Formulated as a pixel-level labeling task, data-driven neural segmentation models for cloud and corresponding shadow detection have achieved a promising accomplishment in remote sensing imagery processing. The limited capability of these methods to delineate the boundaries of clouds and shadows, however, is still referred to as a central issue of precise cloud and shadow detection. In this paper, we focus on the issue of rough cloud and shadow location and fine-grained boundary refinement of clouds on the dataset of Landsat8 OLI and therefore propose the Refined UNet to achieve this goal. To this end, a data-driven UNet-based coarse prediction and a fully-connected conditional random field (Dense CRF) are concatenated to achieve precise detection. Specifically, the UNet network with adaptive weights of balancing categories is trained from scratch, which can locate the clouds and cloud shadows roughly, while correspondingly the Dense CRF is employed to refine the cloud boundaries. Eventually, Refined UNet can give cloud and shadow proposals sharper and more precisely. The experiments and results illustrate that our model can propose sharper and more precise cloud and shadow segmentation proposals than the ground truths do. Additionally, evaluations on the Landsat 8 OLI imagery dataset of Blue, Green, Red, and NIR bands illustrate that our model can be applied to feasibly segment clouds and shadows on the four-band imagery data.

Haze removal is still an essential prerequisite for image processing and computer vision tasks, and joint inference and refinement of transmission maps remain challenging in the physical scattering model-based haze removal methods. In this article, we propose an end-to-end learnable dehazing network, which is referred to as Guided-Pix2Pix, to jointly estimate and refine the transmission map and further dehaze images by the physical scattering equation. Instead of a two-stage model of predicting and postprocessing the transmission, Guided-Pix2Pix concatenates the trainable Pix2Pix backbone and differentiable guided filter as an embedded layer, which enables generating refined transmission maps in one feed-forward step, and then it substitutes these potential refinements into the physical scattering equation to restore dehazed images. To verify that our Guided-Pix2Pix can be embedded in both training and inference, we demonstrate that the guided filter layer is differentiable and capable of propagating both features forward and gradients backward. Furthermore, explicit derivatives with respect to the input of the guided filter are given, and the relationship between our derivation and that in the guided filter is also explored. Experiments show that our network is effective and robust in image dehazing, can alleviate the halo artifacts along edges, and has great generalization capability.

The use of smart sports equipment and body sensory systems supervising daily sports training is gradually emerging in professional and amateur sports; however, the problem of processing large amounts of data from sensors used in sport and discovering constructive knowledge is a novel topic and the focus of our research. In this article, we investigate golf swing data classification methods based on varieties of representative convolutional neural networks (deep convolutional neural networks) which are fed with swing data from embedded multi-sensors, to group the multi-channel golf swing data labeled by hybrid categories from different golf players and swing shapes. In particular, four convolutional neural classifiers are customized: “GolfVanillaCNN” with the convolutional layers, “GolfVGG” with the stacked convolutional layers, “GolfInception” with the multi-scale convolutional layers, and “GolfResNet” with the residual learning. Testing on the real-world swing dataset sampled from the system integrating two strain gage sensors, three-axis accelerometer, and three-axis gyroscope, we explore the accuracy and performance of our convolutional neural network–based classifiers from two perspectives: classification implementations and sensor combinations. Besides, we further evaluate the performance of these four classifiers in terms of classification accuracy, precision–recall curves, and F1 scores. These common classification indicators illustrate that our convolutional neural network–based classifiers can basically group the golf swing predefined by the combination of shapes and golf players correctly and outperform support vector machine method representing traditional classification methods.

Shape is an important aspect of spatial attributes of land use segments in remotely sensed imagery, but it is still rarely used as a component in land use classification or image-based land use analysis. This study aims to quantitatively characterize land use classes using shape metrics. The study is conducted in a case area located in south China, covering twelve scenes of SPOT-5 images. There were total ten metrics selected for the analysis, namely, Convexity (CONV), Solidity (SOLI), Elongation (ELONG), Roundness (ROUND), Rectangular Fitting (RECT), Compact (COMP), Form Factor (FORM), Square pixel metric (SqP), Fractal Dimension (FD), and Shape Index (SI). The last five metrics were used to measure the complexity of shape. Eight land use classes were investigated in the case area, namely, roads, cultivated lands, settlement places, rivers, ponds, forest and grass lands, reservoirs, and dams. The results show that all typical shape properties of land use segments can be well measured by shape metrics. We identified the land use classes whose values are significantly differentiated from most classes for each metric. Two of the five complexity metrics, FORM and SqP, were identified to be more effective in characterizing the complexity of land use classes. We finally selected six shape metrics and deduced the "Shape Metric Signatures" (SMS) of different land use classes. SMS can serve as accurate and predictive discriminators of land use classes within the study area. Our results show that SMS can clearly distinguish spectrally similar land use classes. The results will help to build a more accurate and intelligent object-oriented classification system for land use classes.