Video object segmentation in rainy situations based on difference scheme with object structure and color analysis

A scheme based on a difference scheme using object structures and color analysis is proposed for video object segmentation in rainy situations. Since shadows and color reflections on the wet ground pose problems for conventional video object segmentation, the proposed method combines the background construction-based video object segmentation and the foreground extraction-based video object segmentation where pixels in both the foreground and background from a video sequence are separated using histogram-based change detection from which the background can be constructed and detection of the initial moving object masks based on a frame difference mask and a background subtraction mask can be further used to obtain coarse object regions. Shadow regions and color-reflection regions on the wet ground are removed from the initial moving object masks via a diamond window mask and color analysis of the moving object. Finally, the boundary of the moving object is refined using connected component labeling and morphological operations. Experimental results show that the proposed method performs well for video object segmentation in rainy situations.     

SE-PSNet: Silhouette-based Enhancement Feature for Panoptic Segmentation Network

In this work, we propose a panoptic segmentation model that integrates bottom-up and top-down methods. Our framework is designed to guarantee both the performance and the inference speed. We also focus on improving the quality of semantic and instance masks. The proposed auxiliary task with the silhouette-based enhanced features can help the model improve the prediction quality of mask contours. Additionally, we introduce a new mask quality score intending to solve the occlusion problem. The model has less chance of ignoring small objects, which often have lower confidence scores than larger objects behind them. The results show that the proposed mask quality score can better distinguish the priority of objects when the occlusion occurs. We demonstrate the results of our work on two datasets: the COCO dataset and the CityScapes dataset. Via our approach, we obtained competitive results with fast inference time.     

基于点标注的弱监督实例分割

实例分割,又名同时检测和分割（simultaneous detection and segmentation）,需要标注像素级别的实例掩膜用于训练。然而,这种标注工作需要非常细致的人力劳动,费时费力。本论文提出只使用每个目标实例的单点标注,使得标注成本大大降低。本文提出的模型包括两个模块:基于外观信息和相邻包围框投票的框校验模块,以及基于推断掩膜的上下文信息的区块校验模块。这种设计保留了像素级别的实例信息,有助于抑制单纯图像分割模型训练过程中的误差累积。本文使用弱监督和半监督训练的实验来验证本工作的有效性,比现有方法取得更高的实例分割性能。      

基于跨模态空间匹配的多模态肺部肿块分割网络

现有多模态分割方法通常先对图像进行配准,再对配准后的图像进行分割.对于成像特点差异较大的不同模态,两阶段的结构匹配与分割算法下的分割精度较低.针对该问题,该文提出一种基于跨模态空间匹配的多模态肺部肿块分割网络(MMSASegNet),其具有模型复杂度低和分割精度高的特点.该模型采用双路残差U型分割网络作为骨干分割网络,...     

Binary and phase shifting mask design for optical lithography

The authors propose a number of pre-distorted mask design techniques for binary and phase-shifting masks. Their approach is based on modeling the imaging mechanism of a stepper by the Hopkins equations and taking advantage of the contrast-enhancement characteristics of photoresist. Optimization techniques such as the branch and bound algorithm and simulated annealing algorithm are used to systematically design pre-distorted masks under incoherent and partially coherent illumination. Computer simulations are used to show that the intensity contour shapes and developed resist shapes of their designed mask patterns are sharper than those of conventional masks. The designed phase-shifting masks are shown to result in higher contrast as well as sharper contours than binary masks. An example of phase conflicting masks designed with the algorithm is shown to outperform a simple intuitive design. This example indicates that a fairly general design procedure consisting of alternating phase shifts and their optimized phase-shift masks is a viable candidate for future phase-shifting mask design     

Layered moving-object segmentation for stereoscopic video using motion and depth information

