一种面向SAR图像的多窗口道路边缘检测算法

道路作为一种重要地物信息,在城市规划等领域中起着不可替代作用。合成孔径雷达（SAR）具有全天候等成像特点,因此基于SAR图像已有许多道路边缘检测算法。提出一种多窗口道路边缘检测算法,来解决相干斑噪声引起的道路边缘误检率高完整性差等问题。该算法首先以加权局部熵的大小为基础,评估SAR图像中像素点落在道路上的概率,然后以该概率为依据,确定每个像素点多窗口融合的权值。最后,对不同大小窗口的边缘检测结果进行加权融合。通过对不同区域的SAR图像切片进行实验,结果表明加权融合后得到的道路边缘的完整性及对噪声的抑制效果均有所提高。     

结合边缘局部信息的FCM抗噪图像分割算法

针对传统FCM图像分割算法没有充分利用像素点的邻域关系与局部信息,导致算法对噪声敏感,不能准确地分割出弱边缘区域的问题,提出一种结合图像全局信息与边缘局部信息的分割算法.首先引入局部窗口变异系数和邻域灰度相似性2个概念重新设计模糊因子,使其能够更精确地衡量邻域点对中心点的影响程度,降低噪声对分割的影响;然后在分割结果的边缘上选取局部窗口,将边缘局部信息融入分割过程;最后在选取窗口中再分割,等同于在边缘处增加多个更符合局部信息的聚类中心来纠正被错误分类的像素点.实验结果表明,该算法能够有效地消除噪声对分割的影响,同时保留更多图像细节信息.     

一种基于排序阈值的开关中值滤波方法

提出了一种基于排序阈值的开关中值滤波方法以克服图像滤波中去噪与细节保护的矛盾。该方法利用滤波窗口内像素点的排序信息，在极值中值滤波方法的基础上，将受脉冲噪声污染图像中的像素点进一步分为噪声点、边缘细节区和平坦区3种类型。通过对多种图像测试的统计结果，获得合适的分类器参数，然后利用类型判决，进行开关中值滤波，即对噪声点和平坦区进行中值滤波以得到良好的噪声滤除效果，而对边缘细节区不做处理以获得良好的细节保护效果。比较了标准中值滤波、极值中值滤波和本方法的结果。实验结果表明，本方法具有更好的效果。     

一种新型的自适应模糊中值滤波算法

针对传统中值滤波算法不能很好地保护图像细节以及受严重噪声污染时性能急剧下降的情况,提出了一种新型的自适应模糊中值滤波算法。通过比较滤波窗口内像素点的灰度值与像素点灰度值的均值定义了模糊滤波系数,利用此模糊滤波系数对滤波方法进行加权,得到一种加权中值滤波器。通过对小窗口内的灰度值不等于最大灰度值和最小灰度值的像素点的检测自适应调整窗口大小,对超过设定的最大窗口的情况,噪声点的灰度值用四个相邻的已处理的像素点灰度值的均值进行替换。仿真结果表明,新算法具有较好的细节保护能力和较强的去除噪声能力。     

基于相似性噪声检测的边缘保护滤波算法

为了改善受脉冲噪声污染的图像的滤波效果,提出了一种新的滤波算法。该算法包括3个阶段,首先,利用像素点之间的相似性来检测图像中受噪声污染的像素点;然后,将滤波窗口分为8个主要方向来确定边缘方向;最后,针对噪声点进行边缘保护滤波。实验结果表明,在噪声污染度较小的情况下,该算法不仅能准确地检测出噪声点,而且更多地保护了噪声图像的边缘部分以及非噪声点,具有良好的滤波效果。     

基于边缘连续性的边缘检测算法

针对传统的边缘检测算法抗噪能力弱、弱小边缘难以检测以及边缘图像容易出现断层等问题,本文提出了一种新的边缘检测算法。该方法首先对边缘进行提取,然后进行边缘连接。边缘是图像灰度突变的反应,像素点的梯度以该像素点为对称中心,由对称位置灰度有明显变化的像素点的个数加权得到。对梯度较大的像素点计算其方向,通过像素点方向的连续性进行边缘提取。为了克服边缘图像出现断层的缺陷,利用蚁群算法进行边缘连接 。实验结果表明,该方法有较强的抗噪能力,尤其对椒盐噪声,且可以有效地检测出灰度变 化不明显的边缘。     

