Shadow Inpainting and Removal Using Generative Adversarial Networks with Slice Convolutions

In this paper, we propose a two‐stage top‐down and bottom‐up Generative Adversarial Networks (TBGANs) for shadow inpainting and removal which uses a novel top‐down encoder and a bottom‐up decoder with slice convolutions. These slice convolutions can effectively extract and restore the long‐range spatial information for either down‐sampling or up‐sampling. Different from the previous shadow removal methods based on deep learning, we propose to inpaint shadow to handle the possible dark shadows to achieve a coarse shadow‐removal image at the first stage, and then further recover the details and enhance the color and texture details with a non‐local block to explore both local and global inter‐dependencies of pixels at the second stage. With such a two‐stage coarse‐to‐fine processing, the overall effect of shadow removal is greatly improved, and the effect of color retention in non‐shaded areas is significant. By comparing with a variety of mainstream shadow removal methods, we demonstrate that our proposed method outperforms the state‐of‐the‐art methods.     

Animating static objects by illusion‐based projection mapping

By applying scientific knowledge about human visual processing, we have recently developed a light projection technique, called Deformation Lamps, which can add a variety of illusory, yet realistic distortions, to a wide range of static projection targets. In this paper, to explain how Deformation Lamps works, we first describe its basic algorithm and related human visual processing. We then describe the latest version of the Deformation Lamps system. It is a ready‐to‐use application that automatically finds projection targets and projects motion‐inducer patterns in alignment with images or textures on the targets' surfaces. The application also supports interactive editing of animation contents.     

Efficient Shadow Removal Using Subregion Matching Illumination Transfer

This paper proposes a new shadow removal approach for input single natural image by using subregion matching illumination transfer We first propose an effective and automatic shadow detection algorithm incorporating global successive thresholding scheme and local boundary refinement. Then we present a novel shadow removal algorithm by performing illumination transfer on the matched subregion pairs between the shadow regions and non‐shadow regions, and this method can process complex images with different kinds of shadowed texture regions and illumination conditions. In addition, we develop an efficient shadow boundary processing method by using alpha matte interpolation, which produces seamless transition between the shadow and non‐shadow regions. Experimental results demonstrate the capabilities of our algorithm in both the shadow removal quality and performance.     

Video Shadow Removal Using Spatio‐temporal Illumination Transfer

Shadow removal for videos is an important and challenging vision task. In this paper, we present a novel shadow removal approach for videos captured by free moving cameras using illumination transfer optimization. We first detect the shadows of the input video using interactive fast video matting. Then, based on the shadow detection results, we decompose the input video into overlapped 2D patches, and find the coherent correspondences between the shadow and non‐shadow patches via discrete optimization technique built on the patch similarity metric. We finally remove the shadows of the input video sequences using an optimized illumination transfer method, which reasonably recovers the illumination information of the shadow regions and produces spatio‐temporal shadow‐free videos. We also process the shadow boundaries to make the transition between shadow and non‐shadow regions smooth. Compared with previous works, our method can handle videos captured by free moving cameras and achieve better shadow removal results. We validate the effectiveness of the proposed algorithm via a variety of experiments.     

A novel consensus algorithm for second‐order multi‐agent systems without velocity measurements

In this paper, a novel consensus protocol for second‐order multi‐agent systems is elegantly designed, and it relaxes the common requirement of the velocity information of the agents. An interesting consensus criterion is explicitly derived in terms of the proposed cooperation law provided that the dynamical equation for each agent is linear. As an extension, the proposed cooperation rule is further extended to a general scenario, where the coupling weights characterizing the relationships among the neighboring agents are time‐varying. Accordingly, two distributed cooperative algorithms (node/edge‐based scheme) are explicitly designed. Moreover, we study the case of network with switching communication setting. It shows that edge‐based law is capable with the time‐varying topology, while the node‐based scheme is not. In addition, the proposed coordination strategies are applied to the tracking problem as well. Finally, these obtained consensus results are well supported in the light of the pendulum models. Copyright © 2016 John Wiley & Sons, Ltd.     

