Deep learning–based fabric defect detection methods have been widely investigated to improve production efficiency and product quality. Although deep learning–based methods have proved to be powerful tools for classification and segmentation, some key issues remain to be addressed when applied to real applications. Firstly, the actual fabric production conditions of factories necessitate higher real-time performance of methods. Moreover, fabric defects as abnormal samples are very rare compared with normal samples, which results in data imbalance. It makes model training based on deep learning challenging. To solve these problems, an extremely efficient convolutional neural network, Mobile-Unet, is proposed to achieve the end-to-end defect segmentation. The median frequency balancing loss function is used to overcome the challenge of sample imbalance. Additionally, Mobile-Unet introduces depth-wise separable convolution, which dramatically reduces the complexity cost and model size of the network. It comprises two parts: encoder and decoder. The MobileNetV2 feature extractor is used as the encoder, and then five deconvolution layers are added as the decoder. Finally, the softmax layer is used to generate the segmentation mask. The performance of the proposed model has been evaluated by public fabric datasets and self-built fabric datasets. In comparison with other methods, the experimental results demonstrate that segmentation accuracy and detection speed in the proposed method achieve state-of-the-art performance.

Fabric defect detection plays an essential role in the textile production process, which was widely applied in the textile industry. For fabric defect detection, many algorithms have been proposed. However, lots of important problems, such as the accuracy of detection, the computational complexity of the algorithm, and data imbalance, still needed to be addressed for application in industrial production. In this article, we propose an efficient convolutional neural network for defect segmentation and detection. The design of this framework significantly alleviates the manual annotation cost of the data set; it only needs few defect samples combined with standard samples to learn the potential feature of defects and obtain the location of defects with high accuracy. The network is divided into two parts: segmentation and decision. First, the fabric data set without training is utilized as the input of the segmentation network. Then, the output of the segmentation network is applied as the raw materials for training the decision network. Finally, a well-trained network is used to obtain the location of defects with high accuracy. The proposed method only demands almost 50 defect samples to get accurate segmentation results and can achieve the requirement of real-time detection with a speed of 25 frames per second (FPS). The experimental results based on a public data set and three self-made fabric data sets show that the proposed method significantly outperforms eight state-of-the-art methods in terms of accuracy and robustness.

Surface inspection is a necessary process of fabric quality control. However, it remains a challenging task owing to diverse types of defects, various patterns of fabric texture, and application requirements for detection speed. In this paper, a lightweight deep learning model is therefore proposed to complete the segmentation of fabric defects. The input of the model is a fabric image, and the output is a binary image. Generally known, a deep learning model usually needs much data to update the parameters. Still, as an abnormal phenomenon, fabric defects are unpredictable, which makes it impossible to collect a large number of data. Distinct from other models, the proposed method is a supervised network but does not need manually labeled samples for training. A fake sample generator is designed to simulate the defect image, which only needs the defect-free fabric image. The proposed model is trained with fake samples and verified with real samples. The experimental results show that the model trained with false data is useful and achieves high segmentation accuracy on real fabric samples. Besides, a loss function is proposed to deal with the problem of imbalance between the number of background pixels and the number of defective pixels in the fabric image. Comprehensive experiments were performed on representative fabric samples to verify the segmentation accuracy and detection speed of this method.

Historical catenary trip fault data of China high-speed railway (HSR) revealed that the risk of catenary trip varies distinctively in different time periods and different regions, and catenary trip fault risk has obvious characteristics of time-space differences. In order to represent and quantify the characteristics of risk, this paper proposes a risk index system for catenary lines of HSR considering the characteristics of time-space differences. First, the characteristics of the catenary trip risk and the corresponding reasons are analyzed. Second the risk index system is established from the perspectives of time and space differences. Subsequently, the proposed risk index system is applied to the benchmark data taken from a railway administration in China related to catenary trip records in 3 years. The results of the risk indices are relevant information which can reveal the time-space differences of catenary trip risk, and reflect the influence of external environmental factors as well as catenary's ability of disaster prevention and resilience. This uniform and quantitative information is helpful for the management of the catenary operation risk.

UAV-to-satellite geolocalization offers accurate drift-free navigation in the absence of external positioning signals. Increased deep-learning-based approaches have demonstrated their potential for high accuracy by framing the problem as a one-to-all retrieval task. However, in real-world scenario, the problem is not just a one-to-all retrieval task, which leads to a gap between research and applications. Based on this observation, We attempt to look closer to the problem instead of designing sophisticated network architectures or objective functions. In this study, we proposed a flexible and simple coarse-to-fine sequence-matching solution with targeted joint use of deep learning and classical machine learning approaches. Our goal is to improve geolocalization accuracy by matching UAV images with a few relevant reference image patches instead of all images. To this end, we first coarsely constructed a sequence of reference satellite image patches corresponding to the UAV trajectory, for which we proposed a deep feature- and manifold learning-based image-sorting method. Once the reference satellite patches are sorted and aligned with the UAV trajectory, the reference sequence is determined. Given a query UAV frame, the search area can be decreased from two to one dimensions. In particular, both deep-learning-based and classical image-matching algorithms can provide competitive accuracy when integrating sequence constraints. We demonstrate that classical manifold learning-based and image matching methods perform exceptionally well for UAV-to-satellite geolocalization when utilized jointly with suitable deep learning techniques. We validated the approach’s unique outperformance on two challenging and realistic UAV-to-satellite geolocalization datasets. Dataset, code and models are available for research purposes at https://seqmatch.geovisuallocalization.com/.