Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation

Facial Expression Recognition (FER) is an important subject of human–computer interaction and has long been a research area of great interest. Accurate Facial Expression Sequence Interception (FESI) and discriminative expression feature extraction are two enormous challenges for the video-based FER. This paper proposes a framework of FER for the intercepted video sequences by using feature point movement trend and feature block texture variation. Firstly, the feature points are marked by Active Appearance Model (AAM) and the most representative 24 of them are selected. Secondly, facial expression sequence is intercepted from the face video by determining two key frames whose emotional intensities are minimum and maximum, respectively. Thirdly, the trend curve which represents the Euclidean distance variations between any two selected feature points is fitted, and the slopes of specific points on the trend curve are calculated. Finally, combining Slope Set which is composed by the calculated slopes with the proposed Feature Block Texture Difference (FBTD) which refers to the texture variation of facial patch, the final expressional feature are formed and inputted to One-dimensional Convolution Neural Network (1DCNN) for FER. Five experiments are conducted in this research, and three average FER rates 95.2%, 96.5%, and 97% for Beihang University (BHU) facial expression database, MMI facial expression database, and the combination of two databases, respectively, have shown the significant advantages of the proposed method over the existing ones.     

Processing of Yttria-Alumina Coated Silicon Nitride Slips by Slip Casting

Si₃N₄powders coated with 6 wt% Y₂O₃and 4 wt% Al₂O₃were prepared by coprecipitation. The resulting powders were dispersed in water at different pH values and with addition of various amounts of ammonium polyacrylate (NH₄PA) to produce 32 vol% slips. The influence of the amount of NH₄PA solution added and pH on the rheological properties of 32 vol% coated Si₃N₄slips were studied. In addition, the sintered density of cast samples was determined and related to the degree of slip dispersion. The adsorption of the NH₄PA on the coated particle surface was rather high and the surface became saturated near 0.86 mg/m²at pH 9.2. High NH₄PA concentrations (1.7–3 wt%) were necessary to obtain well dispersed 32 vol% coated Si₃N₄slips at pH 9.2. The best stabilization was obtained with the addition of 2.3 wt% NH₄PA; in this condition, the viscosity reached a minimum value of 35 mPa.s at 100 s^–1. The slip viscosity increased with increasing pH from 9.2 to 10.2. Slips with low viscosities gave a more dense packing of cast samples and consequently higher sintered density values.     

Pullout tests of epoxy-coated reinforcement in concrete

The bond strength and slip of epoxy-coated reinforcing bars in concrete have been evaluated by carrying out single pullout and double pullout tests. In extended single pullout tests, slip measurements were made while tensile force was applied to reinforcing bars embedded in concrete. In double pullout tests, 20 cycles of load were applied at levels of steel stress between zero and 0·5 times characteristic steel strength. Strains were measured by electrical resistance strain gauges glued inside the bars. Both epoxy-coated and uncoated bars were used in the investigation, to obtain comparative results. The strain gradient along the bar was found to be less for the coated reinforcement. In general, the epoxy coating was found to increase slip in bond and thereby reduce the bond performance of coated bars.     

Characterization of the flow behaviour of sausage emulsions with a simple tube viscometer

A specially designed tube viscometer was used to measure apparent viscosity during flow of Bologna type sausage emulsions moving through a pipe. Emulsions varied in fat content (from 21.8 to 44.3%) and in moisture/protein ratio (from 3.7 to 5.6), and the effects of added sodium chloride, sodium diphosphate, starch and blood plasma were investigated in a 36% fat, 3.7 moisture/protein emulsion.
The shear stresses determined as a function of shear rate were fitted by a power law. Yield stress of the emulsions was negligible relative to the applied stress. However, inspection of the flow profiles indicated that considerable slip of the sausage emulsion occurred at the pipe wall. Both emulsion flow and slip contribute to overall flow behaviour, so a kind of effective viscosity is determined. Intrinsic rheological properties and wall slip will both be affected by the composition of the sausage emulsion.     

垂直井两相流动生产测井解释滑动模型

在两相流动模拟实验数据分析的基础上 ,提出油水两相和气液两相流动的滑脱速度的实验关系 ,进而确定垂直井两相流动生产测井解释的滑动模型。现场实际测井资料处理结果表明该模型有很好的应用效果     

浅议斜坡稳定性计算中水压力的作用

理论推导证明了静水压力模式与动水压力模式下地下水作用效果的差异,并且结合前人的研究成果,提出要取得合理的稳定性计算结果,两种水压力模式下所选用的强度参数应有所区分,对于静水压力模式,应取快剪或不排水剪指标;对于动水压力模式,则应取用慢剪或排水剪指标。最后采用一个具体的工程实例验证了结论的合理性。     

海底管道的沉降量计算

根据极限平衡和极限分析方法,建立了软黏土地基土体上海底管道的极限承载力计算公式。当地基处于极限状态时,基础作用于地基的全部荷载应该等于该地基土体的承载能力,根据这一关系式可以推导出海底管道沉降量的计算公式。通过对试验结果的分析,证实所采用的计算方法是可行的。     

贵定露天石灰石矿不稳定边坡的治理

着重讨论了贵定石灰石矿边坡１２２０～１１８０ｍ水平在Ｉ号剖面左右深层不稳定地段的边坡治理方案。推荐方案强调多台阶同时回采，以推迟靠帮，进而推迟可能的表层滑坡治理。还讨论了护坡矿壁回收及该矿其他不稳定地段边坡治理等问题。     

一种新的坡位定量描述方法及其与滑坡发生的关系

滑坡发生与地形因子的关系是区域滑坡静态规律研究的重点,但以往的研究多注重考虑其与反映几何形态的基本地形属性因子(几何形态属性因子)之间的关系,如坡度和坡向等。首先提出一种新的基于子流域内相对位置定量描述坡位(相对位置因子)的方法,并以温州地区瓯江流域1990~2001年发生的滑坡为研究对象,使用证据权法对比滑坡发生与两种不同类型地形因子之间的关系。结果表明,相对位置因子与滑坡发生的相关性大于滑坡危险性评价经常使用的几何形态属性因子;并且滑坡大多发生在定量坡位值较低的区域,这些地区处在下游,遭受流水侵蚀的强度更大、频率更高。