Development of fan‐shaped tracker for single particle tracking

With the development of super‐resolution fluorescence microscopy, complex dynamic processes in living cells can be observed and recorded with unprecedented temporal and spatial resolution. Single particle tracking (SPT) is the most important step to explore the relationship between the spatio‐temporal dynamics of subcellular molecules and their functions. Although previous studies have developed SPT algorithms to quantitatively analyze particle dynamics in cell, traditional tracking methods have poor performance when dealing with intersecting trajectories. This can be attributed to two main reasons: (a) they do not have point compensation process for overlapping objects; (b) they use inefficient motion prediction models. In this paper, we present a novel fan‐shaped tracker (FsT) algorithm to reconstruct the trajectories of subcellular vesicles in living cells. We proposed a customized point compensation method for overlapping objects based on the fan‐shaped motion trend of the particles. Furthermore, we validated the performance of the FsT in both simulated time‐lapse movies with variable imaging quality and in real vesicle moving images. Meanwhile, we compared the performance of FsT with other five state‐of‐the‐art tracking algorithms by using commonly defined measures. The results showed that our FsT achieves better performance in high signal‐to‐noise ratio conditions and in tracking of overlapping objects. We anticipate that our FsT method will have vast applications in tracking of moving objects in cell.     

内插螺旋立式上行管流场及传热性能的实验研究

通过粒子图像测速流场实验与传热实验相结合，研究了内插螺旋立式上行管的螺旋节距、丝径、中径比等结构参数在不同Re下对流场、阻力及传热性能的影响。结果表明，内插螺旋能够有效扰动和混合管内流体，使管内形成多个纵向旋涡的流体结构、增大管壁附近液体涡量，有利于强化传热。当Re相同时，管内平均流速v、Nu和综合换热性能PEC均随丝径增大而增大，随中径比减小而增大；随节距增大，3种参数均出现增大的趋势，节距大于20 mm后开始减小。管内流体的阻力f随丝径和节距增大而减小，随中径比增大而增大。综合比较，在较低Re时，节距p=20 mm、丝径e=1.6 mm、中径比D/d=0.75时综合传热效果最好。     

Image Super-Resolution Based on Generative Adversarial Networks: A Brief Review

Single image super resolution (SISR) is an important research content in the field of computer vision and image processing. With the rapid development of deep neural networks, different image super-resolution models have emerged. Compared to some traditional SISR methods, deep learning-based methods can complete the superresolution tasks through a single image. In addition, compared with the SISR methods using traditional convolutional neural networks, SISR based on generative adversarial networks (GAN) has achieved the most advanced visual performance. In this review, we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics. Then, we review the improved network structures and loss functions of GAN-based perceptual SISR. Subsequently, the advantages and disadvantages of different networks are analyzed by multiple comparative experiments. Finally, we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.     

Multi-Purpose Forensics of Image Manipulations Using Residual- Based Feature

The multi-purpose forensics is an important tool for forge image detection. In this paper, we propose a universal feature set for the multi-purpose forensics which is capable of simultaneously identifying several typical image manipulations, including spatial low-pass Gaussian blurring, median filtering, re-sampling, and JPEG compression. To eliminate the influences caused by diverse image contents on the effectiveness and robustness of the feature, a residual group which contains several highpass filtered residuals is introduced. The partial correlation coefficient is exploited from the residual group to purely measure neighborhood correlations in a linear way. Besides that, we also combine autoregressive coefficient and transition probability to form the proposed composite feature which is used to measure how manipulations change the neighborhood relationships in both linear and non-linear way. After a series of dimension reductions, the proposed feature set can accelerate the training and testing for the multipurpose forensics. The proposed feature set is then fed into a multi-classifier to train a multi-purpose detector. Experimental results show that the proposed detector can identify several typical image manipulations, and is superior to the complicated deep CNN-based methods in terms of detection accuracy and time efficiency for JPEG compressed image with low resolution.     

Color design of cigarette packaging for reducing smoking rate in youth

Since smokers are becoming younger and younger, it is necessary to curb the tobacco epidemic at a younger age to prevent the devastating damage caused by tobacco products to future generations. This study focuses on the color schemes of cigarette packaging. It aims to find out color schemes of teenage consumers' disgust and apply them to cigarette packaging, which ultimately reduces the desire of purchasing and the smoking rate of young people. First, there were two ways to acquire color schemes. One was to extract the color schemes that can make teenagers disgust and keep them away from cigarette by association of psychological adjectives. The other way was to match achromatic colors with the chromatic colors that teenagers dislike in the questionnaire of 126 colors. Finally, eye movement experiment was used to verify the acquired color schemes meet the expected objectives of this study. A new idea to reduce the smoking rate of teenagers was proposed, and a method for the color design of cigarette packaging was provided.     

