In this study, we propose a new post processing algorithm, using a stable low-rank decomposed pseudo restored heat flux based on the ensemble variational Bayes tensor factorization (EVBTF-RPHF) algorithm for performing periodic square wave thermographic nondestructive testing (thermographic NDT). Previous studies have shown that both RPHF and EVBTF can separately improve the detectability of thermography by enhancing some defect features. However, both methods are limited by their particularly constraints: RPHF are heavily degraded by noises and missing data due to the assumptions under which the physical models are derived while efficiency of EVBT reduces when the lateral heat diffusion weights out. By embedding RPHF into the stable low-rank decomposition EVBTF, the proposed algorithm allows to improve the detectability of defects in thermographic NDT using a periodic heat flux with low-rank spatial distribution. The study verifies the capacity of the proposed method by theoretical analysis. Then, experiments were conducted on a carbon fiber composite panel with foreign inserts buried up to 5 mm deep. The sampled data are processed by the proposed method. The results are compared with existing methods such as phase-locked RPHF and EVBTF. The experimental results demonstrated that defects with normalized diameter-to-depth ratios as small as 0.9, barely detected with other available techniques, can reliably be detected by EVBTF-RPHF. The signal to noise ratio and the contrast are used as figure of merit to quantitatively compare the capacity of the proposed method with existing methods. However, the computation efficiency of the proposed algorithms needs further improvement.

In this paper, a new inspection method, joint scanning laser thermography (JSLT) as well as its data reconstruction and processing algorithm, is proposed. The new inspection method is utilized to detect and characterize the flatbottom holes (FBH) in carbon fiber composites by using joint laser scanning scheme. By analyzing the nature of the thermal image sequences sampled under such a scanning scheme, a quick and simple reconstruction method is developed to characterize the buried depth of defects based on 1D heat conduction model. The processed thermal images are expected to get higher temporal resolution and spatial resolution. It can inspect larger area within shorter acquisition time than the pulse thermography. Thus, the study solves the dilemma between the inspection speed and the inspection capacity. Later, a joint laser scanning thermography test is set up to test the algorithm on a carbon fiber composite panel with defects buried at different depth. The experimental results show that the reconstructed data almost behave as those under pulse excitation. The tendency of temperature to change in the logarithmic domain over time is similar to the curve in the TSR method. But, unlike the pulse thermography data, the defect detection rate of PCA based on reconstructed data is higher than that of fast Fourier transform (FFT) amplitude image, independent component analysis (ICA) and FFT phase image. The JSLT system is used to detect FBH and the diameter-depth ratio reached 3.33.

In traffic scenes, target detection is impacted by factors such as complex backgrounds, illumination, and mutual occlusion of moving targets, all of which tend to cause the sensors to perform poorly and have a high false detection rate. To solve these challenges, this study proposes a multi-data source target detection network integrating target tracking based on camera and LiDAR fusion (YCANet), which utilizes the improved YOLOv7 and CenterPoint to detect the visible images and point clouds separately, and uses the Aggregated Euclidean Distances (AED) as the new metric in the data correlation module for tracking the detection results of the images and point clouds, which effectively improves the correlation robustness and reduces the tracking errors. An optimal matching fusion strategy is presented to merge the detection and tracking results of two sensors for decision matching. The fusion of camera and LiDAR improves the poor detection results, while the target tracking incorporated into the detection approach reduces the false detection rate. Homemade dataset and partial ONCE dataset are used for network training and testing, and comparing with the other seven algorithms, the experimental results show that our proposed approach better meets the accuracy requirements, and the mAP reaches 83.40% while maintaining the false detection rate of 18.19%.

Impact damage, caused by low-energy impact, is inevitable during the whole life time of carbon fiber reinforced plastic (CFRP) material. However, the barely visible impact damage (BVID) is difficult to be detected by visual methods. Ultrasonic thermography (UT) is an emerging non-destructive testing technique that visualizes damage in thermal images captured by an infrared (IR) camera when the material is stimulated by ultrasound. However, noise and blurry edges around the high temperature areas may cause confusion and lead to unreliable results in the thermal images of UT test. In this work, an impact damage inspection method is proposed based on manifold learning for CFRP material. Low-power ultrasonic excitation is used for this UT. The IR image sequences are processed as data sets in high-dimensional space. These data sets are reduced to lower dimensions by manifold learning to find the intrinsic structure in the two-dimensional manifold. Each dimension of the embedding manifold correlates highly with one degree of freedom underlying the original pixel: steady and random components. The steady component, which reflects the temperature rise caused by damage, is used for VID and BVID detection. The experimental system was set up, and CFRP plate specimens with different impact damage were tested. All the impact damage could be detected and shown in reconstructed static image with little noise. The proposed method using image sequences could provide a visualized, reliable and effective impact damage inspection and localization means for CFRP material during manufacturing and in service.

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity of anomalies, existing methods only use easily collected regular events to model the inherent normality of normal spatial-temporal patterns in an unsupervised manner. Although such methods have made significant progress benefiting from the development of deep learning, they attempt to model the statistical dependency between observable videos and semantic labels, which is a crude description of normality and lacks a systematic exploration of its underlying causal relationships. Previous studies have shown that existing unsupervised VAD models are incapable of label-independent data offsets (e.g., scene changes) in real-world scenarios and may fail to respond to light anomalies due to the overgeneralization of deep neural networks. Inspired by causality learning, we argue that there exist causal factors that can adequately generalize the prototypical patterns of regular events and present significant deviations when anomalous instances occur. In this regard, we propose Causal Representation Consistency Learning (CRCL) to implicitly mine potential scene-robust causal variable in unsupervised video normality learning. Specifically, building on the structural causal models, we propose scene-debiasing learning and causality-inspired normality learning to strip away entangled scene bias in deep representations and learn causal video normality, respectively. Extensive experiments on benchmarks validate the superiority of our method over conventional deep representation learning. Moreover, ablation studies and extension validation show that the CRCL can cope with label-independent biases in multi-scene settings and maintain stable performance with only limited training data available.