基于投影技术的增强现实注册方法

注册技术是实现增强现实应用系统的关键问题之一。实现了一种利用投影技术改进了的注册方法。这种注册方法主要包含4个步骤：（1）检测标识和特征点的位置;（2）利用投影技术跟踪摄像机;（3）计算模型视图矩阵;（4）绘制虚拟物体。在初始阶段,指定4个点建立世界坐标系,虚拟物体将会被叠加到这个坐标系上;在注册过程中,利用投影技术跟踪特征点的位置,并计算用于增强的模型视图转换。这种注册方法可以为一般的室内增强现实系统提供所需的精确度和实时性。     

融合目标检测和空间投影的增强现实方法

实现对固定目标物的注册跟踪方法中, 目前最常使用预制标识物的方法, 或者需要使用集成深度摄像头等配件的专业AR设备, 成本较高. 针对现有方法的缺陷, 提出一种融合目标检测和空间投影算法的简单协作式混合跟踪注册技术, 先通过深度学习算法进行目标检测得到目标物类型, 再利用传感器位姿信息通过空间投影算法确定目标物ID, 从而提高了虚拟信息叠加在真实场景中的匹配度和准确性. 基于此算法实现了智慧物联基础设施维护的增强现实应用, 并对灯杆、垃圾桶等目标物进行了实验. 实验结果表明, 本方法可以在普通智能手机及AR眼镜上运行, 取得了预期效果, 也避免了预制标识物, 降低了对硬件资源的要求.     

A systematic framework for on‐line calibration of a head‐mounted projection display for augmented‐reality systems

Abstract— Augmented reality (AR) is a technology in which computer‐generated virtual images are dynamically superimposed upon a real‐world scene to enhance a user's perceptions of the physical environment. A successful AR system requires that the overlaid digital information be aligned with the user's real‐world senses — a process known as registration. An accurate registration process requires the knowledge of both the intrinsic and extrinsic parameters of the viewing device and these parameters form the viewing and projection transformations for creating the simulations of virtual images. In our previous work, an easy off‐line calibration method in which an image‐based automatic matching method was used to establish the world‐to‐image correspondences was presented, and it is able to achieve subpixel accuracy. However, this off‐line method yields accurate registration only when a user's eye placements relative to the display device coincides with locations established during the offline calibration process. A likely deviation of eye placements, for instance, due to helmet slippage or user‐dependent factors such as interpupillary distance, will lead to misregistration. In this paper, a systematic on‐line calibration framework to refine the off‐line calibration results and to account for user‐dependent factors is presented. Specifically, based on an equivalent viewing projection model, a six‐parameter on‐line calibration method to refine the user‐dependent parameters in the viewing transformations is presented. Calibration procedures and results as well as evaluation experiments are described in detail. The evaluation experiments demonstrate the improvement of the registration accuracy.     

基于直接投射扩散的烟雾阴影实时模拟

为了提高烟雾模拟的真实感,提出了一种基于直接投射扩散的烟雾阴影实时生成算法。该方法将3维烟雾密度场直接投射到2维平面上,并保存于光亮缓存中,首先生成一张能描述阴影浓度信息的阴影纹理;然后为了解决阴影浓度过估计问题,还新颖地采用流体力学领域的扩散方程来修正浓度分布情况;最后,在可编程图形硬件上,采取投影纹理映射技术将阴影纹理投射到场景中的相应表面。实验证明,该方法所需计算开销小,能简单高效地实时生成计算机3维游戏和动画的烟雾阴影效果。     

Event‐triggered distributed model predictive control with optimal network topology

In this paper, we consider a novel iterative DMPC (distributed model predictive control) scheme for linear discrete‐time systems which are connected by network. Every system is dynamically coupled to neighbors. The proposed method can reduce the communication load without degrading performance compared to cooperative DMPC by sensitivity and information topology analysis. The proposed algorithms are applied in a four‐water‐tanks numerical example, and the simulation results show the effectiveness of the proposed algorithms.     

