scholarly journals Appraisal of Low-Cost Pushbroom Hyper-Spectral Sensor Systems for Material Classification in Reflectance

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4398
Author(s):  
Steven Hobbs ◽  
Andrew Lambert ◽  
Michael J. Ryan ◽  
David J. Paull ◽  
John Haythorpe
Keyword(s):  
Near Infrared ◽  
Low Cost ◽  
Raspberry Pi ◽  
Vegetation Analysis ◽  
Processing Pipeline ◽  
Asteroid Exploration ◽  
Hyper Spectral ◽  
Infra Red ◽  
Scientific Results

Near infrared (NIR) remote sensing has applications in vegetation analysis as well as geological investigations. For extra-terrestrial applications, this is particularly relevant to Moon, Mars and asteroid exploration, where minerals exhibiting spectral phenomenology between 600 and 800 nm have been identified. Recent progress in the availability of processors and sensors has created the possibility of development of low-cost instruments able to return useful scientific results. In this work, two Raspberry Pi camera types and a panchromatic astronomy camera were trialed within a pushbroom sensor to determine their utility in measuring and processing the spectrum in reflectance. Algorithmic classification of all 15 test materials exhibiting spectral phenomenology between 600 and 800 nm was easily performed. Calibration against a spectrometer considers the effects of the sensor, inherent image processing pipeline and compression. It was found that even the color Raspberry Pi cameras that are popular with STEM applications were able to record and distinguish between most minerals and, contrary to expectations, exploited the infra-red secondary transmissions in the Bayer filter to gain a wider spectral range. Such a camera without a Bayer filter can markedly improve spectral sensitivity but may not be necessary.

Portable multispectral imaging system based on Raspberry Pi

Sensor Review ◽  
2017 ◽  
Vol 37 (3) ◽  
pp. 322-329 ◽  
Author(s):  
Nuria Lopez-Ruiz ◽  
Fernando Granados-Ortega ◽  
Miguel Angel Carvajal ◽  
Antonio Martinez-Olmos
Keyword(s):  
Near Infrared ◽  
Multispectral Imaging ◽  
Imaging System ◽  
Light Emitting Diode ◽  
Low Cost ◽  
Image Sensor ◽  
Raspberry Pi ◽  
Image Processing Algorithm ◽  
Content Type

Purpose In this work, the authors aim to present a compact low-cost and portable spectral imaging system for general purposes. The developed system provides information that can be used for a fast in situ identification and classification of samples based on the analysis of captured images. The connectivity of the instrument allows a deeper analysis of the images in an external computer. Design/methodology/approach The wavelength selection of the system is carried out by light multiplexing through a light-emitting diode panel where eight wavelengths covering the spectrum from ultraviolet (UV) to near-infrared region (NIR) have been included. The image sensor used is a red green blue – infrared (RGB-IR) micro-camera controlled by a Raspberry Pi board where a basic image processing algorithm has been programmed. It allows the visualization in an integrated display of the reflectance and the histogram of the images at each wavelength, including UV and NIRs. Findings The prototype has been tested by analyzing several samples in a variety of applications such as detection of damaged, over-ripe and sprayed fruit, classification of different type of plastic materials and determination of properties of water. Originality/value The designed system presents some advantages as being non-expensive and portable in comparison to other multispectral imaging systems. The low-cost and size of the camera module connected to the Raspberry Pi provides a compact instrument for general purposes.

scholarly journals Feasibility of Using VIS/NIR Spectroscopy and Multivariate Analysis for Pesticide Residue Detection in Tomatoes

Processes ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 196
Author(s):  
Araz Soltani Nazarloo ◽  
Vali Rasooli Sharabiani ◽  
Yousef Abbaspour Gilandeh ◽  
Ebrahim Taghinezhad ◽  
Mariusz Szymanek ◽  
...  
Keyword(s):  
Near Infrared ◽  
Cross Validation ◽  
Low Cost ◽  
Moving Average ◽  
Nir Spectroscopy ◽  
Control Treatment ◽  
Residue Detection ◽  
Non Destructive ◽  
Reflective Spectroscopy