采用轮廓特征匹配的红外-可见光视频自动配准

为了精确地配准近平面场景下的红外-可见光视频序列,本文提出了一种基于轮廓特征匹配的自动配准方法,通过迭代匹配目标轮廓特征来解决异源图像中配准特征的提取和匹配难题。首先,采用运动目标检测技术获取目标轮廓,并由曲率尺度空间(CSS)角点检测算法提取轮廓特征点。此后,建立全局形状上下文描述子和局部边缘方向直方图描述子描述特征,从而实现可靠的特征匹配。来自不同时刻的匹配点对被保存在一个基于高斯距离准则的特征匹配库中。最后,为了克服近平面场景中目标深度变化的影响,本文结合前景样本随机抽样策略计算配准矩阵的损失函数,完成对全局配准矩阵的更新。在LITIV数据库上对方法进行实验验证,结果表明本文方法的配准精度优于当前先进的对比方法,在9个测试视频上的平均重叠率误差仅为0.194,与对比方法相比下降了18.5%。基本满足了近平面场景下红外-可见光视频序列配准的精度要求,且具有较高的鲁棒性。     

Colored apparel and its potential influence on heterosexual attraction

The objective of this study is to determine if men would follow the “red effect” when choosing colors for women to wear on a date, and also to determine if the colors that men would wear when going on a date would be the same as the colors that females (their date) would wish them to wear. A set of psychophysical data was generated from this experiment, where participants were asked to rank a set of 10 colored samples based on preference for each question asked. There were three different sets of colored samples. The set of colored samples given to the participant depended on the question. A total of five questions were asked. Scaling analysis was done on the data to organize a set of items according to preferences providing values, an interval scale (Z values), that correspond to the relative perceptual differences among the stimuli. The Z values were graphed to show the general preference of colors for women to wear, and the preference of colors for men to wear. A Spearman's rank-order correlation coefficient (SRCC) was calculated comparing each individual's rank order with the mean rank order for that specific question. An average Spearman's rank order was calculated for each question and each gender in order to determine the variability in answers. Scaling results indicate that men follow the “red effect,” but women preferred to wear other colors such as turquoise, blue, or yellow depending on the outfit. Males and females agreed that no matter the colored bottoms (denim or black), blue was the preferred color top for men to wear. SRCC results showed a lot of variability between individual answers and the mean answer indicating that participants' rankings did not necessarily agree with general color preferences presented in the scaling analysis. While scaling analysis might suggest certain color preferences such as men following the “red effect” and women preferring to wear blue, the poor correlation found using SRCC between the individual answers and the mean rank orders suggests that color preferences for each individual are inherently unique.     

正弦波纹挡板式沉降器内流动特性

采用VOF模型对正弦波纹式入口挡板的重力非均相沉降器内流场进行数值模拟研究。对比了正弦波纹挡板与平挡板的平均流场分布情况，分析了沉降器的轴向流速均一程度（λ₁）随时间演化特性，探究了λ₁和面积加权平均湍流强度（I_a）在沉降器内空间分布特性；引入流场均稳指标USC，研究了冲击间距（L_b/D）对USC的影响。结果表明：正弦波纹挡板作为入口构件可以有效降低返混。在0.84＜L_b/D＜2.17范围内，正弦波纹板沉降器内流场的均一程度整体高于平面挡板；随着L_b/D减小，平挡板沉降器内流场的λ₁基本不变，但正弦波纹挡板沉降器内流场的λ₁降低，且对I_a的影响不明显。对比平挡板，正弦波纹挡板可以有效降低轴向速度的梯度，使返混区面积减小，流场稳定性提高。随着L_b/D增加，USC值呈现多峰值趋势，L_b/D=2.17时正弦波纹板沉降器的USC取得极大值为14.68，较平挡板提高了93.67%。     

基于深度语义分割的多源遥感图像海面溢油监测

针对遥感图像海面溢油区域通常受到斑噪声以及强度不均等因素的影响,从而导致溢油区域监测效果较差的问题,本文引入了深度语义分割的方法,将深度卷积神经网络与全连接条件随机场相结合,形成端对端连接。以Resnet结构为基础,首先通过深度卷积神经网络对多源遥感图像粗分割并作为输入,然后经过改进的全连接条件随机场,利用高斯成对势和平均场近似定理,建立条件随机场形成递归神经网络作为输出。通过多源遥感图像对海面溢油区域进行监测,并利用可见光图像估计溢油区域面积。实验在所建立的多源遥感图像数据集上与其它先进模型进行对比,结果表明本文方法提高了溢油区域的分割精度以及精细细节程度,平均交并比为82.1%,监测效果具有明显地改善。