Image secret sharing method with two-decoding-options: Lossless recovery and previewing capability

Visual cryptography scheme (VCS) is a research area in image secret sharing, where one can easily stack shadow images and decode a black-and-white secret image through the human visual system without computation. Although VCS does not provide a competitive reconstruction quality, its stacking-to-see property clearly has the intended applications. To develop the ease of decoding of VCS and simultaneously overcome its weakness, Lin et al. recently proposed a novel two-in-one image secret sharing scheme (TiOISSS) with two decoding options based on VCS and a polynomial-based image secret sharing scheme (PISSS). In this TiOISSS, the first decoding stage has the stacking-to-see property to preview a vague image, and the second decoding stage is to obtain the original gray-level secret image. In this paper, we design a new TiOISSS by combining VCS and PISSS in a different way; in specific, our new scheme reduce shadow image size, and is more suitable for faster transmission within a distributed multimedia system.     

Shadow removal of projected imagery by occluder shape measurement in a multiple overlapping projection system

This paper presents a shadow removal technique for a multiple overlapping projection system. In particular, this paper deals with situations where cameras cannot be placed between the occluder and projection surface. We apply a synthetic aperture capturing technique to estimate the appearance of the projection surface, and a visual hull reconstruction technique to measure the shape of the occluder. Once the shape is acquired, shadow regions on the surface can be estimated. The proposed shadow removal technique allows users to balance between the following two criteria: the likelihood of new shadow emergence and the spatial resolution of the projected results. Through a real projection experiment, we evaluate the proposed shadow removal technique     

Vector projection for face recognition

In this paper, a novel approach for face recognition is proposed by using vector projection length to formulate the pattern recognition problem. Face images of a single-object class are more similar than those of different-object classes. The projection length of a test image vector on the direction of a training image vector can measure the similarity of the two images. But the decision cannot be made by only a training image which is the most similar to the test one, the mean image vector of each class also contributes to the final classification. Thus, the decision of the proposed vector projection classification (VPC) algorithm is ruled in favor of the maximum combination projection length. To address the partial occlusion problem in face recognition, we propose a local vector projection classification (LVPC) algorithm. The experimental results show that the proposed VPC and LVPC approaches are efficient and outperform some existing approaches.     

The Shadow Meets the Mask: Pyramid-Based Shadow Removal

In this paper we propose a novel method for detecting and removing shadows from a single image thereby obtaining a high‐quality shadow‐free image. With minimal user assistance, we first identify shadowed and lit areas on the same surface in the scene using an illumination‐invariant distance measure. These areas are used to estimate the parameters of an affine shadow formation model. A novel pyramid‐based restoration process is then applied to produce a shadow‐free image, while avoiding loss of texture contrast and introduction of noise. Unlike previous approaches, we account for varying shadow intensity inside the shadowed region by processing it from the interior towards the boundaries. Finally, to ensure a seamless transition between the original and the recovered regions we apply image inpainting along a thin border. We demonstrate that our approach produces results that are in most cases superior in quality to those of previous shadow removal methods. We also show that it is possible to easily composite the extracted shadow onto a new background or modify its size and direction in the original image.     

基于曲线投影模型的电子断层三维重构并行算法

大尺度高精度的电子断层三维重构可以获得在更大视角下的生物大分子三维结构的细节信息。但研究尺度的增大给获取高精度重构结果和缩短数据处理时间带来了巨大的挑战。TxBR提出的曲线模型显著提高了重构的精度,但其计算比直线模型更复杂耗时,且在曲线模型下,之前的并行策略不再可行。针对这一问题,提出了一种在GPU平台上实现的针对曲线模型的分块迭代并行算法。通过对曲线模型的研究发现,曲线模型具有一定的空间局域性,利用这种性质提出了一种纵向的分块方式。在算法的实现阶段,提出一个基于页的数据传输策略,从而能够去除冗余的数据传输,减少数据传输带来的时间消耗。实验结果显示,本算法可接近40倍的加速比。     

