Cloud detection is the precondition for deriving other information (e.g., cloud cover) in ground-based sky imager applications. This paper puts forward an effective cloud detection approach, the Hybrid Thresholding Algorithm (HYTA) that fully exploits the benefits of the combination of fixed and adaptive thresholding methods. First, HYTA transforms an input color cloud image into a normalized blue/red channel ratio image that can keep a distinct contrast, even with noise and outliers. Then, HYTA identifies the ratio image as either unimodal or bimodal according to its standard deviation, and the unimodal and bimodal images are handled by fixed and minimum cross entropy (MCE) thresholding algorithms, respectively. The experimental results demonstrate that HYTA shows an accuracy of 88.53%, which is far higher than those of either fixed or MCE thresholding alone. Moreover, HYTA is also verified to outperform other state-of-the-art cloud detection approaches.

Rail inspection based on visual inspection system (VIS) has drawn much attention recently, since VIS is automatic, fast, nondestructive, and objective. However, visual rail inspection is still a challenge to accurately identify possible defects involving a large variety of visual appearances. This paper presents an automatic visual inspection system to address these difficulties. Rail surface images are first obtained by the system, and then fed into the proposed hierarchical inspection framework containing coarse extractor and fine extractor. Specifically, the coarse extractor handles this defect inspection problem by exploring characteristics of rail background instead of defect itself, and focuses on finding the background modes. The fine extractor, which integrates the longitudinal context information and transversal prior information, is presented to largely reduce the impacts of other irregulars. The proposed method is evaluated on labeled Type-I and Type-II rail surface discrete defects data sets and a practical rail line. The experimental results demonstrate that our method outperforms the state-of-the-art works.

Computer vision systems have attracted much attention in recent years for use in detecting surface defects on rails; however, accurate and efficient recognition of possible defects remains challenging due to the variations shown by defects and also noise. This paper proposes a coarse-to-fine model (CTFM) to identify defects at different scales. The model works on three scales from coarse to fine: subimage level, region level, and pixel level. At the subimage level, the background subtraction model exploits row consistency in the longitudinal direction, and strongly filters the defect-free range, leaving roughly identified subimages within which defects may exist. At the next level, the region extraction model, inspired by visual saliency models, locates definite defect regions using phase-only Fourier transforms. At the finest level, the pixel subtraction model uses pixel consistency to refine the shape of each defect. The proposed method is evaluated using Type-I and Type-II rail surface defect detection data sets and an actual rail line. The experimental results show that CTFM outperforms state-of-the-art methods according to both the pixel-level index and the defect-level index.

Computer vision based methods have been widely used in surface defect inspection. However, most of these approaches are task-specific, and it is hard to transfer them to similar detection scenarios. This paper proposes an entity sparsity pursuit (ESP) method to identify surface defects. Based on the observation that surface image textures usually form a low-rank structure and the structure can be violated by the presence of rare defects, we formulate the detection task as a low-rank and entity sparsity pursuit problem. To alleviate the feature shortage issue existed in industrial grayscale images, we customize a kind of intuitive features for surface defect inspection. Different from previous work utilizing complicated regularization terms, we resort to mine intrinsic priors of defect images, which can be neatly incorporated into the designed architecture. The proposed model is compact and able to detect surface defects in an unsupervised manner. To fully evaluate the presented method, we conduct a series of experiments using two real-world and one synthetic defect datasets. Experimental results demonstrate that ESP outperforms state-of-the-art methods.

Weather forecasting requires comprehensive analysis of a variety of meteorological data. Recent decades have witnessed the advance of weather observation and simulation technologies, triggering an explosion of meteorological data which are collected from multiple sources (e.g., radar, automatic stations and numerical weather prediction) and usually characterized by a spatiotemporal (ST) structure. As a result, the adequate exploition of these multi‐source ST data emerges as a promising but challenging topic for weather forecasting. To address this issue, we propose a data‐driven forecasting framework (referred to as LightNet+) based on deep neural networks using a lightning scenario. Our framework design enables LightNet+ to make forecasts by mining complementary information distributed across multiple data sources, which may be heterogeneous in spatial (continuous versus discrete) and temporal (observations from the past versus simulation of the future) domains. We evaluate LightNet+ using a real‐world weather dataset in North China. The experimental results demonstrate: (a) LightNet+ produces significantly better forecasts than three established lightning schemes, and (b) the more data sources are fed into LightNet+, the higher forecasting quality it achieves.