Showing papers in "Infrared Physics & Technology in 2019"
••
TL;DR: A deep features and zero-phase component analysis (ZCA) based novel fusion framework is proposed that achieves better performance in both objective assessment and visual quality.
157 citations
••
TL;DR: In this paper, an overview on the applications of infrared thermography for the detection and characterisation of general metal loss in metallic materials is presented, which represents the advances of thermography applications specifically in metal loss/thickness variation measurement along the recent literature.
123 citations
••
TL;DR: In this article, the authors evaluated and compared different mathematical models to extract effective wavelengths for measurement of apple soluble solids content (SSC) based on near infrared (NIR) hyperspectral imaging over the spectral region of 1000-2500nm.
77 citations
••
TL;DR: Simulation results on real infrared images prove that the proposed algorithm not only compensates the AAGD disadvantages but also outperforms the recently published well-known small infrared target detection algorithms in both qualitative and quantitative perspectives.
69 citations
••
TL;DR: The proposed autonomous/intelligent post-processor that is capable of automatically detecting defects from given thermograms via a Convolutional Neural Networks coding, in tandem with a Deep Feed Forward Neural Networks algorithm to estimate the defect depth as well.
58 citations
••
TL;DR: In this article, a multi-linear discriminant analysis (MLDA) algorithm was developed to select the optimal wavelength and transform/reduce the classification features to improve the acquisition and processing speed of the hyperspectral images.
53 citations
••
TL;DR: In this article, the authors used a Computer Vision System (CVS) and spectral information from the Near Infrared (NIR) region by linear and nonlinear algorithms to identify and classify chicken with wooden breast anomaly.
49 citations
••
TL;DR: It can be seen from the results that the potatoes with different types of internal and external defects can be identified more accurately and quickly using H SI technology, and they can be classified based on recognition, which provides a theoretical basis for the application of HSI technology in the actual potatoes automatic sorting system.
49 citations
••
TL;DR: In this paper, the authors performed basic theoretical analysis to provide comparisons of different infrared materials, including InAs/InAsSb and metamorphic InSb, and reported experimental results on a mid-wavelength infrared detector and a focal plane array.
48 citations
••
TL;DR: The proposed approach focuses on the application of low-rank sparse principal component thermography (Sparse-PCT or SPCT) to assess the advantages and drawbacks of the method for non-destructive testing and demonstrates the considerable performance while the other methods failed.
46 citations
••
TL;DR: In this paper, the mean spectrum of each cucumber seed was extracted from hyperspectral images in 400-1000 and 1050-2500 nm separately and it was found that the reflectance spectra decreased as the moisture content of cucumber seeds increased in 10,2500-nm.
••
TL;DR: An efficient contact-point detection (CPD) scheme to detect contact-points from these complex infrared images, including the following three key components, including an improved RANSAC strategy, is presented.
••
TL;DR: In this paper, the authors presented a further development of FTIR spectroscopy focused to the discrimination between biodegradable and non-biodegradability polyethylene terephthalate (PET).
••
TL;DR: This paper proposes an infrared thermography-based NDT technique and a long short term memory recurrent neural network (LSTM-RNN) model which automatically classifies common defects occurring in honeycomb materials, including debonding, adhesive pooling, and liquid ingress.
••
TL;DR: Static NDT results and the further UAV research indicate that the UAV inspection approach could significantly reduce the inspection time, cost, and workload, whilst potentially increasing the probability of detection.
••
TL;DR: A nighttime FIR pedestrian dataset with the largest scale at present is introduced in this paper, which is called SCUT (South China University of Technology) dataset and shows that convolutional neural networks (CNN) based detectors obtained good performance on FIR image.
••
TL;DR: In this paper, the authors used principal component analysis (PCA) to classify wheat kernels into three categories of soft, medium, and hard using NIR hyperspectral imaging data.
••
TL;DR: The results show that near-infrared camera was the best for nighttime pedestrian detection when device cost and pedestrian imaging quality were considered and the optimized CNN model using self-learning softmax had a competitive accuracy and potential in real-time pedestrian recognition.
••
TL;DR: A robust fusion tracking method is proposed that exploits the abovementioned complementary information under a hybrid “tracking-by-detection” framework which consists of two tracking modules—the correlation filter based tracking (CFT) module and histogram basedtracking (HIST) module.
••
TL;DR: In this paper, the feasibility of using multi-cultivar model for quantitatively determining SSC in three cultivars of pears was observed based on visible-NIR spectroscopy.
••
TL;DR: Experimental results have indicated that the proposed fast target detection method guided by visual saliency can not only detect dim and small infrared targets with small amount of computation, high detection probability, and low false alarm rate, but also adapt to various complex backgrounds.
••
TL;DR: This study investigates the efficiency of Infrared Breast Thermography in early breast abnormality detection by doing Temperature based analysis, Intensity based analysis (IBA), and Tumor Location Matching (TLM).
••
TL;DR: Experimental results indicate that the proposed effective event identification method based on a random forest classifier has high accuracy for event identification with an average identification rate of 96.58%.
••
TL;DR: In this article, the authors investigated the efficacy of terahertz (THz) time-domain spectroscopy (TDS) imaging technology in detecting hidden defects in aircraft glass fiber (GF) sandwich composites.
••
TL;DR: The quantitative and qualitative performances of machine learning based approaches, which include segmentation based and feature extraction based methods, dimensionality reduction, and various classification schemes, as proposed in the literature are explored.
••
TL;DR: Unlike other meta-heuristic algorithms used for thresholding operations, MSA provides a higher performance regarding threshold quality and low computational cost and experimental data boosts the use of MSA for energy curve based thresholding with Masi entropy.
••
TL;DR: In this paper, the effects of pulsed laser process parameters including (pulse duration, frequency, current, focal length and welding speed) on the fusion zone temperature variation were investigated.
••
TL;DR: A new infrared ship detection method based on Convolutional Neural Networks (CNN) which is trained only with synthetic targets is proposed which achieves a higher accuracy than other classical ship detection methods.
••
TL;DR: A low-resolution thermopile sensor—GridEye is used to localize and track indoor multiple human targets and the experimental results have shown that multiple humans can be tracked well in the indoor environment.
••
TL;DR: In this article, the step heating contribution is recorded separately by mean of an additional measurement, which can effectively enhance the defect information and improve the thermal contrast between defect and non-defect areas when halogen lamps are used in combination with pulse-compression in reflection mode.