On the Use and Denoising of the Temporal Geometric Mean for SAR Time Series

Gasnier, Nicolas; Denis, Loïc; Tupin, Florence

doi:10.1109/lgrs.2021.3051936

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will consider more complex ways to include multi-temporal information in deep-neural networks. Other methods to compute the super-image can also be considered, see [16].…”

Section: Discussionmentioning

confidence: 99%

Exploiting Multi-Temporal Information for Improved Speckle Reduction of Sentinel-1 SAR Images by Deep Learning

Dalsasso

Meraoumia

Dénis

et al. 2021

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

Self Cite

View full text Add to dashboard Cite

Deep learning approaches show unprecedented results for speckle reduction in SAR amplitude images. The wide availability of multi-temporal stacks of SAR images can improve even further the quality of denoising. In this paper, we propose a flexible yet efficient way to integrate temporal information into a deep neural network for speckle suppression. Archives provide access to long time-series of SAR images, from which multi-temporal averages can be computed with virtually no remaining speckle fluctuations. The proposed method combines this multi-temporal average and the image at a given date in the form of a ratio image and uses a stateof-the-art neural network to remove the speckle in this ratio image. This simple strategy is shown to offer a noticeable improvement compared to filtering the original image without knowledge of the multi-temporal average.

show abstract

“…Future work will consider more complex ways to include multi-temporal information in deep-neural networks. Other methods to compute the super-image can also be considered, see [16].…”

Section: Discussionmentioning

confidence: 99%

Exploiting Multi-Temporal Information for Improved Speckle Reduction of Sentinel-1 SAR Images by Deep Learning

Dalsasso

Meraoumia

Dénis

et al. 2021

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS

Self Cite

View full text Add to dashboard Cite

show abstract

“…This has an impact on getting an accurate final value of the evaluation. The geometric mean is more stable than the arithmetic mean for extreme values and has a smaller coefficient of variation (Gasnier et al, 2021). Singh et al (2014) mentioned that the geometric mean is a good measure of the central tendency of a distribution with a power law.…”

Section: Methodsmentioning

confidence: 99%

A comfort evaluation method based on an intelligent car cockpit

Yang

Chen

Xing

et al. 2022

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

With the rapid development of automobiles, car cockpits are becoming more and more intelligent and advanced, and the intelligent requirements of automobile cockpits are gradually increasing. However, the real value of intelligence can only be realized when it makes passengers in a cockpit feel comfortable. In this study, seven factors that affect passenger comfort in intelligent cockpits are defined. Under these factors, a total of 33 evaluation indicators were developed. The core of the method was to determine the dissatisfaction indicators and degree of dissatisfaction in the intelligent cockpit by analyzing the relationship between people's perceived performance and their expectations. This method was used to evaluate the Tesla Model 3, and it was found in the results that the higher the degree of dissatisfaction with the indicator, the more subjective feedback it had, which in turn proved the effectiveness of the model. According to the degree of dissatisfaction, the indicators affecting comfort were also divided into three levels. This hierarchical division helps clarify which indicators should be prioritized for improvement. Generally, this method has a certain feasibility, which is helpful for the development and redesign of an intelligent car cockpit, and provides some reference strategies for other transportation fields.comfort, evaluation method, expectation, intelligent cockpit, the degree of dissatisfactionWith the rapid development of technology, the number of intelligent cars has also increased in recent years (Arena et al., 2020). Related research describes the intelligent car of the future as not only improving traffic safety like a robot but also further meeting people's demands by connecting to the Internet (Huang et al., 2016;James, 2012). Intelligent vehicles have become a trend now. Companies such as Tesla, Jaguar, and Google are now launching more intelligent vehicles from innovative materials and innovative technologies (Sun et al., 2021).However, for the vast majority of consumers, it is not the technology itself that cares about them, but how they feel in the cockpit (Park et al., 2019). The benefits of intelligent cars include increased safety, reduced need for infrastructure investment, improved fuel economy, and reduced congestion. But most importantly, they make passengers more relaxed and comfortable (Jorlöv et al., 2017). The real benefits of intelligent cars can only be realized when the human driver is comfortable in the intelligent cockpit and the interaction between the driver and the automated system is at a reasonable level (Helldin et al., 2013). Beggiato et al. (2019 believe that comfort plays an important role in the wide acceptance of intelligent vehicles. For some products such as smart cars, consumer satisfaction is a factor for business success (Park et al., 2019;Salomo et al., 2003). Industry and research are working to develop systems that can automatically adapt to maximize well-being (Olugbade et al., 2021). Therefore, making people feel comfortable is

show abstract

“…In physics, it expresses the relationship between the classical and the relativistic Doppler effect [13]. In image processing, a geometric filter based on the geometric mean is used for the reduction of speckle in radar images [16]. As a filter, the geometric mean weakens the contribution of high values heavily corrupted by multiplicative noise.…”

Section: Pythagorean Centrality Measuresmentioning

confidence: 99%

Pythagorean Centrality for Data Selection

Ziou¹

2023

Preprint

View full text Add to dashboard Cite

This paper provides an overview of the Pythagorean centrality measures, which are the arithmetic, geometric, and harmonic means. Both the evolution of their meaning through history and their geometrical interpretation are outlined. Relevant examples of use cases for each of them are introduced, spanning a variety of areas of knowledge. Their differences and similarities are explored. Finally, the issue of which mean to use in different situations in order to make advantageous predictions is addressed.

show abstract

On the Use and Denoising of the Temporal Geometric Mean for SAR Time Series

Cited by 8 publications

References 12 publications

Exploiting Multi-Temporal Information for Improved Speckle Reduction of Sentinel-1 SAR Images by Deep Learning

Exploiting Multi-Temporal Information for Improved Speckle Reduction of Sentinel-1 SAR Images by Deep Learning

A comfort evaluation method based on an intelligent car cockpit

Pythagorean Centrality for Data Selection

Contact Info

Product

Resources

About