A novel layered stereoscopic moving-object segmentation method is proposed in this paper by exploiting both motion information and depth information to extract moving objects for each depth layer with high accuracy on their shape boundary. By taking a higher-order statistics on two frame-difference fields across three adjacent frames, the computed motion information are used to conduct change detection and generate one motion mask that consists of all the moving objects from all the depth layers involved at each view. It would be highly desirable, and challenging, to further differentiate them according to their residing depth layer to achieve layered segmentation. For that, multiple depth-layer masks are generated using our proposed disparity estimation method, one for each depth layer. By intersecting the motion mask and one depth-layer mask at any given layer-of-interest, the moving objects associated with the corresponding layer are then extracted. All the above-mentioned processes are repeatedly performed along the video sequence with a sliding window of three frames at a time. For demonstration, only the foreground and the background layers are considered in this paper, while the proposed method is generic and can be straightforwardly extended to more layers, once the corresponding depth-layer masks are made available. Experimental results have shown that the proposed layered moving-object segmentation method is able to segment the foreground and background moving objects separately, with high accuracy on their shape boundary. In addition, the required computational load is considered fairly inexpensive, since our design methodology is to generate masks and perform intersections for extracting the moving objects for each depth layer.     

Active Mask Segmentation of Fluorescence Microscope Images

We propose a new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns. It combines the (a) flexibility offered by active-contour methods, (b) speed offered by multiresolution methods, (c) smoothing offered by multiscale methods, and (d) statistical modeling offered by region-growing methods into a fast and accurate segmentation tool. The framework moves from the idea of the “contour” to that of “inside and outside,” or masks, allowing for easy multidimensional segmentation. It adapts to the topology of the image through the use of multiple masks. The algorithm is almost invariant under initialization, allowing for random initialization, and uses a few easily tunable parameters. Experiments show that the active mask algorithm matches the ground truth well and outperforms the algorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively.      

一种适用于数字微镜无掩模光刻的图形拼接方法

针对数字投影光刻技术大面积图形曝光的需求,提出了一种基于灰度模板调制的图形拼接方法,包括图形分割、模板设计、子图形灰度调制、子图形曝光4个步骤。图形曝光前,需要将曝光图形分割为多帧大小为1024pixel×768pixel的多个子图形,然后每个子图形与对应模板相乘,实现曝光子图形的预处理。基于数字微镜(DMD)对灰度图形的调制原理,设计了可行的边界灰度调制模板。给出了图形分割的基本方法以及模板设计的原则。计算机仿真实验展示了图形拼接的过程。实验结果表明,该方法能较好地解决大面积图形曝光存在的拼接问题,改善了图形刻蚀的质量。     

采用边界评价的红外视频运动目标时空域分割方法

为了在红外视频中准确分割运动目标,提出了一种基于边界评价的红外运动目标时空域分割的新方法。首先,利用运动目标在时域差分图像中的空洞效应,提取出最有意义运动目标种子点。重点是运动目标的空间分割,利用种子区域整体与局部的关系,在提取出的种子上进行区域生长,可以得到不同生长阈值下的运动目标分割掩膜。为确定最佳生长阈值,提出了一种无需先验知识的红外目标分割掩膜边界评价准则,并采用分割-评价-再分割-再评价的循环迭代模式,利用由粗到精的搜索方法,找出最佳的生长阈值,同时得到最佳的运动目标分割掩膜。实验证明,所提出的方法能在红外视频中准确分割出运动目标区域,效果良好,性能鲁棒。     

掩模的矩阵乘法表示及其应用

通过对掩模的作用原理进行研究,首先给出了行列成比例的二维掩模的矩阵乘法表示,进而得到了掩模的矩阵乘法实现方法,该方法不仅提高了掩模实现的速度,而且避免了处理图像时的加边运算;其次,提出了基于边界的掩模概念,并给出了相应的矩阵乘法表示,在保持原图像大小不变的前提下,避免了算术均值掩模处理后图像的黑边现象;最后,仿真实验验证了以上结论的正确性。尽管以上结论是针对行列成比例的掩模得到的,但仍不失一般性,因为大部分的掩模均可转化为行列成比例的掩模的和或差。     

