Unraveling False Positives in Unsupervised Defect Detection Models: A Study on Anomaly-Free Training Datasets.

Unsupervised defect detection methods have garnered substantial attention in industrial defect detection owing to their capacity to circumvent complex fault sample collection. However, these models grapple with establishing a robust boundary between normal and abnormal conditions in intricate scenarios, leading to a heightened frequency of false-positive predictions. Spurious alerts exacerbate the work of reconfirmation and impede the widespread adoption of unsupervised anomaly detection models in industrial applications. To this end, we delve into the sole available data source in unsupervised defect detection models, the unsupervised training dataset, to introduce a solution called the False Alarm Identification (FAI) method aimed at learning the distribution of potential false alarms using anomaly-free images. It exploits a multi-layer perceptron to capture the semantic information of potential false alarms from a detector trained on anomaly-free training images at the object level. During the testing phase, the FAI model operates as a post-processing module applied after the baseline detection algorithm. The FAI algorithm determines whether each positive patch predicted by the normalizing flow algorithm is a false alarm by its semantic features. When a positive prediction is identified as a false alarm, the corresponding pixel-wise predictions are set to negative. The effectiveness of the FAI method is demonstrated by two state-of-the-art normalizing flow algorithms on extensive industrial applications.

Temperature Effects on Nonlinear Ultrasonic Guided Waves.

Nonlinear ultrasonic guided waves have attracted increasing attention in the field of structural health monitoring due to their high sensitivity and long detection distance. In practical applications, the temperature of the tested structure will inevitably change, so it is essential to evaluate the effects of temperature on nonlinear ultrasonic guided waves. In this paper, an analytical approach is proposed to obtain the response law of nonlinear guided waves to temperature based on the semi-analytical finite element (SAFE) method. The plate structure is investigated as a demonstration example, and the corresponding simulation analysis and experimental verification are carried out. The results show that the variation trends of different cumulative second harmonic modes with temperature are distinct, and their amplitudes monotonically increase or decrease with the continuously rising temperature. Therefore, in the applications with nonlinear ultrasonic guided waves, it is necessary to predict the changing trend of selected cumulative second harmonics under the action of temperature and compensate the result for the influence of temperature. The methods and conclusions presented in this paper are also applicable to other types of structures and have general practicality.

On the Identification of Elastic Moduli of In-Service Rail by Ultrasonic Guided Waves.

Non-destructive rail testing and evaluation based on guided waves need accurate information about the mode propagation characteristics, which can be obtained numerically with the exact material properties of the rails. However, for rails in service, it is difficult to accurately obtain their material properties due to temperature fluctuation, material degradation and rail profile changes caused by wear and grinding. In this study, an inverse method is proposed to identify the material elastic constants of in-service rails by minimizing the discrepancy between the phase velocities predicted by a semi-analytical finite element model and those measured using array transducers attached to the rail. By selecting guided wave modes that are sensitive to moduli but not to rail profile changes, the proposed method can make stable estimations for worn rails. Numerical experiments using a three-dimensional finite element model in ABAQUS/Explicit demonstrate that reconstruction accuracies of 0.36% for Young's modulus and 0.87% for shear modulus can be achieved.

High-Speed Railway Intruding Object Image Generating with Generative Adversarial Networks.

Foreign object intrusion is a great threat to high-speed railway safety operations. Accurate foreign object intrusion detection is particularly important. As a result of the lack of intruding foreign object samples during the operational period, artificially generated ones will greatly benefit the development of the detection methods. In this paper, we propose a novel method to generate railway intruding object images based on an improved conditional deep convolutional generative adversarial network (C-DCGAN). It consists of a generator and multi-scale discriminators. Loss function is also improved so as to generate samples with a high quality and authenticity. The generator is extracted in order to generate foreign object images from input semantic labels. We synthesize the generated objects to the railway scene. To make the generated objects more similar to real objects, on scale in different positions of a railway scene, a scale estimation algorithm based on the gauge constant is proposed. The experimental results on the railway intruding object dataset show that the proposed C-DCGAN model outperforms several state-of-the-art methods and achieves a higher quality (the pixel-wise accuracy, mean intersection-over-union (mIoU), and mean average precision (mAP) are 80.46%, 0.65, and 0.69, respectively) and diversity (the Fréchet-Inception Distance (FID) score is 26.87) of generated samples. The mIoU of the real-generated pedestrian pairs reaches 0.85, and indicates a higher scale of accuracy for the generated intruding objects in the railway scene.

An Adaptive Track Segmentation Algorithm for a Railway Intrusion Detection System.

Video surveillance-based intrusion detection has been widely used in modern railway systems. Objects inside the alarm region, or the track area, can be detected by image processing algorithms. With the increasing number of surveillance cameras, manual labeling of alarm regions for each camera has become time-consuming and is sometimes not feasible at all, especially for pan-tilt-zoom (PTZ) cameras which may change their monitoring area at any time. To automatically label the track area for all cameras, video surveillance system requires an accurate track segmentation algorithm with small memory footprint and short inference delay. In this paper, we propose an adaptive segmentation algorithm to delineate the boundary of the track area with very light computation burden. The proposed algorithm includes three steps. Firstly, the image is segmented into fragmented regions. To reduce the redundant calculation in the evaluation of the boundary weight for generating the fragmented regions, an optimal set of Gaussian kernels with adaptive directions for each specific scene is calculated using Hough transformation. Secondly, the fragmented regions are combined into local areas by using a new clustering rule, based on the region's boundary weight and size. Finally, a classification network is used to recognize the track area among all local areas. To achieve a fast and accurate classification, a simplified CNN network is designed by using pre-trained convolution kernels and a loss function that can enhance the diversity of the feature maps. Experimental results show that the proposed method finds an effective balance between the segmentation precision, calculation time, and hardware cost of the system.

Foreground Detection with Deeply Learned Multi-Scale Spatial-Temporal Features.

Foreground detection, which extracts moving objects from videos, is an important and fundamental problem of video analysis. Classic methods often build background models based on some hand-craft features. Recent deep neural network (DNN) based methods can learn more effective image features by training, but most of them do not use temporal feature or use simple hand-craft temporal features. In this paper, we propose a new dual multi-scale 3D fully-convolutional neural network for foreground detection problems. It uses an encoder⁻decoder structure to establish a mapping from image sequences to pixel-wise classification results. We also propose a two-stage training procedure, which trains the encoder and decoder separately to improve the training results. With multi-scale architecture, the network can learning deep and hierarchical multi-scale features in both spatial and temporal domains, which is proved to have good invariance for both spatial and temporal scales. We used the CDnet dataset, which is currently the largest foreground detection dataset, to evaluate our method. The experiment results show that the proposed method achieves state-of-the-art results in most test scenes, comparing to current DNN based methods.