Pulsed thermography is a nondestructive method commonly used to explore anomalies in composite materials. This paper presents a procedure for the automated detection of defects in thermal images of ...composite materials obtained with pulsed thermography experiments. The proposed methodology is simple and novel as it is reliable in low-contrast and nonuniform heating conditions and does not require data preprocessing. Nonuniform heating correction and the gradient direction information combined with a local and global segmentation phase are used to analyze carbon fiber-reinforced plastic (CFRP) thermal images with Teflon inserts with different length/depth ratios. Additionally, a comparison between the actual depths and estimated depths of detected defects is performed. The performance of the nonuniform heating correction proposed method is superior to that obtained on the same CFRP sample analyzed with a deep learning algorithm and the background thermal compensation by filtering strategy.
The
Finite Difference Thermal Contrast
(FDTC) is a new technique based on the approximation to the discretization of the Fourier heat propagation model in 3D, in order to be applied on a sequence of ...infrared images to enhance contrast for automatic detection and characterization of flaws in composite slabs. This contrast enhancement is performed by the calculus of relative error between predicted and real temperature over the heated surface only and for each pixel, in such a way that defective regions will exhibit greater errors than sound ones. Thermal sequences from a simulated
Carbon Fiber Reinforced Plastic
(CFRP) slab with air-filled defects, and from a real CFRP slab sample with Teflon squared defects, are used to evaluate and compare the enhancement obtained from FDTC,
Normalized Contrast
(NC) and
Modified Differential Absolute Contrast
(m-DAC). In spite of the need of executing an additional background compensation in case of real slabs, results show that the proposed technique offers a better contrast between defects and background than the other techniques (about 33 % less residuary thermal non-uniformity with the adjusted version—FDTCa), mainly because of the more energy of the resulting thermal profiles. Also, as this technique does not estimate the temperature distribution along depth axis, but approximates temperature after a spatial step only, it can run faster than other thermal reconstruction methods like the classic
3D thermal filtering
.
En el caso de personas con limitación motriz de miembros superiores, los gestos faciales son la principal forma de comunicarse con el mundo. Sin embargo, las interfaces actuales basadas en gestos no ...tienen en cuenta la reducción de movilidad que la mayoría de las personas con limitación motriz experimentan durante sus periodos de recuperación. Como alternativa para superar esta limitación, se presenta una interfaz humana-computador basada en técnicas de visión por computador sobre dos tipos de imagen: la imagen del rostro capturada mediante webcam y la captura de pantalla de una aplicación de escritorio en primer plano. La primera imagen es utilizada para detectar, seguir y estimar la pose del rostro con el fin de desplazar y ejecutar comandos con el cursor; la segunda imagen es utilizada para lograr que los desplazamientos del cursor sean realizados a zonas específicas de interacción de la aplicación de escritorio. La interfaz es programada totalmente en Python 3.6 utilizando bibliotecas de código abierto y se ejecuta en segundo plano dentro del sistema operativo Windows. El desempeño de la interfaz se evalúa con videos de personas utilizando cuatro comandos de interacción con la aplicación WhatsApp versión de escritorio. Se encontró que la interfaz puede operar con varios tipos de iluminación, fondos, distancias a la cámara, posturas y velocidades de movimiento; la ubicación y el tamaño de la ventana de WhatsApp no afecta la efectividad de la interfaz. La interfaz opera a una velocidad de 1 Hz y utiliza el 35 % de la capacidad de un procesador Intel Core i5 y 1,5 GB de RAM para su ejecución lo que permite concebir esta solución en equipos de cómputo personales.
Las interfaces cerebro-computadora no invasivas basadas en EEG de imaginación motora (miBCI) prometen restaurar efectivamente el control motor a pacientes con discapacidades motoras, por ejemplo, ...aquellos con lesión de la médula espinal (LME). Sin embargo, todavía es necesario investigar las miBCI, con fines de rehabilitación, para este tipo de pacientes que utilizan dispositivos de adquisición de señales EEG de bajo costo, tales como Emotiv EPOC. En este trabajo, se describe en detalle y se comparan diez arquitecturas miBCI basadas en información de covarianza de señales EEG, adquiridas con Emotiv EPOC, para la decodificación de intención de mano abierta y cerrada en tres sujetos control y dos pacientes con LME cervical. Cuatro de estas diez miBCI usan información de covarianza para construir filtros espaciales y el resto usa la información covarianza como una representación directa de las señales EEG, permitiendo la manipulación directa mediante geometría de Riemann. Como resultado, se encontró que, a pesar de que todas las arquitecturas miBCI tienen una precisión general por encima del nivel de azar, las que utilizan la covarianza como representación directa de las señales EEG junto con clasificadores lineales, superan las miBCI que usan la covarianza para el filtrado espacial, tanto en sujetos de control como en pacientes con LME. Estos resultados sugieren un alto potencial de las miBCI basadas en la geometría de Riemann para la rehabilitación de pacientes con LME, utilizando dispositivos de adquisición de EEG de bajo costo.