Fabrication of Flexible Binary Amplitude Masks for Patterning on Highly Curved Surfaces

This paper describes soft lithography methods that expand current fabrication capabilities by enabling high‐throughput patterning on nonplanar substrates. These techniques exploit optically dense elastomeric mask elements embedded in a transparent poly(dimethylsiloxane) (PDMS) matrix by vacuum‐assisted microfluidic patterning, UV–ozone‐mediated irreversible sealing, and chemical etching. These protocols provide highly flexible photomasks exhibiting either positive‐ or negative‐image contrasts, which serve as amplitude masks for large‐area photolithographic patterning on a variety of curved (and planar) surfaces. When patterning on cylindrical surfaces, the developed masks do not experience significant pattern distortions. For substrates with 3D curvatures/geometries, however, the PDMS mask must undergo relatively large strains in order to make conformal contact. The new methods described in this report provide planar masks that can be patterned to compliantly compensate for both the displacements and distortions of features that result from stretching the mask to span the 3D geometry. To demonstrate this, a distortion‐corrected grid pattern mask was fabricated and used in conjunction with a homemade inflation device to pattern an electrode mesh on a glass hemisphere with predictable registration and distortion compensation. The showcased mask fabrication processes are compatible with a broad range of substrates, illustrating the potential for development of complex lithographic patterns for a variety of applications in the realm of curved electronics (i.e., synthetic retinal implants and curved LED arrays) and wide field‐of‐view optics.     

基于差异混合掩码与混沌Gyrator变换的光学图像加密算法

为了提高光学加密技术的抗选择明文攻击能力与未知攻击下的解密质量,该文设计了基于差异混合掩码与混沌Gyrator变换的光学图像加密算法。将输入明文转换成相应的快速响应码;考虑明文特性,根据Logistic映射,生成一个混沌相位掩码;同时,联合径向希尔伯特与波带片相位函数,将其与混沌相位掩码融合,构建了混合相位掩码;随后,利用明文图像迭代Logistic映射所输出的随机序列来计算Gyrator变换的旋转角度,结合混合相位掩码,对快速响应码进行调制,形成Gyrator频谱;引入等量分解技术,将Gyrator频谱分割为两个分量,并设置不同的阶数,形成两个差异螺旋相位掩码;利用奇异值分解(SVD)方法,将其中一个Gyrator频谱分量进行处理,并联合两个差异螺旋相位掩码,分别对其相应的正交矩阵进行编码;最后,通过组合编码后的正交矩阵与对角矩阵,基于可逆SVD技术,输出加密密文。理论分析了所提算法抵抗明文攻击和裁剪攻击的能力,以及加密结果针对密钥变化的敏感性水平。实验结果验证了所提算法拥有良好的安全性能。     

Null holographic test structures for the measurement of overlay andits statistical variation

Results are presented on the use of null wire segment holograms for the in-line assessment of mask alignment errors in the integrated circuit fabrication process. Process variations are detected by measuring the light intensity generated by a hologram designed to project a null image. To detect alignment errors, the mask for the wire segment hologram (WSH) is distributed between two mask layers. If the two sets of diffracting structures defined by the masks are transferred to the wafer with perfect registration, the result is an area of light cancellation (null) in the image plane. Increased mask misalignment leads to imperfect wavefront cancellation, which is manifested as an increase in light intensity in the null region. In order to characterize misalignment under controlled conditions, the two portions of the holographic test structure were initially recombined into a single structure but with intentional misalignment between the two portions designed into the mask. The technique was then used to characterize the alignment errors between two separate masks with the actual fabricated offsets measured using atomic force microscopy. Initial results indicate the technique is capable of resolving 0.1-μm mask misalignment for a 1-μm minimum feature process     