The purpose of this work was to investigate the detection of the pesticide residual (profenofos) in tomatoes by using visible/near-infrared spectroscopy. Therefore, the experiments were performed on 180 tomato samples with different percentages of profenofos pesticide (higher and lower values than the maximum residual limit (MRL)) as compared to the control (no pesticide). VIS/near infrared (NIR) spectral data from pesticide solution and non-pesticide tomato samples (used as control treatment) impregnated with different concentrations of pesticide in the range of 400 to 1050 nm were recorded by a spectrometer. For classification of tomatoes with pesticide content at lower and higher levels of MRL as healthy and unhealthy samples, we used different spectral pre-processing methods with partial least squares discriminant analysis (PLS-DA) models. The Smoothing Moving Average pre-processing method with the standard error of cross validation (SECV) = 4.2767 was selected as the best model for this study. In addition, in the calibration and prediction sets, the percentages of total correctly classified samples were 90 and 91.66%, respectively. Therefore, it can be concluded that reflective spectroscopy (VIS/NIR) can be used as a non-destructive, low-cost, and rapid technique to control the health of tomatoes impregnated with profenofos pesticide.

scholarly journals Fast Object Detection Using Dimensional Based Features for Public Street Environments

Smart Cities ◽  
2020 ◽  
Vol 3 (1) ◽  
pp. 93-111 ◽  
Author(s):  
Ivan Matveev ◽  
Kirill Karpov ◽  
Ingo Chmielewski ◽  
Eduard Siemens ◽  
Aleksey Yurchenko
Keyword(s):  
Low Power ◽  
Near Infrared ◽  
Moving Objects ◽  
Infrared Camera ◽  
Machine Learning Algorithms ◽  
Frame Rate ◽  
Raspberry Pi ◽  
Real World Data ◽  
Iot Devices

Modern object recognition algorithms have very high precision. At the same time, they require high computational power. Thus, widely used low-power IoT devices, which gather a substantial amount of data, cannot directly apply the corresponding machine learning algorithms to process it due to the lack of local computational resources. A method for fast detection and classification of moving objects for low-power single-board computers is shown in this paper. The developed algorithm uses geometric parameters of an object as well as scene-related parameters as features for classification. The extraction and classification of these features is a relatively simple process which can be executed by low-power IoT devices. The algorithm aims to recognize the most common objects in the street environment, e.g., pedestrians, cyclists, and cars. The algorithm can be applied in the dark environment by processing images from a near-infrared camera. The method has been tested on both synthetic virtual scenes and real-world data. The research showed that a low-performance computing system, such as a Raspberry Pi 3, is able to classify objects with acceptable frame rate and accuracy.

scholarly journals Classification of functional Near Infra Red Signals with Machine Learning for Prediction of Epilepsy

10.29007/qqx8 ◽  
2020 ◽  
Author(s):  
Roberto Rosas Romero ◽  
Edgar Guevara
Keyword(s):  
Neural Network ◽  
Near Infrared ◽  
Epileptic Seizures ◽  
Prediction Performance ◽  
Support Vector ◽  
Seizure Prediction ◽  
Functional Near Infrared Spectroscopy ◽  
Infra Red ◽  
Epileptic Seizure Prediction

This work presents the classification of functional near-infrared spectroscopy (fNIRS) signals as a tool for prediction of epileptic seizures. The implementation of epilepsy prediction is accomplished by using two classifiers, namely a Support Vector Machine (SVM) for EEG-based prediction and a Convolutional Neural Network (CNN) for fNIRS-based prediction. Performance was measured by computing the Positive Predictive Value (PPV) and the Accuracy of a classifier within a 5-minute window adjacent and previous to the start of the seizure. The objectives of this research are to show that fNIRS-based epileptic seizure prediction yields results that are superior to those based on EEG and to show how deep learning is applied to the solution of this problem.