Resumen El número de trabajos relacionados con Interfaces Cerebro-Computador (BCI, Brain-Computer Interface en inglés) directamente aplicados al proceso de rehabilitación de pacientes con lesiones de ...médula espinal está en aumento debido a la mejora en las técnicas de procesamiento digital de señales y reconocimiento de patrones que permiten relacionar las señales electroencefalográficas con acciones motoras. Los resultados preliminares de las pruebas de las BCI sobre sujetos reales permiten visualizar en un futuro relativamente cercano la inclusión de este tipo de herramientas en los protocolos de rehabilitación. Sin embargo, hay muchas barreras por resolver, principalmente las relacionadas con el aumento del desempeño y la generación de múltiples comandos naturales mediante interfaces cerebro-computador a partir de electroencefalografía superficial (EEG). En este trabajo se hace una revisión de los más importantes trabajos que muestran la evolución, el estado actual y las oportunidades de investigación alrededor de la temática de interfaces cerebro-computador en procesos de neurorrehabilitación de miembros superiores en pacientes con lesiones medulares.
This paper presents a thermal imaging dataset from composite material samples (carbon and glass fiber reinforced plastic) that were inspected by pulsed thermography with the goal of detecting and ...characterizing subsurface defective zones (Teflon inserts representing delaminations between plies). The pulsed thermography experiment was applied to 6 academic plates (inspected from both sides) all having the dimensions of 300 mm x 300 mm x 2 mm and same distribution of defects but made of different materials: three plates on carbon fiber-reinforced plastic (CFRP) and three plates made on glass fiber reinforced plastic (GFRP) specimens with three different geometries: planar, curved and trapezoidal. Each plate contains 25 inserts having length/depth ratios between 1.7 and 75. Two FX60 BALCAR photographic flashes (6.2 kJ per flash) were used to generate the heat pulse (2 ms duration), an X6900 FLIR infrared camera using ResearchIR software to record the thermal images and a custom-built software/control unit to synchronize data recording with pulse generation. Finally, the dataset proposed consists of 12 sequences of approximately 2000 images of 512 × 512 pixels each.
This paper presents the design and implementation of a novel technique for the recognition of four hand motions for real time response (flexion (FL), extension (EX), opening (OP) and closure (CL)) ...from electromyographic (EMG) signals generated from two forearm muscles: palmaris longus and extensor digitorum. The development of the work had two main stages: the low cost hardware for acquisition and conditioning of the EMG analog signals and the processing system for the identification and classification of the movement performed for real time response; the entire system was integrated in a hardware-software application using MATLAB and processing techniques for the discriminant analysis were performed. Three methods were evaluated for pattern recognition getting 98% recognition rates with the method proposed which had the best performance.
Thermographic image analysis is a subfield of diagnostic image processing aimed at detecting breast abnormalities in women at an early stage. It is a developing field of research and its ...effectiveness and scope require scientific assessment to be determined. An open-access dataset has been created for the scientific community to test and develop techniques for computational detection of normal and abnormal breast conditions from thermograms. This dataset is a valuable resource for researchers due to the scarcity of publicly available datasets of breast thermographic images. It includes thermographic images of the female chest area in three capture positions: anterior, left oblique and right oblique. The data set comes from 119 women ranging from 18 to 81 years of age. A table is attached to the dataset with the diagnosis of breast pathology, showing that 84 patients had benign pathology and 35 patients had malignant pathology. The diagnoses of women with healthy breast pathology are not included.
Visual tracking of objects is a fundamental technology for industry 4.0, allowing the integration of digital content and real-world objects. The industrial operation known as manual cargo packing can ...benefit from the visual tracking of objects. No dataset exists to evaluate the visual tracking algorithms on manual packing scenarios. To close this gap, this article presents 6D-ViCuT, a dataset of images, and 6D pose ground truth of cuboids in a manual packing operation in intralogistics. The initial release of the dataset comprehends 28 sessions acquired in a space that rebuilds a manual packing zone: indoors, area of (6 × 4 × 2) m3, and warehouse illumination. The data acquisition experiment involves capturing images from fixed and mobile RGBD devices and a motion capture system while an operator performs a manual packing operation. Each session contains between 6 and 18 boxes from an available set of 10 types, with each type varying in height, width, depth, and texture. Each session had a duration in the range of 1 to 5 minutes. Each session exhibits operator speed and box type differences (box texture, size heterogeneity, occlusion).
This article presents a dataset of thermographic images of terrain with antipersonnel mines to identify the presence or absence of these artifacts using machine learning and artificial vision ...techniques. The dataset has 2700 thermographic images acquired at different heights, using a Zenmuse XT infrared camera (7-13 µm), embedded in the DJI Matrice 100 drone. The data acquisition experiment consists of capturing aerial infrared images of a terrain where elements with characteristics similar to antipersonnel mines type legbreaker were buried. The mines were planted in the ground between 0 cm and 10 cm deep and were spread over an area of 10 m x 10 m. The drone used a flight protocol that set the trajectory, the time of the flight, the acquisition height, and the image sampling frequency. This dataset was used in “Detection of “legbreaker” antipersonnel landmines by analysis of aerial thermographic images of the soil” 7.