一种具有人类视觉敏感性的灰度图象滤波器设计

提高图象视觉效果是图象处理的重要任务之一.通过分析人对灰度图象视觉敏感特点,提出了人的视觉敏感性的光滑度、亮度和对比度三个特征参数.不仅减少了运算复杂性,而且改善了视觉敏感滤波器的自适应性.提出了检测图象的视觉敏感性系数的方法.按照这些系数,对图象进行不同水平的滤波,在一定程度上克服了在滤波降噪与保持主要特征之间的矛盾.由于视觉敏感性系数是在滤波实施之前获得的,所以可以与不同的滤波器结合构成不同作用的视觉敏感滤波器.     

HVS模型及其在静止图象压缩质量评价中的应用

图象质量尺度是最优化图象压缩算法参数和提高图象质量的重要依据 .建立在人类视觉模型 (HVS)基础之上的感知质量尺度作为主客观联系的桥梁 ,能有效地反映出人对图象失真在视觉上的感知 .近年来 ,有许多研究者借助人类视觉系统研究中的最新成果 ,深入分析了与图象质量密切相关的视觉感知特性 ,提出了大量效果不错的静止图象压缩感知质量尺度 ,并对视觉感知特性在图象质量尺度中的应用方法进行了较全面的综述 ,揭示了影响其图象质量预测准确性、鲁棒性的主要因素 ,给出了该领域的最新研究成果和未来发展方向 .     

计算机视觉的理论框架研究

1.引言计算机视觉是计算机科学和人工智能的一个重要分支,它是工业生产自动化、机器人智能化、自主车导航、目标跟踪以及工业检测、医疗和军事应用的核心,也是实现机器智能及第五代计算机的关键因素之一。计算机视觉的研究目的和内容有两个方面,一是用计算机部分实现人类视觉的功能;二是理解人类视觉机理。此二方面使计算机视觉的研究既带有基础性,又有很强的应用特征和工程性质。就人类视觉而言,其功能集中于识别与理解周围环境内对象物坐标、物体间相对位置及颜色等。仿人类视觉机制,利用计算机实现从二维或系列图象中构造、理解三维世界模型的功能就称之为计算机视觉。由此亦知,计算机视觉是一综合性学科,它涉及图象处理、模式识别、图象理解、计算机科学等诸多领域。     

基于图象差的平面大范围视觉伺服控制

为解决大范围偏差的控制问题,将期望图象按给定的角度间隔旋转,离线生成一系列子期望图象。比较实时采集图象与期望子图象间的差异程序可获取目标绕重心的旋转运动参数。纵使图象求重心方法给出的平动参数,实现了在大范围偏差时迅速将摄象机调整到期望位姿。在期望位姿附近结合直接图象反馈方式,实现了基于图象差的平面大范围视觉伺服控制。     

对平面物体多图象数据进行拼接的方法

通过对平面物体拍摄多幅图象,利用视觉标定技术,求出物体在世界坐标系下的坐标,消除了由于摄像头参数不同对图象拼接造成的影响,实现了在世界坐标系下构造实际物体整体的目的;同时利用具有视觉不变性的特征量,解决了拼接时数据的取舍问题.     

计算机视觉

本文首先扼要介绍了正统的计算机视觉理论及其方法.侧重于通用重构中的不适定问题.然后介绍了目前在计算机视觉中出现的一些新技术和新思想,包括三维深度图象技术及主动视觉等,最后提出了几点供同行们参考的意见.     

基于人类视觉智能和粒子滤波的鲁棒目标跟踪算法

与计算机视觉目标跟踪算法遇到的各种困难和瓶颈不同的是,鲁棒视觉目标跟踪仅仅是人类视觉系统的一项基本功能.为此,基于自顶向下的视觉注意机制,构建了一种相应的计算模型,提出一种利用检测视觉注意力焦点区域的方法来模拟人类视觉系统的全局搜索过程,并用粒子滤波跟踪来模拟人类视觉系统的局部跟踪过程的目标跟踪算法.多组对比实验结果表明了所提出的算法在视觉目标跟踪中的优越性.     

