炉顶红外摄像装置在新钢6号高炉上的安装及应用

阐述了高炉炉顶红外摄像装置的安装及应用。该装置对及时了解和掌握高炉炉喉的料面情况、煤气流的分布状况，对指导高炉操作、维护炉况顺行和稳定，改善各项技经指标，发挥了重要作用。     

关于中国加入WTO后影视高等教育体系的构想

关于中国加入WTO以后,如何适应新的形势和面对新的竞争,从而构建新的影视高等教育体系?本文从以下三个方面进行了论述:21世纪是彩色读图时代,影视知识技术是人才所必备的三大基本知识技术之一;中国的影视教育必须构建学历教育、职业技能教育和成人继续教育相结合的国民教育体系以及四合一的教育教学模式和产学研相结合的人才培养体制及其运行机制。     

感光测定在航空摄影图像处理中的应用

阐述了感光测定曝光条件确定原理和方法,讨论了感光测定在航空摄影曝光、影像质量控制、药液补充量控制、工作药液性能检测等航空摄影过程中的应用。     

Sky Based Light Metering for High Dynamic Range Images

Image calibration requires both linearization of pixel values and scaling so that values in the image correspond to real‐world luminances. In this paper we focus on the latter and rather than rely on camera characterization, we calibrate images by analysing their content and metadata, obviating the need for expensive measuring devices or modeling of lens and camera combinations. Our analysis correlates sky pixel values to luminances that would be expected based on geographical metadata. Combined with high dynamic range (HDR) imaging, which gives us linear pixel data, our algorithm allows us to find absolute luminance values for each pixel—effectively turning digital cameras into absolute light meters. To validate our algorithm we have collected and annotated a calibrated set of HDR images and compared our estimation with several other approaches, showing that our approach is able to more accurately recover absolute luminance. We discuss various applications and demonstrate the utility of our method in the context of calibrated color appearance reproduction and lighting design.     

Learning Natural Colors for Image Recoloring

We present a data‐driven method for automatically recoloring a photo to enhance its appearance or change a viewer's emotional response to it. A compact representation called a RegionNet summarizes color and geometric features of image regions, and geometric relationships between them. Correlations between color property distributions and geometric features of regions are learned from a database of well‐colored photos. A probabilistic factor graph model is used to summarize distributions of color properties and generate an overall probability distribution for color suggestions. Given a new input image, we can generate multiple recolored results which unlike previous automatic results, are both natural and artistic, and compatible with their spatial arrangements.     

Cavitation characteristics of pit structure in ultrasonic field

Bubble collecting, bubble holding and micro-bubble ejecting characteristics of pit structure and the influence of cavitation bubble on the development of erosion pit are investigated by means of high-speed photography experiments. Pits tend to collect and hold wandering cavitation bubbles. The air holding phenomenon of pits can be a destination of the incubation period in the process of cavitation erosion. The holding bubble tends to eject micro-bubbles from the top of holding cavitation bubble, making the pit a source of nuclei. With bubbles being held in pits, the diameters of pits increase rapidly. But in the given experiment condition, there is a specific stable value beyond which the diameter of pits will not increase. This characteristic will be helpful in understanding and predicting the cavitation erosion process. Supported by the National Basic Research Program of China (“973” Program) (Grant No. 2007CB714105) and the National Natural Science Foundation of China (Grant No. 50539060)     

空地融合的城市道路基础设施数字化技术研究

城市道路基础设施三维模型的重构,在城市道路BIM应用与数字化领域具有重大意义;针对城市交通基础设施数字化重构的需求,对车载激光扫描与无人机倾斜摄影采集技术进行综合运用,提出一套从信息采集、空地点云配准、点云分割到三维重构的完整技术方法;首先使用车载激光扫描技术和无人机倾斜摄影技术对交通基础设施信息进行采集,并使用运动恢复结构算法(SfM,structure from motion)生成基础设施空地点云;其次使用迭代最近点法(ICP,iterative closest point)对空地点云进行精配准,然后利用基于PointNet网络的方法对融合点云进行语义分割;最后对分割出的交通基础设施对象进行三维重构;提出的空地融合的城市交通基础设施数字化技术能够高效地实现交通基础设施重构,为城市交通基础设施数字化提供基础、为后续交通专业领域的应用研究提供便利.     

深度学习屈光检测方法研究

屈光不正是一种非常常见且对视功能发育有严重危害的眼科问题。准确与方便的屈光检测技术,对于及时发现屈光不正问题以及采取相应措施进行干预具有非常重要的意义。目前的屈光筛查设备虽然能较快进行屈光检测,但主要存在两个问题：检测准确度较低,对被测者配合度要求较高。因此,提出一种新的屈光检测方法,此方法使用基于偏心摄影验光原理的光学系统获取人脸面部近红外图像,使用图像处理技术对面部近红外图像进行处理,得到左右瞳孔图像和瞳孔位置信息,使用提出的结合了深度可分离卷积和SE模块的混合数据多输入神经网络模型进行训练与屈光度的计算。与传统偏心摄影验光原理的屈光检测方法相比,此方法有望随着数据集的扩增而达到更高的准确度,并且此方法将瞳孔位置信息作为模型的输入,可以解决传统算法对被测者配合度要求较高的问题。该研究是对屈光检测新方法的一种有益探索,使用此方法有利于屈光筛查更便利地进行,为实现非接触自助式的屈光筛查提供基础。     

基于对抗深度学习的无人机航拍违建场地识别

对违建场地的检测方法主要是通过人工对无人机航拍视频进行检查,存在检测精度低、识别性能差、工作效率低的问题。提出一种结合空间变换网络与Fast RCNN的生成对抗网络ASTN-Fast RCNN,通过深度学习与无人机航拍视频相结合自动识别检测处在建设初期的违建场地。将空间变换网络作为生成器,生成Fast RCNN目标检测器难以识别的旋转形变样本,并通过目标检测器与生成器的对抗式训练,提高检测器的鲁棒性。实验结果表明,该方法能够有效提高对无人机航拍违建场地的识别性能。     

Photo Noise

Like past avant-garde movements, glitch and noise in the twenty-first century are used to reveal the materiality of the medium. But instead of providing insight or clarity into the politics or social conditions of a technology, they demarcate broader conditions of opacity and blockage, contributing to what Jodi Dean has called ‘communicative capitalism’. The work of German photographer Thomas Ruff alongside the Düsseldorf School, New Photography and JPEG technology are used in this article to illustrate this tendency as a move away from meaning and toward visual noise and communicative breakdown. I use three core analytic registers: the deliberate failure to adhere to visual norms, communicative failure and machine failure and breakdown. Ruff’s work uses visual noise as art to at once reaffirm pervasive conditions of breakdown, failure and decline in high-tech global capitalism, while simultaneously providing a temporary reprieve from these conditions through an emergent form of visual beauty.