基于误差修正的自适应边缘保持图像插值

传统插值算法容易产生细节模糊和边缘锯齿效应,而边缘是图像的重要信息,直接影响插值图像的视觉效果。为了解决这一问题,提出了一种新的基于误差修正的自适应边缘保持插值算法。首先将原图像向插值图像进行映射,再定义一个3×3的滑动窗口,用水平和垂直两个模板确定边缘类型,根据边缘类型进行插值,最后对仍未定义像素点用插值误差定理进行处理,总体上对所有像素都进行了分情况插值处理。实验结果表明,本算法有效地保持了图像的边缘信息,能够获得视觉质量较好的插值图像,且算法比较简单,容易实现。     

利用排序聚类的局部滤波框架

针对传统局部滤波框架存在边缘模糊的问题,提出利用排序聚类的局部滤波框架.首先,将局部窗口分为4个子窗口,并且将待处理点放置在4个子窗口的交汇处,从策略上实现保持边缘的目的;其次,通过排序提高类内相似度与类间差异,并利用子窗口内像素值之间的相似性,提出一种排序聚类算法,聚类之后,只利用子窗口内与待处理点相似的像素点进行滤波;最后,取4个滤波结果中与待处理点差异最小的作为最终滤波结果,进一步提高算法保持边缘的能力.基于SSID数据集的实验结果表明,基于该框架的滤波算法有着更高的PSNR和SSIM值;该框架有效地提升了传统局部滤波框架保持边缘与平滑滤波的能力,且具有一定的鲁棒性.     

基于误差修正的自适应边缘保持图像插值

传统插值算法容易产生细节模糊和边缘锯齿效应,而边缘是图像的重要信息,直接影响插值图像的视觉效果.为了解决这一问题,提出了一种新的基于误差修正的自适应边缘保持插值算法.首先将原图像向插值图像进行映射,再定义一个3×3的滑动窗口,用水平和垂直两个模板确定边缘类型,根据边缘类型进行插值,最后对仍未定义像素点用插值误差定理进行处理,总体上对所有像素都进行了分情况插值处理.实验结果表明,本算法有效地保持了图像的边缘信息,能够获得视觉质量较好的插值图像,且算法比较简单,容易实现.     

眼前节组织OCT图像边缘检测及特征角点提取

提出了一种适用于眼前节组织OCT图像的边缘检测算法。该算法在单尺度下用多个结构元素进行边缘检测,根据边缘图像灰阶值的差异性,采用动态自适应权重进行像素点融合;再利用连通域的方法抹去面积小的干扰区域,最终得到多结构元素单尺度边缘检测图像,并在其上通过象限区间有效地提取出了角膜特征角点。仿真结果表明边缘特征明显,较以往边缘检测算法有效避免了OCT图像边缘结果的突变像素点的出现,抹去了干扰区域。因此,提出的特征角点具有较高的准确性。     

Wearable vibrotactile systems for virtual contact and information display

This paper presents a development history of a wearable, scalable vibrotactile stimulus delivery system. This history has followed a path from desktop-based, fully wired systems, through hybrid approaches consisting of a wireless connection from the host computer to a body-worn control box and wires to each tactor, to a completely wireless system employing Bluetooth technology to connect directly from the host to each individual tactor unit. Applications for such a system include delivering vibrotactile contact cues to users of virtual environments, providing directional cues in order to increase situational awareness in both real and virtual environments, and for general information display in wearable contexts. Through empirical study, we show that even a simple configuration, such as eight tactors arrayed around the torso, can be effective in increasing situational awareness in a building-clearing task, compared to users who perform the same task without the added cues.     

Development of a scale for fantasy state in digital games

Digital games appear to motivate players intrinsically. Of various game features, fantasy in particularly plays a crucial role in enhancing motivation and is a key factor in immersion in gameplay. As with its inherent value, fantasy also plays a vital role in distinguishing digital games itself from other media. Despite its significance, fantasy has received little attention, and this concept is still ambiguous to define with any certainty. This study thus aims to create a framework to explore a dimension of fantasy and to develop a scale to measure a state of fantasy in digital games. As a result, four factors were extracted, which were ‘identification’, ‘imagination’, ‘analogy’, and ‘satisfaction’, to account for fantasy state in digital gameplay. Based on these factors, a fantasy scale in digital games (FSDGs) included 16 items was developed.     