计算视觉及其正则化方法

以视觉信息处理的理论研究为中心课题的计算视觉,是当今世界视觉研究的主流.它不仅在生物智能中为我们全面地理解视觉创造了条件,而且在人工智能中为我们开发自动图象分析系统奠定了基础.本文扼要地论述了 Marr 的视觉理论和 Poggio 的视觉正则化方法,目的是要说明计算方法是研究人和机器的视觉信息处理的一个自然方法.     

深度学习在目标视觉检测中的应用进展与展望

目标视觉检测是计算机视觉领域的一个重要问题,在视频监控、自主驾驶、人机交互等方面具有重要的研究意义和应用价值.近年来,深度学习在图像分类研究中取得了突破性进展,也带动着目标视觉检测取得突飞猛进的发展.本文综述了深度学习在目标视觉检测中的应用进展与展望.首先对目标视觉检测的基本流程进行总结,并介绍了目标视觉检测研究常用的公共数据集;然后重点介绍了目前发展迅猛的深度学习方法在目标视觉检测中的最新应用进展;最后讨论了深度学习方法应用于目标视觉检测时存在的困难和挑战,并对今后的发展趋势进行展望.     

一种基于视觉兴趣性的图象质量评价方法

图象质量的正确评价是图象信息工程领域内一项很有意义的研究课题,但现有的图象客观评价方法并不完全符合人眼视觉特性。合理地评价图象质量应充分遵循人眼的视觉特性,但由于受到人的心理、文化背景、周围环境、不同的应用场合等多种因素的影响,人眼对同一幅图象中的不同区域往往具有不同的感兴趣程度,即人眼具有视觉兴趣性特性,该文在充分利用视觉兴趣性特性的基础上,针对只存在一个感兴趣区的图象,提出了一种简化的图象质量     

Weakly Supervised Localization and Learning with Generic Knowledge

Learning a new object class from cluttered training images is very challenging when the location of object instances is unknown, i.e. in a weakly supervised setting. Many previous works require objects covering a large portion of the images. We present a novel approach that can cope with extensive clutter as well as large scale and appearance variations between object instances. To make this possible we exploit generic knowledge learned beforehand from images of other classes for which location annotation is available. Generic knowledge facilitates learning any new class from weakly supervised images, because it reduces the uncertainty in the location of its object instances. We propose a conditional random field that starts from generic knowledge and then progressively adapts to the new class. Our approach simultaneously localizes object instances while learning an appearance model specific for the class. We demonstrate this on several datasets, including the very challenging Pascal VOC 2007. Furthermore, our method allows training any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.     

Spatial color histogram based center voting method for subsequent object tracking and segmentation

In this paper, we introduce an algorithm for object tracking in video sequences. In order to represent the object to be tracked, we propose a new spatial color histogram model which encodes both the color distribution and spatial information. Using this spatial color histogram model, a voting method based on the generalized Hough transform is employed to estimate the object location from frame to frame. The proposed voting based method, called the center voting method, requests every pixel near the previous object center to cast a vote for locating the new object center in the new frame. Once the location of the object is obtained, the back projection method is used to segment the object from the background. Experiment results show successful tracking of the object even when the object being tracked changes in size and shares similar color with the background.     

Object motion tracking using a moving direction estimate and color updates

This paper presents a direction detection and tracking object color update algorithm used to track moving objects that change colors. Different from traditional color-based tracking methods, which use an initial color distribution in order to track objects as long as the object carries the full or partial initial color, this method introduces a color update method used to quickly find the new object color in a new location if the object changes its color partially or completely; the updated color is then used to locate the object. In our algorithm, an initial color pattern is used to track an object using the color. During the tracking, an object’s new location is at first estimated and then used to detect any color change. If the color has changed, a new color pattern is updated based on the changes in the previous color distribution, and then the new color pattern is used to calculate the current location of the object. This algorithm utilizes the property that the movement of an object can be estimated either by using the object’s shadow or by background subtraction. The implementation of our algorithm results in an effective real-time object tracking. The validity of the approach is illustrated by the presentation of experiment results obtained using the methods described in this paper.     

