Infrared-Visible Image Fusion Based on Semantic Guidance and Visual Perception

Infrared-visible fusion has great potential in night-vision enhancement for intelligent vehicles. The fusion performance depends on fusion rules that balance target saliency and visual perception. However, most existing methods do not have explicit and effective rules, which leads to the poor contrast and saliency of the target. In this paper, we propose the SGVPGAN, an adversarial framework for high-quality infrared-visible image fusion, which consists of an infrared-visible image fusion network based on Adversarial Semantic Guidance (ASG) and Adversarial Visual Perception (AVP) modules. Specifically, the ASG module transfers the semantics of the target and background to the fusion process for target highlighting. The AVP module analyzes the visual features from the global structure and local details of the visible and fusion images and then guides the fusion network to adaptively generate a weight map of signal completion so that the resulting fusion images possess a natural and visible appearance. We construct a joint distribution function between the fusion images and the corresponding semantics and use the discriminator to improve the fusion performance in terms of natural appearance and target saliency. Experimental results demonstrate that our proposed ASG and AVP modules can effectively guide the image-fusion process by selectively preserving the details in visible images and the salient information of targets in infrared images. The SGVPGAN exhibits significant improvements over other fusion methods.     

Highly Accurate Visual Method of Mars Terrain Classification for Rovers Based on Novel Image Features

It is important for Mars exploration rovers to achieve autonomous and safe mobility over rough terrain. Terrain classification can help rovers to select a safe terrain to traverse and avoid sinking and/or damaging the vehicle. Mars terrains are often classified using visual methods. However, the accuracy of terrain classification has been less than 90% in read operations. A high-accuracy vision-based method for Mars terrain classification is presented in this paper. By analyzing Mars terrain characteristics, novel image features, including multiscale gray gradient-grade features, multiscale edges strength-grade features, multiscale frequency-domain mean amplitude features, multiscale spectrum symmetry features, and multiscale spectrum amplitude-moment features, are proposed that are specifically targeted for terrain classification. Three classifiers, K-nearest neighbor (KNN), support vector machine (SVM), and random forests (RF), are adopted to classify the terrain using the proposed features. The Mars image dataset MSLNet that was collected by the Mars Science Laboratory (MSL, Curiosity) rover is used to conduct terrain classification experiments. The resolution of Mars images in the dataset is 256 × 256. Experimental results indicate that the RF classifies Mars terrain at the highest level of accuracy of 94.66%.     

精密仪器设备半挂运输列车的振动模态分析

研究了具有牵引悬置装置的精密仪器设备半挂运输列车的振动问题,建立了14 自由度的动力学模型并进行振动模态分析, 在此基础上,计算了某典型半挂运输列车在有阻尼和无阻尼情况下的固有频率和振型.     

颜色视觉匹配中明度阈值的评价

为了对颜色视觉匹配中的明度阈值特性进行评价,采用在阴极射线管显示器上获得的颜色刺激,在5个不同明度的中性色背景下,标准刺激的明度L*从5到95以5个CIELAB单位为变化步长,共对19个不同明度的中性标准颜色进行视觉匹配实验。通过对实验结果的处理和分析,验证了关于颜色刺激视觉辨别明度阈值与背景明度之间相关性的韦伯法则和crispening效应,同时利用颜色视觉匹配数据对基于CIELAB的相关色差公式进行了评价和比较,CIEDE2000具有最好的明度差预测性能,CMC次之,CIELAB和CIE94最差。     

基于人眼视觉特性的火炮内膛图像增强方法

为了提高窥膛图像的观测效果,减小背景和噪声对目标图像的模糊度,根据图像特点提出了一种基于人眼视觉特性的图像增强新方法.该方法根据目标图像与背景、噪声图像特性的差异来进行不同的处理,使待测的疵病图像相对增强,目标图像突出,便于人眼观察.     

基于杂交链式反应的可视化免疫分析检测癌胚抗原

构建了基于杂交链反应的比色免疫分析方法,实现了对肿瘤标志物癌胚抗原的检测。在抗原-抗体的特异性结合作用下,在磁珠表面构建夹心式免疫复合物,进一步结合杂交链式反应(HCR)作为信号放大策略,将染料曙红Y嵌入至DNA长链中。在可见光的照射下,能使反应底液中的四甲基联苯胺(TMB)氧化,发生明显的颜色变化,由无色变为蓝色,且与癌胚抗原的浓度呈正相关性。在最优实验条件下,癌胚抗原的浓度在1 pg/mL^5 ng/mL范围内呈线性变化,检出限为1 pg/mL。     

Acoustic comfort on board ships: An evaluation based on a questionnaire

An initial attempt has been made to understand factors that determine acoustic comfort for cruise ship passengers. Although no literature directly pertinent to the question could be found, use of elements from studies on railways coaches in a questionnaire administered to shipbuilder and sub-contractor professionals on board during sea trials was judged a relevant initial approach. The questionnaire, consisting of closed questions followed by open questions, was drawn up to assess acoustic comfort in relation to others factors (such as temperature or light) and to identify the main conditions causing acoustic discomfort. During two sea trials 100 questionnaires were completed. Acoustics, then temperature, are pointed out as the first two comfort criteria and the priorities for improvement. Creaking and squeaking noises, noise of engines and whistles from HVAC are the main reported causes of annoyance. The results of the investigation demonstrate the prominent role of acoustics in respect of ship-board comfort.     

视觉模式识别网络及光电实现

在形态学网络及改进的Ｈａｍｍｉｎｇ网络基础上，提出视觉模式识别网络及训练算法，形态学网络作为特征提取网络，具有相对图像平移和尺度不变的特性，改进的Ｈａｍｍｉｎｇ网络加速完成特征矢量的分类操作。经过学习的视觉模式识别网络，可完成图像特征的提取，实现相对于图像平移和尺度不变的模式识别，在此基础上，建立了光电视觉模式识别体系，从而实现实时模式识别。     

广角无限视景显示系统后投射屏的设计与研究

根据球面反射镜成像理论,利用改变光轴的方法,推导出了广角无限视景显示系统后投射屏面形的计算公式,完成了后投射屏最佳面形的设计。对后投射屏外表面散射层的材料和厚度进行了探讨,给出了最佳的选择方案。首次通过热吹模具成型法研制了高精度的整体投射屏。通过试验验证,该投射屏满足设计要求。使用该投射屏的广角无限显示系统具有图像清晰、视场角大、纵深感强等优点,同时观察者的视点还可在一定的出瞳范围内移动。     

Preparation and formation mechanism of wood-block-like calcite particles

Pure calcite crystal with different morphologies such as wood-block and spherical aggregates were prepared by a precipitation reaction in the presence of citric acid. The as-prepared products were characterized with scanning electron microscope (SEM) and X-ray diffraction (XRD). The results showed that citric acid obviously influenced the formation of precipitates and the morphology of final products. The formation mechanism of wood-block-like particles was proposed according to theoretical deduction and the proposed growth mode.