The Small Telescopes Performance in the Visual to Near Infrared Wavelengths

2015 ◽  
Vol 771 ◽  
pp. 129-132
Author(s):  
Dhani Herdiwijaya
Keyword(s):  
Optical System ◽  
Near Infrared ◽  
Focal Length ◽  
Low Cost ◽  
Sloan Digital Sky Survey ◽  
Modulation Transfer ◽  
Sky Survey ◽  
Infra Red ◽  
Infrared Wavelengths ◽  
Bar Test

Optical system is important and optimized for highly spatial resolution in certain wavelength bandwidth. We tested three small refractor telescopes with different aperture (two telescopes with 80 mm in diameter and one with 66 mm diameter) and focal-length (544 mm, 400 mm, and 389 mm, respectively) in order to know the resolution from visual to near infra red regions. The images of sinusoidal bar test chart were recorded from CCD detector. The reference filter of Sloan Digital Sky Survey (SDSS) is also attached in front of detector. The filters have the range of G (401-550 nm), R (555-695 nm), I (690-820 nm), Z (>820 nm), Z_s (826-920 nm), and Y (950-1058 nm). The last filter is referred to the limit of quantum efficiency of the detector. The maximum frequency for each pixel from each Modulation Transfer Function (MTF) was performed. We found that smaller diameter telescope is better resolution in the visual wavelength than the wider diameter and longer focal-length. In the near infra red region, the opposite results were obtained. The coating lens quality may affect the wavelength dependences. This study has advantages of selecting low cost and high resolution optical system for different applications, e.g. very young crescent moon observation, etc.

Multiparametric measurements of the lava lake at Masaya volcano

2020 ◽  
Author(s):  
Tom D. Pering ◽  
Tehnuka Ilanko ◽  
Thomas C. Wilkes ◽  
Leigh Stanger ◽  
Jon R. Willmott ◽  
...  
Keyword(s):  
Near Infrared ◽  
Low Cost ◽  
Lava Lake ◽  
Optical Absorption Spectroscopy ◽  
Raspberry Pi ◽  
High Time Resolution ◽  
Spherical Cap ◽  
Video Footage ◽  
Masaya Volcano ◽  
Gas Measurements

<p>The recent lava lake activity at Masaya volcano, Nicaragua, provided an ideal and rare moment to investigate dynamic and rapid magmatic processes. A multiparametric and low-cost approach which combined high time resolution gas, thermal, and video of the rapidly convecting lava lake was used. Gas measurements were conducted using DOAS (Differential Optical Absorption Spectroscopy) by traversing beneath the plume and Raspberry Pi ultraviolet (UV) cameras. Temperature measurements of the lake were made using a Raspberry Pi near infrared thermal camera approach. Video footage of the lava lake allowed the determination of the unusually rapid lake velocity, and crucially the generation of activity statistics such as location and frequency of the frequent small (spherical-cap) bubble bursts at the surface. Contemporaneously acquired UV and thermal datasets also allowed the assessment of a detected oscillation in the sulphur dioxide degassing data. By combing all these data streams, the unique fluid dynamics of lava lake activity at this location is highlighted.</p>

scholarly journals Measurement Strategies for the Classification of Edible Oils Using Low-Cost Miniaturised Portable NIR Instruments

Foods ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 2856
Author(s):  
Barbara Giussani ◽  
Alix Tatiana Escalante-Quiceno ◽  
Ricard Boqué ◽  
Jordi Riu
Keyword(s):  
Cost Analysis ◽  
Near Infrared ◽  
Edible Oils ◽  
Low Cost ◽  
Olive Oils ◽  
Different Types ◽  
Measurement Strategies

Miniaturised near-infrared (NIR) instruments have been increasingly used in the last few years, and they have become useful tools for many applications on different types of samples. The market already offers a wide variety of these instruments, each one having specific requirements for the correct acquisition of the instrumental signal. This paper presents the development and optimisation of different measuring strategies for two miniaturised NIR instruments in order to find the best measuring conditions for the rapid and low-cost analysis of olive oils. The developed strategies have been applied to the classification of different samples of olive oils, obtaining good results in all cases.

Sign in / Sign up

Export Citation Format

Share Document