基于特征颜色空间变换的目标跟踪融合算法

利用LUV色彩空间的特性,提出将RGB色彩空间的目标特征描述转换到LUV色彩空间,从而解决目标表面特征变化造成的目标丢失现象,提高目标跟踪算法的鲁棒性。结合卡尔曼滤波和均值漂移跟踪算法的优点,通过一种判别机制将这两个算法得到的跟踪结果进行融合,提高目标跟踪算法的准确性。通过实验证明了新方法的有效性和准确性。     

基于复杂对象分解的相似性计算方法

针对目前常用的相似性度量方法难以满足复杂对象的相似性计算要求,提出了一种基于复杂对象结构分解的分层相似性度量方法。根据属性间的关系紧密程度将复杂对象结构迭代分解,直至基于分解后的简单对象结构的对象可以使用传统相似性度量方法计算对象间的相似性。分解过程可以得到树型结构的对象结构划分。在此基础上,利用树型的对象结构从叶节点向根方向对对象逐层进行相似性度量,最终得到复杂对象的相似性综合度量。结合某大型电信运营商的套餐数据进行应用分析,证明该方法具有较好的性能。     

一种OSD文件系统的设计

OSD文件系统主要承担通用文件系统中存储管理部分的功能,其与通用文件系统存在很大的差异,针对OSD的特征,设计了一种适用于小对象的OsD文件系统,其中提出了“盘区记录表”这种对象ID到对象数据的映射方式和一种新的空间分配策略,同时结合空间分配方式的特点提出了一种主动对象数据调整策略.实验表明,该文件系统在管理小型对象时能有效提高读写性能.     

基于压缩域的视频关注对象提取

针对视频压缩域的对象分割问题,提出了一种视频对象精确提取方法.先将视频对象的颜色空间进行均值偏移和区域生长,得到分块的视频图像.同时对视频编码过程中所产生的运动矢量统计熵值,提取出视频中能引起人眼关注的运动对象.最后利用提出的对象轮廓精确分割方法,提取视频关注对象.实验表明该算法能精确和完整地分割出视频关注对象,并对视频中关注对象的切换、物体的非刚性形变有很好的鲁棒性.     

Function from motion

In order for a robot to operate autonomously in its environment, it must be able to perceive its environment and take actions based on these perceptions. Recognizing the functionalities of objects is an important component of this ability. In this paper, we look into a new area of functionality recognition: determining the function of an object from its motion. Given a sequence of images of a known object performing some function, we attempt to determine what that function is. We show that the motion of an object, when combined with information about the object and its normal uses, provides us with strong constraints on possible functions that the object might be performing     

A spherical representation for recognition of free-form surfaces

Introduces a new surface representation for recognizing curved objects. The authors approach begins by representing an object by a discrete mesh of points built from range data or from a geometric model of the object. The mesh is computed from the data by deforming a standard shaped mesh, for example, an ellipsoid, until it fits the surface of the object. The authors define local regularity constraints that the mesh must satisfy. The authors then define a canonical mapping between the mesh describing the object and a standard spherical mesh. A surface curvature index that is pose-invariant is stored at every node of the mesh. The authors use this object representation for recognition by comparing the spherical model of a reference object with the model extracted from a new observed scene. The authors show how the similarity between reference model and observed data can be evaluated and they show how the pose of the reference object in the observed scene can be easily computed using this representation. The authors present results on real range images which show that this approach to modelling and recognizing 3D objects has three main advantages: (1) it is applicable to complex curved surfaces that cannot be handled by conventional techniques; (2) it reduces the recognition problem to the computation of similarity between spherical distributions; in particular, the recognition algorithm does not require any combinatorial search; and (3) even though it is based on a spherical mapping, the approach can handle occlusions and partial views