Active three-dimensional(3-D) thermography combines 3-D shape and active thermography. Thus, it enables the provision of the intuitive thermographic inspection results for composite parts with a complex geometry. However, conventional 3-D thermography acquires thermographic information and 3-D shape through at least two independent sensors and requires complex cross-modal image registration algorithm based on the keypoint detection and matching. In this article, an active 3-D thermography system is proposed using only one thermal camera for moving objects. This system does not require an independent 3-D sensor while the thermal camera acts as the 3-D sensor. Nature behind that is that a mathematical model is proposed to unify the line scanning thermography and laser triangulation in the dynamic scanning process, taking a line laser as both heat excitation for active thermography and spatial coding for 3-D reconstruction. Furthermore, the model enables the feature-free registration of thermogram sequence and 3-D shape, so that the registration is fast and robust without keypoint features. The experiments on standard height specimens, 3-D printing glass fiber composites, and carbon fiber intake tube have shown the error is calibrated within 0.25 mm in the range of 1 to 150 mm and evidenced the capability for subsurface defects detection. The ease and robustness of the proposed active 3-D thermography have a bright future for 3-D measurement, defects detection, and quality control in the production line.

Dramatic imaging viewpoint variation is the critical challenge toward action recognition for depth video. To address this, one feasible way is to enhance view-tolerance of visual feature, while still maintaining strong discriminative capacity. Multi-view dynamic image (MVDI) is the most recently proposed 3-D action representation manner that is able to compactly encode human motion information and 3-D visual clue well. However, it is still view-sensitive. To leverage its performance, a discriminative MVDI fusion method is proposed by us via multi-instance learning (MIL). Specifically, the dynamic images (DIs) from different observation viewpoints are regarded as the instances for 3-D action characterization. After being encoded using Fisher vector (FV), they are then aggregated by sum-pooling to yield the representative 3-D action signature. Our insight is that viewpoint aggregation helps to enhance view-tolerance. And, FV can map the raw DI feature to the higher dimensional feature space to promote the discriminative power. Meanwhile, a discriminative viewpoint instance discovery method is also proposed to discard the viewpoint instances unfavorable for action characterization. The wide-range experiments on five data sets demonstrate that our proposition can significantly enhance the performance of cross-view 3-D action recognition. And, it is also applicable to cross-view 3-D object recognition. The source code is available at https://github.com/3huo/ActionView .

Joint laser scanning thermography (JLST) is well-known for its efficiency to overcome the field of view (FOV) limitation of thermal imagers. However, JLST requires a data reconstruction to reveal the location of the defective area straightforwardly. Moreover, its detection capacity is limited by the lack of a deconvolution algorithm adaptive to the reconstructed data. In this study, a deconvolutional reconstruction method based on the Lucy-Richardson (LR) algorithm has been developed for JST, which is effective in suppressing random noise and the blur effect caused by thermal diffusion. A JLST inspection is carried out on a functional coating material with cylinder-like defects to test the performance of the proposed method. In comparison to the directly processed method on the original data, the proposed method is processed on the reconstructed data and then compared with principal component analysis (PCA), restored pseudo heat flux (RPHF), fast Fourier transform (FFT) methods, and non-negative matrix factorization (NMF). The experimental results indicated that our proposed LR method exhibited a higher signal-to-noise ratio. Besides, it can detect the cylinder-mocked debonding defects with a diameter of 1.5 mm and a depth of 2.0 mm buried under the 1.0 mm coating. In addition, the defect detection diameter-to-depth ratio reached 1.5, while the defect detection rate of the test specimens can approach 90%.

Traditional cameras struggle to perform in challenging scenarios such as low latency, high speed and high dynamic range. In contrast, neuromorphic vision sensors (event cameras) have great potential for robotics and computer vision due to the advantages of high temporal resolution, high dynamic range, and ultra-low resource consumption. Event cameras are novel bio-inspired sensors that monitor the brightness change of each pixel asynchronously and provide a stream of events encoding the time, position and sign of the brightness changes. Hence, traditional computer vision methods cannot be directly applied to the event-stream. Finding event representations that completely maintain event attributes, as well as efficient and accurate learning approaches, is the key to unlocking the potential of event cameras. In this study, we reveal the rigid transfer from event-stream to graph that has been overlooked in previous work and introduce a novel event representation, namely event graph sequence (EGS) considering the local and global temporal clues. Coupled with EGS, we propose a spatio-temporal pattern extracting (STPE) module to capture the spatio-temporal correlation and evolution of EGS. Our novel framework, Event Graph Sequence Transformer (EGST) , exploits event properties to provide efficient and accurate recognition. This study focuses on the event-based human gaits recognition task, and EGST is evaluated on three different event-based gait datasets. The evaluation results show better or comparable accuracy than the state-of-the-art, while requiring extremely low computation resources. The code will be available at https://github.com/C19h/EGST.

Due to the effects of electromagnetic stress and thermoelastic effect, mechanical stress waves are generated in power semiconductor devices during turn-off moment. The characteristics of these turn-off stress waves vary when power semiconductor devices are subjected to different temperature environments. Measuring these turn-off stress waves is beneficial for analyzing the influence of temperature on the physical properties of power semiconductor devices. As a traditional contact-based mechanical stress wave detection method, acoustic emission testing (AET) is inevitably influenced by temperature, affecting the sensor’s measurement performance. This study employs non-contact laser Doppler vibrometry (LDV) to measure turn-off stress waves in silicon carbide metal-oxide-semiconductor field-effect transistor (SiC MOSFET) at different temperatures. By comparing the signals measured using AET, it has been demonstrated that the signals measured using LDV more effectively reflect the temperature-dependent variations in turn-off stress waves of SiC MOSFET. This research not only broadens the application scope of condition monitoring technology based on mechanical stress wave parameters for power semiconductor devices but also demonstrates the unique advantages of LDV in condition monitoring of power semiconductor devices in different temperature environments.

Decision making system in smart healthcare of Heart failure (HF) disease can facilitate patients remotely, which is an active research area in medical fields, industrial applications, and academia. However, implementation of HF decision making systems on the edge using consumer electronic devices face challenges in processing huge suboptimal heart disease data due to limited computational capabilities. To alleviate such challenges, we introduce an optimize method of HF prediction using four statistical parameters such as strong correlation coefficient, mutual information, analysis of variance (ANOVA) f-test and chi-squared χ2. These parameters select best features through maximum likelihood based threshold value. We then use mean value fusion approach to construct a combine feature space. Afterwards, combine features further optimized via sequential forward selection (SFS) algorithm, which provide best subset of variables. Finally, a novel deep Multi-tier long short-term memory (LSTM) trained on top of the acquired features for diagnosis of HF. We conduct extensive experimentation on Cleveland heart disease dataset, which initially consist of 13 features. Moreover, after execution of our proposed optimize strategy, the size of features restricted to 8. Consequently, these optimal features provide enormous help in diagnosis procedure of HF. The competence of our propose technique evaluated using various metrics such as accuracy, sensitivity, precision, specificity, F1-score, Mathew correlation coefficient (MCC), receiver operating characteristic (ROC) and area under curve (AUC). As shown by the experimental results, the proposed features optimization and multi-tier LSTM strategy improve accuracy of 8.9% compared with different traditional classifiers.