Prediction of thermal crossover based on imaging measurements over the diurnal cycle

Retief, S. J. P.; Willers, Cornelius J.; Wheeler, Mark

doi:10.1117/12.488358

Cited by 9 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Esta padronização permite não só comparar diretamente os diferentes horários do MODIS, como também confrontar os dois municípios em estudo. informação -ainda muito pouco utilizada (Dousset et al, 2007) A relação negativa entre Ts e o NDVI amplamente estudada no espaço urbano (e.g., Weng et al, 2004, Lopes, 2003Klock et al, 2012;Guo et al, 2015), apenas se verifica nos munícios (Nichol, 2005) -fenómeno que ocorre quando a assinatura do infravermelho de duas superfícies adjacentes se torna indistinguível (Retief et al, 2003). A substituição dos fluxos de calor latente pelos de calor sensível contribui diretamente para o aquecimento do ar na atmosfera urbana inferior (Lopes, 2003;Zaitchik et al, 2006).…”

Section: áRea De Estudounclassified

Comportamento da temperatura de superfície em Braga e Guimarães no decorrer da onda de calor de julho de 2010

Pinheiro

Laranjeira

Bandeira

2020

GOT

View full text Add to dashboard Cite

As projeções climáticas apontam para um aumento da duração, frequência e intensidade das ondas de calor no Sul da Europa. Nos espaços urbanos a situação é ainda mais problemática, por causa do efeito da ilha de calor que exacerba as suas consequências. Sem embargo, pouco se sabe do comportamento das áreas urbanas perante esta anomalia climática, e particularmente como evolui a temperatura das diferentes superfícies (impermeáveis ou não) nestes dias de calor extremo. Neste cômputo, recorre-se a uma abordagem integrada da Deteção Remota (i.e., MODIS-Terra e MODIS-Aqua) com os Sistema de Informação Geográfica para estudar o comportamento do ambiente térmico superficial nos municípios de Braga e de Guimarães no decorrer da onda de calor de 23 a 30 de julho de 2010. Os resultados evidenciam que as variações no ambiente térmico ocorrem de modo gradual, coincidindo o pico da temperatura de superfície (Ts) com o dia com a temperatura do ar mais elevada. O processamento integrado das imagens MODIS patenteia bem que o centro urbano de Braga constitui uma área crítica em todos os horários, ao passo que Guimarães aparece relativamente mais fresco. Concluindo, os efeitos da onda de calor são assimétricos do ponto de vista temporal (i.e., nos diferentes horários do MODIS) e espacial, em função da cobertura do solo e da posição topográfica. Atendendo ao atual contexto de alterações climáticas esta informação revela-se indispensável na definição de políticas urbanas indutoras de um território ambiental e socialmente resiliente.

show abstract

Section: áRea De Estudounclassified

Comportamento da temperatura de superfície em Braga e Guimarães no decorrer da onda de calor de julho de 2010

Pinheiro

Laranjeira

Bandeira

2020

GOT

View full text Add to dashboard Cite

show abstract

“…In order to ensure the target detection ability of the satellite-borne infrared hyperspectral sensor, efficient optimization of the imaging index is required based on the evaluation for target detection performance during integrative system design period. Michael T. Eismann used multidimensional signal-to-clutter ratio (SCR) for the first time to evaluate the detection ability of infrared hyperspectral sensor [1] during thermal crossover period [2] , and analyzed imaging index requirement of target detection from aircraft or tower [3,4] . However, the effects of atmosphere scattering and absorbing on signal radiated or reflected from objects under the condition of remote sensing was not considered, which could hardly guide the integrative design of satelliteborne infrared hyperspectral sensor.…”

Section: Introductionmentioning

confidence: 99%

Optimized integrative system design in satellite with MWIR/LWIR hyperspectral imaging based on multidimensional SCR and random forest learning

Liu,

Li,

Cao

et al. 2023

Target and Background Signatures IX

View full text Add to dashboard Cite

At present, aerospace development puts forward an urgent need for the integrative system design in satellite with MWIR/LWIR hyperspectral imaging spectrometer to provide the solution of target detection problem under the circumstance of weak thermal contrast between target and background at night, which can hardly be solved by traditional thermal infrared imaging system. In order to efficiently optimize the imaging index of the MWIR/LWIR hyperspectral imaging spectrometer, i.e. ground sample distance (GSD), spectral resolution, noise equivalent temperature difference (NETD), this paper proposed a novel optimized integrative system design method based on evaluation for target detection performance through multidimensional signal-to-clutter ratio (SCR). For assumed Gaussian target and background statistics, multidimensional SCR is the primary parameter describing the detection performance of a variety of detection algorithms based on the generalized maximum likelihood formulation, especially when the thermal contrast between target and background approach to zero. Therefore, we calculate the multidimensional SCR from MWIR/ LWIR hyperspectral images that are obtained through the simulation of satellite borne hyperspectral imaging chain with imaging indices, as the equivalent of detection performance. Based on the training datasets composed of multidimensional SCR and imaging indices, we can use random forest regression to identify the sensitivities of different imaging indices to multidimensional SCR. The sensitivity analysis of multidimensional SCR can help to determine the key to index optimization, guiding the integrative system design. More importantly, the relationship between the SCR and imaging indices can be predicted through random forest learning, which can be applied to the further global optimization of imaging indices with related optimization algorithms. With our proposed method, the integrative system design is closely associated to the demand for target detection task, meeting the satellite-borne detection performance requirements, and the manufacturing cost could be reduced due to the absence of excessive index optimization.

show abstract

“…Nevertheless, thermal cameras also have some shortcomings for pedestrian detection, such as sensing fewer detailed appearance features and background textures than visible cameras. Additionally, there is the so-called thermal crossover phenomenon where pedestrians might get indistinguishable from the background environment when their temperatures are similar [8]. Some typical examples could be found in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Transfer Learning Framework for Visible-Thermal Pedestrian Detection

Lyu

Heyer

Goossens

et al. 2022

Sensors

View full text Add to dashboard Cite

Dual cameras with visible-thermal multispectral pairs provide both visual and thermal appearance, thereby enabling detecting pedestrians around the clock in various conditions and applications, including autonomous driving and intelligent transportation systems. However, due to the greatly varying real-world scenarios, the performance of a detector trained on a source dataset might change dramatically when evaluated on another dataset. A large amount of training data is often necessary to guarantee the detection performance in a new scenario. Typically, human annotators need to conduct the data labeling work, which is time-consuming, labor-intensive and unscalable. To overcome the problem, we propose a novel unsupervised transfer learning framework for multispectral pedestrian detection, which adapts a multispectral pedestrian detector to the target domain based on pseudo training labels. In particular, auxiliary detectors are utilized and different label fusion strategies are introduced according to the estimated environmental illumination level. Intermediate domain images are generated by translating the source images to mimic the target ones, acting as a better starting point for the parameter update of the pedestrian detector. The experimental results on the KAIST and FLIR ADAS datasets demonstrate that the proposed method achieves new state-of-the-art performance without any manual training annotations on the target data.

show abstract

Prediction of thermal crossover based on imaging measurements over the diurnal cycle

Cited by 9 publications

References 2 publications

Comportamento da temperatura de superfície em Braga e Guimarães no decorrer da onda de calor de julho de 2010

Comportamento da temperatura de superfície em Braga e Guimarães no decorrer da onda de calor de julho de 2010

Optimized integrative system design in satellite with MWIR/LWIR hyperspectral imaging based on multidimensional SCR and random forest learning

An Unsupervised Transfer Learning Framework for Visible-Thermal Pedestrian Detection

Contact Info

Product

Resources

About