Real‐Time Human Shadow Removal in a Front Projection System

When a person is located between a display and an operating projector, a shadow is cast on the display. The shadow on the display may eliminate important visual information and therefore adversely affect the viewing experiences. There have been various attempts to remove the human shadow cast on a projection display by using multiple projectors. While previous approaches successfully removed the shadow region when a person moderately moves around or stands stationary in front of the display, there is still an afterimage effect due to the lack of consideration of the limb motion of the person. We propose a new real‐time approach to removing the shadow cast by a person who dynamically interacts with the display, making limb motions in a front projection system. The proposed method utilizes a human skeleton obtained from a depth camera to track the posture of the person which changes over time. A model that consists of spheres and conical frustums is constructed based on the skeleton information in order to represent volumetric information of the person being tracked. Our method precisely estimates the shadow region by projecting the volumetric model onto the display. In addition, employment of intensity masks that are built based on a distance field helps suppress the afterimage of the shadow that appears when the person moves abruptly. It also helps blend the projected overlapping images from different projectors and show one smoothly combined display. The experiment results verify that our approach removes the shadow of a person effectively in a front projection environment and is fast enough to achieve real‐time performance.     

Analog LCOS SLM devices for AR display applications

Liquid crystal on silicon (LCOS) device is a potential candidate for spatial light modulators (SLMs) due to its high resolution and the wide range of tunable phase retardation. Besides the telecom applications, SLM is also very promising for display applications, especially for the augmented reality (AR) displays. In this paper, we will discuss the advantages of analog LCOS SLM compared with the digital one. A 0.6‐in short‐loop sample test result with precise cell gap controlled is discussed. A fast liquid crystal with high birefringence that attains less than 2.5‐ms full‐on–full‐off response time is also introduced. Regarding the computer‐generated hologram (CGH), a new algorithm called multiconstraints angular spectrum algorithm (MASA) is proposed to enhance the image quality of dual‐plane holographic projection.     

Global Illumination Shadow Layers

Computer graphics artists often resort to compositing to rework light effects in a synthetic image without requiring a new render. Shadows are primary subjects of artistic manipulation as they carry important stylistic information while our perception is tolerant with their editing. In this paper we formalize the notion of global shadow, generalizing direct shadow found in previous work to a global illumination context. We define an object's shadow layer as the difference between two altered renders of the scene. A shadow layer contains the radiance lost on the camera film because of a given object. We translate this definition in the theoretical framework of Monte‐Carlo integration, obtaining a concise expression of the shadow layer. Building on it, we propose a path tracing algorithm that renders both the original image and any number of shadow layers in a single pass: the user may choose to separate shadows on a per‐object and per‐light basis, enabling intuitive and decoupled edits.     

Backstepping and Sliding‐Mode Techniques Applied to Distributed Secondary Control of Islanded Microgrids

In this paper, secondary voltage control scheme for a droop‐controlled inverter‐based islanded microgrid is addressed. Motivated by the cooperative control theory of multi‐agent systems, the proposed secondary voltage control is a distributed scheme which uses a simple communication network. Two nonlinear control algorithms are applied to restore the voltage of each distribution generation (DG) to the reference value. The simulation results verify the effectiveness of the proposed secondary voltage control for a prototype microgrid system.     

由多聚集投影进行图象重建

扇形束投影用于单光子发射型ＣＴ中可以较大地提高系统的灵敏度，却带来投影数据截断产生的伪影问题。多聚焦格式采集投影数据是近几年提出的，它可以避免扇形束投影截断问题。针对多聚集投影数据的重建，此文提出了一种新的基于Ｆｏｕｒｉｅｒ级数展开和正则化技巧的近似级数展开算法。该方法推导简单严格。它可应用于平行束和扇形束的重建。新算法在实时可采用快速璃散Ｆｏｕｒｉｅｒ算法和不等距的梯形求积公式。数值实验表明该方