An architecture for real-time distributed artificial intelligent systems

This paper introduces a new architecture for a real-time distributed artificial intelligence system: DENIS—a Dynamic Embedded Noticeboard Information System. The fundamental idea underlying the architecture draws heavily upon a distributed human system analogy, as seen, for example, in the workplace. The aim of DENIS is to provide a simple, meaningful means by which autonomous intelligent agents can cooperate and coordinate their actions in order to enhance the reliability and effectiveness of a real-time distributed control system. Based on a human paradigm, the architecture inherently allows for the control of an intelligent agent to be taken over by a human operator, yet still to maintain consistency in the distributed system. The key to the thinking in this new approach is to try to model how humans work together, and to implement this in a distributed architecture. One of the main issues raised is that humans owe much of their flexibility to their ability to reason, not only logically, but also in terms of time.     

A novel vision-based method for 3D profile extraction of wire harness in robotized assembly process

Automating stages for deformable objects in the production line, in which assembling a wire harness into a predefined position is a complex task owing to the specialized characteristics of the objects. Besides a few automatized systems proposed in the other studies to implement this task under simplified setup conditions, a significant portion of this process remains to be completed manually in industrial environments. To construct an automatic wire harness assembly system, the development of a method that can automatically detect the wire harness profile in a 3D environment and, consequently, guide robot arms to implement assembly tasks is indispensable. Therefore, this study presents an approach that satisfies this requirement, which not only proposes a deep learning-based system to detect the wire profile, but also improves the accuracy of the detected results through a correction method according to the depth values of contiguous areas. The verification of the approach in a robot system that highlights its usefulness and practicality demonstrates the potential of the proposed method to replace people and consequently, reduce labour costs in factory environments.     

机器人多指手抓取中的规划问题

在机器人抓取系统中，一般认为需要４种规划器：即策略规划器，触觉规划器，轨迹规划抓取规划器，抓取规划器对成功抓取来说是非常重要的，在抓取规划器中，视觉模块用来把图象变换成物体的描述，接着用抓取模式选择模块把物体的描述换成一系列的控制信号，本文从最优抓取规划和基于专家系统的抓取规划这两个方面，着重从基于专家系统的抓取规划方面对当前机器人多指手抓取规划的研究现状及主要问题进行了深入地剖析。     

Anticipatory routing of police helicopters

We have developed a decision support application for the Dutch Aviation Police and Air Support unit for routing their helicopters in anticipation of unknown future incidents. These incidents are not known in advance, yet do require a swift response. A response might include the dispatch of a police helicopter to support the police on the ground. If a helicopter takes too long to arrive at the crime scene, it might be too late to assist. Hence, helicopters have to be proximate when an incident happens to increase the likelihood of being able to support the police on the ground in apprehending suspects. We propose the use of a forecasting technique, followed by a routing heuristic to maximize the number of incidents where a helicopter provides a successful assist. We have implemented these techniques in a decision support application in collaboration with the Dutch Aviation Police and Air Support. Using numerical experiments, we show that our application has the potential to improve the success rate with a factor nine. The Dutch Air Support and Aviation Police are now using the application.     

Averaging analysis of periodically forced fluid networks

For a lumped parameter model of a flow network driven by a periodic generator, we apply averaging to find an approximate solution and analyze its stability. The approximate solution has three parts: mean flow due to the resistive effects of branches, a time-periodic part due to “inductive” effects, and a mean flow average correction due to the interaction of nonlinear and time varying effects. We present an example that may explain the scenario leading to venous diseases. It is shown that the widening of a branch in a venous network leads to an increase in the AC flow and a decrease in the DC flow through that branch, thus increasing the stress on venous valves, and consequently leading to a further increase in the effective width of the vein.     

Managing commitments in multiple concurrent negotiations

Automated negotiation by software agents is a key enabling technology for agent mediated e-commerce. To this end, this paper considers an important class of such negotiations – namely those in which an agent engages in multiple concurrent bilateral negotiations for a good or service. In particular, we consider the situation in which a buyer agent is looking for a single service provider from a number of available ones in its environment. By bargaining simultaneously with these providers and interleaving partial agreements that it makes with them, a buyer can reach good deals in an efficient manner. However, a key problem in such encounters is managing commitments since an agent may want to make intermediate deals (so that it has a definite agreement) with other agents before it gets to finalize a deal at the end of the encounter. To do this effectively, however, the agents need to have a flexible model of commitments that they can reason about in order to determine when to commit and to decommit. This paper provides and evaluates such a commitment model and integrates it into a concurrent negotiation model.