Multi-scale and multi-patch transformer for sandstorm image enhancement

Sandstorm is a meteorological phenomenon common in arid and semi-arid regions. A sandstorm can carry large volumes of sand unexpectedly, which leads to severe color deviations and significantly degraded visibility when an image is taken in such a scenario. However, existing image enhancement methods cannot enhance sandstorm images well due to the challenging degradations and the scarcity of sandstorm training data. In this paper, we propose a Transformer with rotary position embedding to perform sandstorm image enhancement via building multi-scale and multi-patch dependencies. Our key insights in this work are 1) a multi-scale Transformer can globally eliminate the color deviations of sandstorm images via aggregating global information, 2) a multi-patch Transformer can recover local details well via learning the spatial variant degradations, and 3) a U-shape Transformer with rotary position embedding as the core unit of multi-scale and multi-patch Transformer can effectively build the long-range dependencies. We also contribute a real-world Sandstorm Image Enhancement (SIE) dataset including 1,400 sandstorm images with different degrees of degradations and various scenes. Experiments performed on synthetic images and real-world sandstorm images demonstrate that our proposed method not only obtains visually pleasing results but also outperforms state-of-the-art methods qualitatively and quantitatively.     

Neural Style Transfer for image within images and conditional GANs for destylization

In this paper, the feature representation of an image by CNN is used to hide the secret image into the cover image. The style of the cover image hides the content of the secret image and produce a stego image using Neural Style Transfer (NST) algorithm, which resembles the cover image and also contains the semantic content of secret image. The main technical contributions are to hide the content of the secret image in the in-between hidden layered style features of the cover image, which is the first of its kind in the present state-of-art-technique. Also, to recover the secret image from the stego image, destylization is done with the help of conditional generative adversarial networks (GANs) using Residual in Residual Dense Blocks (RRDBs). Further, stego images from different layer combinations of content and style features are obtained and evaluated. Evaluation is based on the visual similarity and quality loss between the cover-stego pair and the secret-reconstructed secret pair of images. From the experiments, it has been observed that the proposed algorithm has 43.95 dB Peak Signal-to-Noise Ratio (PSNR)), .995 Structural Similarity Index (SSIM), and .993 Visual Information Fidelity (VIF) for the ImageNet dataset. The proposed algorithm is found to be more robust against StegExpose than the traditional methods.     

Image sequence-based risk behavior detection of power operation inspection personnel

A novel image sequence-based risk behavior detection method to achieve high-precision risk behavior detection for power maintenance personnel is proposed in this paper. In this method, the original image sequence data is first separated from the foreground and background. Then, the free anchor frame detection method is used in the foreground image to detect the personnel and correct their direction. Finally, human posture nodes are extracted from each frame of the image sequence, which are then used to identify the abnormal behavior of the human. Simulation experiment results demonstrate that the proposed algorithm has significant advantages in terms of the accuracy of human posture node detection and risk behavior identification.     

Controlled growth of Bi-Functional La doped CeO2 nanorods for photocatalytic H2 production and supercapacitor applications

The rapid increase in energy consumption has severely rehabilitated human life urging to develop reliable and environmental friendly energy storage devices. Target oriented, systematic approach has been adopted to synthesis La doped CeO₂ nanostructures with percentage as La_xCe_1-xO₂ (X = 0,1,3,5,7) for potential super capacitors applications. Morphological doping impact on H₂ production, electrochemical and optical properties are thoroughly investigated. XRD studies revealed the crystalline phase purity and attained approximately 35 nm average crystallite size. The SEM images exposed that primary morphology nano-particles has been tuned into nanorods by increasing the La concentration in CeO₂ with size range 40～60 nm. CV graphs depicted that the prepared electrodes obey the pseudo capacitive faradaic reactions behavior in nature. Maximum capacitance (925 F g^-1) has been achieved by La_0·05Ce_0·95O₂ which is better than numerous reported materials. The La_0·05Ce_0·95O₂ also exhibited excellent GCD stability with 87.8% retention exhibiting it suitability for supercapacitor applications. Furthermore, the La_0·05Ce_0·95O₂ showed the significantly higher H₂ (9 μmol h^?1g^?1) production rate as compared to undoped CeO₂ and La_0·01Ce_0·99O_2, La_0·03Ce_0·97O₂ samples. This higher production is attributed to the recombination rate and have strong substantial correlation with optical characteristics.     

Role of particle shape on the shear strength of sand-GCL interfaces under dry and wet conditions

Interface shear strength of geosynthetic clay liners (GCL) with the sand particles is predominantly influenced by the surface characteristics of the GCL, size and shape of the sand particles and their interaction mechanisms. This study brings out the quantitative effects of particle shape on the interaction mechanisms and shear strength of GCL-sand interfaces. Interface direct shear tests are conducted on GCL in contact with a natural sand and a manufactured sand of identical gradation, eliminating the particle size effects. Results showed that manufactured sand provides effective particle-fiber interlocking compared to river sand, due to the favorable shape of its grains. Further, the role of particle shape on the hydration of GCL is investigated through interface shear tests on GCL-sand interfaces at different water contents. Bentonite hydration is found to be less in tests with manufactured sand, leading to better interface shear strength. Grain shape parameters of sands, surface changes related to hydration and particle entrapment in GCL are quantified through image analysis on sands and tested GCL surfaces. It is observed that the manufactured sand provides higher interface shear strength and causes lesser hydration related damages to GCL, owing to its angular particles and low permeability.     

A novel 4D resolution imaging method for low and medium atomic number objects at the centimeter scale by coincidence detection technique of cosmic-ray muon and its secondary particles

The muon radiography imaging technique for high-atomic-number objects(Z) and large-volume objects via muon transmission imaging and muon multiple scattering imaging remains a popular topic in the field of radiation detection imaging. However, few imaging studies have been reported on low and medium Z objects at the centimeter scale. This paper presents an imaging system that consists of three layers of a position-sensitive detector and four plastic scintillation detectors. It acquires data by co...     

安卓平台上的医用图像信息采集系统的开发设计

为了探讨在安卓平台上构建医用图像采集系统的开发个案,分析通过以智能手机、平板电脑为核心安卓设备通过拍照获得化验单数据后进行文本识别并提交智慧医疗系统的解决方案。本文首先通过二值化算法形成低阈值图像数据,使用卷积神经元网络算法对文本进行逐一识别,使用K-means算法对识别后的单字文本进行字段记录值的整合并形成元数据库服务于其他智慧医疗系统模块。在使用9000组数据对神经元网络进行前期训练的前提下,该系统的识别准确率达到了99.5%以上。本系统具有一定的可行性,对未来智慧医疗的系统开发有实践意义。     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

Quality assessment for color correction-based stitched images via bi-directional matching

With the deepening of social information, the panoramic image has drawn a significant interest of viewers and researchers as it can provide a very wide field of view (FoV). Since panoramic images are usually obtained by capturing images with the overlapping regions and then stitching them together, image stitching plays an important role in generating panoramic images. In order to effectively evaluate the quality of stitched images, a novel quality assessment method based on bi-directional matching is proposed for stitched images. Specifically, dense correspondences between the testing and benchmark stitched images are first established by bi-directional SIFT-flow matching. Then, color-aware, geometric-aware and structure-aware features are respectively extracted and fused via support vector regression (SVR) to obtain the final quality score. Experiments on our newly constructed database and ISIQA database demonstrate that the proposed method can achieve comparable performance compared with the conventional blind quality metrics and the quality metrics specially designed for stitched images.