labelled images. Deep learning has recently been used for remote sensing in coastal research for surface elevation measurements [3].…”

Section: Algorithmmentioning

confidence: 99%

Assessment of Surf Amenity using Computer Vision with Convolutional Neural Networks to Track Wave Pockets

Thompson¹,

Watterson²,

Baldock³

2020

Australasian Fluid Mechanics Conference (AFMC)

View full text Add to dashboard Cite

Surf amenity can be significantly affected by coastal infrastructure and is a growing consideration for local governments. Quantitative assessment of the surf amenity of artificial reefs is also growing in interest. Surf amenity has been quantified using metrics derived from the surfable region near the breaking edge of a wave, defined as the 'wave pocket'. Wave pocket tracking software has been developed to track potential surfing rides using computer vision. This software enabled a surf amenity assessment of the Rainbow Bay (QLD) 'superbank' during Cyclone Eusi and the Palm Beach artificial reef. The produced data revealed new insights into the surf amenity of natural and artificial surf locations.

show abstract

“…In contrast with previous studies, the input to the machine learning alogrithm in this study is imagery. Other machine learning/coastal imaging studies have used machine learning as a measurement technique for hydrodynamic quantities such as significant wave height in laboratory settings [41] and in the field [42], and for morphological properties such as grain size [43] and laboratory bed level [44]. Machine learning has also been used for segmenting and classifying coastal images [45], improving shoreline detection [46], classifying wave breaking type [47], and predicting wave run-up [48].…”

Section: Introductionmentioning

confidence: 99%

Beach State Recognition Using Argus Imagery and Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

Nearshore morphology is a key driver in wave breaking and the resulting nearshore circulation, recreational safety, and nutrient dispersion. Morphology persists within the nearshore in specific shapes that can be classified into equilibrium states. Equilibrium states convey qualitative information about bathymetry and relevant physical processes. While nearshore bathymetry is a challenge to collect, much information about the underlying bathymetry can be gained from remote sensing of the surfzone. This study presents a new method to automatically classify beach state from Argus daytimexposure imagery using a machine learning technique called convolutional neural networks (CNNs). The CNN processed imagery from two locations: Narrabeen, New South Wales, Australia and Duck, North Carolina, USA. Three different CNN models are examined, one trained at Narrabeen, one at Duck, and one trained at both locations. Each model was tested at the location where it was trained in a self-test, and the single-beach models were tested at the location where it was not trained in a transfer-test. For the self-tests, skill (as measured by the F-score) was comparable to expert agreement (CNN F-values at Duck = 0.80 and Narrabeen = 0.59). For the transfer-tests, the CNN model skill was reduced by 24–48%, suggesting the algorithm requires additional local data to improve transferability performance. Transferability tests showed that comparable F-scores (within 10%) to the self-trained cases can be achieved at both locations when at least 25% of the training data is from each site. This suggests that if applied to additional locations, a CNN model trained at one location may be skillful at new sites with limited new imagery data needed. Finally, a CNN visualization technique (Guided-Grad-CAM) confirmed that the CNN determined classifications using image regions (e.g., incised rip channels, terraces) that were consistent with beach state labelling rules.

show abstract

Deep learning video analysis as measurement technique in physical models

Cited by 30 publications

References 18 publications

The Effectiveness of Archiving Videos and Online Learning on Student’s Learning and Innovation Skills

The Effectiveness of Archiving Videos and Online Learning on Student’s Learning and Innovation Skills

Assessment of Surf Amenity using Computer Vision with Convolutional Neural Networks to Track Wave Pockets

Beach State Recognition Using Argus Imagery and Convolutional Neural Networks

Contact Info

Product

Resources

About