CVD金刚石薄膜RIE掩模技术研究

金铡石薄膜反应离子刻蚀（RIE）必须选用硬掩模，其于掩刻蚀选择比和掩模图形化加工特性考虑，镍和镍钛合金掩模是较好选择，其中，NiTi合金薄膜具有刻蚀选择比高，加工工艺简单，图形化效果好的优势，Ni掩模特别是电镀方法制作的Ni掩模以其精确的尺寸控制能力，理想的多层结构模式和适当的刻蚀选择比而特别适合于精细结构加工的使用，使用上述掩模对金刚石薄膜进行RIE，可以获得线条整齐规则，侧壁平滑陡直的优异加工效果。     

A focus mask for color picture tubes using dipolar and quadrupolar lensing

Post-deflection focus masks can increase the electron-beam transmission in a color picture tube over that achievable by conventional shadow masks. Various focus mask structures are considered here and most attention is given to one in which the electrostatic fields in each mask aperture consist of a dipole and a quadrupole component. A theory of the combination of dipolar deflection and quadrupolar focusing is given. Experiments on small masks are described and their quantitative behavior is evaluated. A demountable focus-mask color tube is described which has a 10-in diagonal flat mask. This has been used to display video and the 50-percent transmission of the focus mask has allowed high brightness operation with screen voltage of only 10 kV.     

掩模制作中的邻近效应

计算模拟了激光束和电子束直写加工的掩模畸变,并分别用理想掩模和有畸变的掩模进行投影光学光刻过程的模拟和比较,讨论了光学邻近效应校正掩模在加工过程中所产生的畸变对传递到最终基片上的图形的影响。模拟分析指出,掩模加工中的邻近畸变应在设计光学邻近校正掩模时予以注意,即在掩模设计时,应把掩模加工中的邻近效应和光刻图形传递过程的邻近效应进行总体考虑,以便设计出最优化的掩模,获得最好的邻近效应校正效果。     

Predicting out-of-plane distortions during X-ray mask fabrication

Sub-0.25 μm technology may require gap settings as small as 10 μm. Consequently, it is of the utmost importance to fabricate masks which do not have large curvature towards the device wafer. In this work, finite element methods are used to predict the out-of-plane shape of the mask blank throughout the fabrication process in order to predict and correct bow (out-of-plane distortion) of mask blanks.     

An automatic segmentation method for moving objects based on the spatial-temporal information of video

The new MPEG-4 video coding standard enables content-based functions. In order to support the new standard, frames should be decomposed into Video Object Planes （VOP）, each VOP representing a moving object. This paper proposes an image segmentation method to separate moving objects from image sequences. The proposed method utilizes the spatial-temporal information. Spatial segmentation is applied to divide each image into connected areas and to find pre~：ise object boundaries of moving objects. To locate moving objects in image sequences, two consecutive image frames in the temporal direction are examined and a hypothesis testing is performed with Neyman-Pearson criterion. Spatial segmentation produces a spatial segmentation mask, and temporal segmentation yields a change detection mask that indicates moving objects and the background. Then spatial-temporal merging can be used to get the final results. This method has been tested on several images. Experimental results show that this segmentation method is efficient.     

Multiple-image encryption based on chaotic phase mask and equal modulus decomposition in quaternion gyrator domain

In order to transmit multiple-image synchronously, this paper introduces an encryption algorithm by combining equal modulus decomposition with quaternion gyrator transform. Firstly, each color image is encoded into a quaternion-valued matrix for a holistic processing. With the chaotic random phase mask, the quaternion gyrator spectrum is obtained. It is subsequently split into a complex-valued interim matrix and the equal modulus decomposition is performed to enhance the security, where the spectrum is divided into two complex-valued masks. Thereafter, the two set of phase masks are respectively superimposed and followed by gyrator transforms. Finally, a real-valued matrix is constructed as the final ciphertext image by splicing the real and imaginary parts together. The phase masks that are generated using the chaotic and real-valued ciphertext are convenient to storage and transmission. Moreover, the initial conditions are closely related with the plaintext images, which makes the cryptosystem achieve high security. Numerical simulations are made to demonstrate the reliability of the proposed cryptosystem.