Wyniki wyszukiwania - BazTech

1

Detection of human faces in thermal infrared images

Kowalski Marcin Ł., Grudzień Artur, Ciurapiński Wiesław

Metrology and Measurement Systems

|

2021

|

Vol. 28, nr 2

307--321

EN

The presented study concerns development of a facial detection algorithm operating robustly in the thermal infrared spectrum. The paper presents a brief review of existing face detection algorithms, describes the experiment methodology and selected algorithms. For the comparative study of facial detection three methods presenting three different approaches were chosen, namely the Viola-Jones, YOLOv2 and Faster-RCNN. All these algorithms were investigated along with various configurations and parameters and evaluated using three publicly available thermal face datasets. The comparison of the original results of various experiments for the selected algorithms is presented.

2

Comparison of emissivity retrieval methods from ASTER data using Fourier Transform Infrared Spectroscopy

Rolim Silvia Beatriz Alves, Veettil Bijeesh Kozhikkodan, Käfer Pâmela Suélen, Grondona Atilio Efrain Bica, Iglesias María Luján, Diaz Lucas Ribeiro, Hackmann Cristiano Lima

Acta Geophysica

|

2020

|

Vol. 68, no. 6

1867--1876

EN

Land surface emissivity retrieval is important for the remote identifcation of natural materials and can be used to identify the presence of silicate minerals. However, its estimation from passive sensors involves an undetermined function related to radiance data, which is infuenced by the atmosphere. We tested three methods for temperature emissivity retrieval in a dune feld composed of 99.53% quartz (SiO2) using Advanced Spaceborne Thermal Emission and Refection Radiometer (ASTER) imagery. The tested methods were the reference channel method (RCM), emissivity normalization method (ENM), and temperature emissivity separation (TES) method. An average quartz reference spectrum for the dune samples was calculated from an emissivity database based on temperature and used to evaluate the emissivity products of four ASTER images. In general, the three tested methods had a good approximation when analysed the emissivity reference curve, especially for longer wavelengths that ranged between 2 and 4% of emissivity. The RCM and ENM produced very similar results with the coefcients of determination (R2 ) as 0.9960 (RMSE 0.0184) and 0.9959 (RMSE 0.0185), respectively. RCM method presented superior results (R2 : 0.9960, RMSE: 0.0184), compared to the TES method (R2 : 0.9947, RMSE: 0.0197). The TES method showed good results only for shorter wavelengths and, hence, to identify specifc targets using ASTER data, such as silicate minerals, it is better to use the RCM method. The emissivity value selected at the saturation point of the spectral library based on temperature is fundamental in acquiring more reliable data.

3

Estimation of land surface temperature using Landsat satellite data: A case study of Mueang Maha Sarakham District, Maha Sarakham Province, Thailand for the years 2006 and 2015

Rotjanakusol T., Laosuwan T.

Przegląd Naukowy Inżynieria i Kształtowanie Środowiska

|

2018

|

Vol. 28, No. 4

401--409

EN

At present, the climate has constantly been changing, especially the increase in global average temperature that results in the risk of severe climatic conditions such as heat wave, drought and flood. The objective of this study is to estimate land surface temperature (LST) by applying Landsat satellite data in Mueang Maha Sarakham District, Maha Sarakham Province, Thailand. The study focuses on investigating the temperature changes for the years 2006 and 2015. The research was conducted by analyzing the satellite data in the thermal infrared band with a geo-informatics package software mutually with mathematical models. The operation results indicated that the average LST was at 26.28°C in 2006 and 27.15°C in 2015. In order to verify the accuracy of the data in this study, the results of the annual satellite data analysis were brought to find out a statistical correlation with the LST data from the Meteorological Station of Thai Meteorological Department (TMD). The results indicated that there was a correlation of the data at a high level in 2006 and 2015. The results of this study indicated that the satellite data analysis method is reliable and can be used to analyze, track, and verify data to predict surface temperatures effectively.

4

Badanie zmian kształtu, wielkości i temperatur wybranych elementów terenowych na termogramach w funkcji dystansu czasowego i odległościowego ich rejestracji

Lubecki A.

Archiwum Fotogrametrii, Kartografii i Teledetekcji

|

2006

|

Vol. 16

403--414

PL

W pracy przedstawiono rezultaty badań przeprowadzonych celem tworzenia obrazów stereotermalnych, pozyskiwanych z pojedynczej kamery termowizyjnej AGEMA LWB 880 łącznie z kamerą CCD dla orientacji. Termogramy wykonywano z różnych wysokości i odległości od badanych obiektów. Badanymi obiektami były elementy terenowe znajdujące się w zasięgu widzenia skanera termalnego. Do najczęściej występujących należą: budynki, pola uprawne, łąki, nieużytki, wody, pastwiska, lasy, zakrzaczenia i zadrzewienia, drogi. Stanowiska kamery znajdowały się na wysokościach stabilnych, stacjonarnych od 1.5 do 50 m npt. Kąt rejestracji celowej do normalnej wahał się w granicach od 10 do 45°. Rejestrowano obiekty terenowe w trzech rejonach kraju, koło Koszalina w sąsiedztwie brzegu morskiego, koło Olsztyna i w terenie górzystym w sąsiedztwie Szymbarka, koło Gorlic. Wszystkie termogramy i kolorowe obrazy wizyjne pozyskano w terenie przy udziale programu ,,Thermoscope”. Termogramy rejestrowano w różnych odstępach czasowych, w różnych porach dni słonecznych, w optymalnych warunkach atmosferycznych. Elementy terenowe stanowiące obiekty badawcze porównywano z tymi samymi obiektami zarejestrowanymi na sąsiednich termogramach, wykonanych z odpowiednim pokryciem podłużnym. Analizę badanych obiektów wykonano za pomocą wyżej wspomnianego programu. Podczas analizowania poszczególnych obiektów wykorzystano możliwości tworzenia histogramów liczbowych i graficznych oraz dane statystyczne. W efekcie badań stwierdzono, że występowanie większego dystansu czasowego między poszczególnymi rejestracjami termogramów, tym trudniej uzyskać stereotermogramy w odniesieniu do pozyskiwanych termogramów tylko w dni bezchmurne.

EN

A study was carried out to develop stereothermal images obtained from a single AGEMA LWB 880 type thermovisual camera in line with a CCD camera for orientation. Thermograms were made at varied heights and distances from the selected objects. The studied objects included field elements situated within the thermal scanner sight range such as buildings, crop fields, meadows, wastelands, water bodies, pastures, forests, bush and tree communities and roads. The camera was situated at stable and stationary sites from 1.5 to 50 m above the surface. The registration angle (target) to the optic normal ranged from 10 to 45° The registered objects were located in the following three regions of Poland: near Koszalin - by the seaside, near Olsztyn and in the mountainous area around Szymbark, near Gorlice. All the thermograms and colour video images were obtained in the field with the use of Thermoscope software. The thermograms were registered with different time delays, at different times of sunny days and under optimum weather conditions. The studied field elements registered on thermograms were compared with their images registered at neighbouring thermograms shot according to relevant longitudinal coverage. The studied objects were analysed with the above-mentioned software. Numerical and graphical histograms, as well as statistical data, were used in the analysis of the particular objects. Based on the results, the greater the time distance between the particular thermogram registrations was, the more difficult it was to obtain stereothermograms in relation to the studied thermograms on cloudless days.