Defects on rail surfaces, which have become critical problems, need to be detected and removed as quickly as possible to ensure the fast, safe, and stable operation of trains. At present, although many solutions have been proposed to address these problems, the comprehensiveness, rapidity, and accuracy of defect detection remain unsatisfactory. This study aims to resolve these existing problems and accordingly proposes a multi-model rail surface defect detection system based on convolutional neural networks (MRSDI-CNN) from the standpoint of studying the squat on the rail surface. The convolutional neural networks utilized include the improved Single Shot MultiBox Detector (SSD) and You Only Look Once version 3(YOLOv3)—two types of one-stage networks. We expounded and analyzed the performance of the convolutional neural networks as well as their applicability to rail surface defect detection. We used a diverse range of rail defect sizes to improve the detection performance of the two deep learning networks, following which they could identify three types of squats in parallel with improved accuracy and without reduction of the detection speed. The experimental results confirm the effectiveness and superiority of the proposed method over those of previous studies.

Hyperspectral images (HSIs) are composed of hundreds of contiguous waveband images, offering a wealth of spatial and spectral information. However, the practical use of HSIs is often hindered by the presence of complicated noise caused by various factors such as non-uniform sensor response and dark current. Traditional methods for denoising HSIs rely on constrained optimization approaches, where selecting appropriate prior knowledge is critical for achieving satisfactory results. Nevertheless, these traditional algorithms are limited by hand-crafted priors, leaving room for improvement in their denoising performance. Recently, the supervised deep learning technique has emerged as a promising approach for HSI denoising. However, their requirement for paired training data and poor generalization ability on untrained noise distributions pose challenges in practical applications. In this paper, we design a novel algorithm by the synergism of optimization-based methods and deep learning techniques. Specifically, we introduce a plug-and-play Deep Low-rank Decomposition (DLD) model into the optimization framework. Furthermore, we propose an effective mechanism to incorporate traditional prior knowledge into the DLD model. Finally, we provide a detailed analysis of the optimization process and convergence of the proposed method. Empirical evaluations on various tasks, including hyperspectral image denoising and spectral compressive imaging, demonstrate the superiority of our approach over state-of-the-art methods.

Anomaly detection refers to the identification of cases that do not conform to the expected pattern, which takes a key role in diverse research areas and application domains. Most of existing methods can be summarized as anomaly object detection-based and reconstruction error-based techniques. However, due to the bottleneck of defining encompasses of real-world high-diversity outliers and inaccessible inference process, individually, most of them have not derived groundbreaking progress. To deal with those imperfectness, and motivated by memory-based decision-making and visual attention mechanism as a filter to select environmental information in human vision perceptual system, in this paper, we propose a Multi-scale Attention Memory with hash addressing Autoencoder network (MAMA Net) for anomaly detection. First, to overcome a battery of problems result from the restricted stationary receptive field of convolution operator, we coin the multi-scale global spatial attention block which can be straightforwardly plugged into any networks as sampling, upsampling and downsampling function. On account of its efficient features representation ability, networks can achieve competitive results with only several level blocks. Second, it’s observed that traditional autoencoder can only learn an ambiguous model that also reconstructs anomalies ”well” due to lack of constraints in training and inference process. To mitigate this challenge, we design a hash addressing memory module that proves abnormalities to produce higher reconstruction error for classification. In addition, we couple the mean square error (MSE) with Wasserstein loss to improve the encoding data distribution. Experiments on various datasets, including two different COVID-19 datasets and one brain MRI (RIDER) dataset prove the robustness and excellent generalization of the proposed MAMA Net.

Spectral images with rich spatial and spectral information have wide usage, however, traditional spectral imaging techniques undeniably take a long time to capture scenes. We consider the computational imaging problem of the snapshot spectral spectrometer, i.e., the Coded Aperture Snapshot Spectral Imaging (CASSI) system. For the sake of a fast and generalized reconstruction algorithm, we propose a prior image guidance-based snapshot compressive imaging method. Typically, the prior image denotes the RGB measurement captured by the additional uncoded panchromatic camera of the dual-camera CASSI system. We argue that the RGB image as a prior image can provide valuable semantic information. More importantly, we design the Prior Image Semantic Similarity (PIDS) regularization term to enhance the reconstructed spectral image fidelity. In particular, the PIDS is formulated as the difference between the total variation of the prior image and the recovered spectral image. Then, we solve the PIDS regularized reconstruction problem by the Alternating Direction Method of Multipliers (ADMM) optimization algorithm. Comprehensive experiments on various datasets demonstrate the superior performance of our method.

Power line parts detection refers to the inspection of key parts on transmission lines against the complex background in aerial images and identifying whether exist anomalies that cause transmission failure. Obviously, this process plays a pivotal role in ensuring the safety of power transmission. Most of the existing methods are based on deep convolutional neural networks. However, the complexity and variability of the aerial image background and the problem of unmanned aerial vehicles (UAVs) shooting perspective and distance pose a challenge for previous works. This study aims to improve the detection accuracy of the model and propose an attention-guided multitask convolutional neural network (AGMNet). First, to enhance the feature representation of objects in aerial images, we construct spatial region attention blocks that are suitable for object detection. It can be inserted into any existing convolutional backbone network. Due to its efficient feature tensor computation method, the network can obtain competitive results with less computational memory. Second, we introduce a multitask framework that creatively considers the identification of rust levels and abnormal conditions of power line components, which has not been considered in previous works. Finally, we incorporate the refinable region proposal network (RPN) structure and multiscale training strategy to improve the robustness of the network. The experimental results on the testing datasets show that the proposed AGMNet can recognize the power parts (dampers and suspension clamps) with a mean average precision (mAP) of 95.3% and simultaneously identify their rust levels with an mAP of 75.4% and abnormal conditions with an mAP of 92.7%.

Real-world transmission line inspections (RTLIs) ensure power stability and safety. Deep learning (DL) models have become prevalent approaches for performing RTLI tasks. However, the high computational demands and substantial parameter requirements of DL models limit their real-world applicability. This article introduces a novel approach, a multiscale uncertainty-aware knowledge-based network, which is designed to balance the accuracy and efficiency in RTLI tasks. Specifically, we propose an uncertainty-aware knowledge distillation method that incorporates pixel-level uncertainty into the knowledge transfer process, mitigating the impact of noisy knowledge derived from extra background information contained in ground truths. In addition, our method integrates a multiscale relationship distillation technique, thus enhancing the transfer of multiscale information between the teacher and student models. Consequently, RTLI tasks can be efficiently accomplished using the well-learned lightweight student model. Comprehensive experiments conducted on a real-world dataset collected via uncrewed aerial vehicles demonstrate the efficacy of our proposed approach in terms of achieving high detection accuracy with reduced computational costs.