机器人视觉中彩色时变图像光流场计算的综述

本文对机器人视觉中彩色时变图像的光流场计算方法做了全面概述 .彩色时变图像光流场计算的基础是基本等式 ,列举了目前几种基于彩色图像光流场计算方法 ,并提出目前彩色时变图像光流场计算中存在的几个问题 ,总结出今后彩色时变图像光流场计算的发展趋势 。

基于时变图像序列的脉搏信息提取

为获取全面客观的脉诊信息,本文提出一种全新的脉搏信息检测方法—脉搏触觉图像化法。本系统模拟中医脉诊实际,采用软性薄膜加压探头,由单一CCD摄像头采集得到脉搏动态时变图像序列。在算法实现上,从图像整体灰度变化入手,应用图像相关性和图像灰度重心变化分别提取脉搏波形图,并利用图像重心法分析得出不同人在不同取脉压力下的部分脉搏特征。研究结果表明,基于时变图像序列的方法能够有效提取脉搏波的幅度、形态和脉搏频率、节律等信息,为脉搏信息的检测和表征提供了新的手段和方法。

利用点线对应计算彩色时变图像光流场

时变图像光流场计算是当今计算机视觉研究的前沿方向 ,彩色时变图像光流场是光流场计算从灰度图像到彩色图像的推广。利用彩色图像提供的更丰富的光学信息 ,使光流场计算的不适定问题转换成适定问题。文中首先利用图像边缘检测与 Hough变换 ,提取图像的边缘点和边缘线。然后把提取出的边缘点和边缘线分别作为图像的特征点和特征线。最后利用彩色时变图像中的特征点线对应 ,把基于特征的方法和基于光流场的方法结合起来 。

基于色彩和饱和度的彩色时变图像光流场计算

从物体光照模型的角度出发,依据物体的颜色在运动过程中保持不变,表示物体色彩和饱和度的量在运动过程中也不变,提出了基于色彩和饱和度信息的彩色时变图像光流场汁算方法.该方法不仅可以避免RGB颜色模型带来的线性相关问题.而且更符合生物视觉原理.本文用HSV和HLS两种颜色模型计算彩色时变图像的光流场,实验结果表明该算法能够得到较好的计算结果.

一种时变序列轮廓图像运动参数重建方法

针对现有的基于特征场的运动场估计方法对帧间位移比较大时运动参数建立困难的问题,提出了基于目标轮廓图像序列的运动估计理论和参数重建方法.该方法基于水平集方法理论,通过对二维轮廓线的标识处理,对轮廓线的演化运动序列进行了建模,并通过仿真试验进行了验证.本方法可用于重建瞬态目标及形变目标的运动位移、速度和加速度等运动参数检测研究,尤其可用于膛口火焰、爆炸过程分析等动态图像检测领域.

从序列图像计算二次曲线的光流

提出一种二次曲线的整体表示法:空间二次曲线和平面二次曲线的坐标表示法,建立了基于动态灰度图像和基于序列灰度图像的二次曲线光流概念。采用边缘检测、边缘细化和轮廓跟踪等技术,获得了具有单像素宽的边缘点集,提出用分段二次曲线描述边缘,计算得到了二次曲线的光流。

图像化脉象仪数学建模与脉搏信息提取

为获取脉诊触觉信息,采用绘制有圆形网格点的软性薄膜加压传感探头,由单一CCD摄像头获取脉搏动态图像.在对脉搏图像传感器结构分析的基础上,建立详细的测量原理模型,论证了该图像化脉象仪获取脉搏多维信息的可行性.在此模型基础上,应用图像处理的方法提取得到脉搏波形,并给出定量分析及实验结论.研究表明,本系统能够有效提取多维脉搏特征信息,为中医诊断客观化和科学化提供了一种新的手段和方法.

网格图像法提取多维脉搏特征信息

利用前期研制的基于单CCD(charge coupled device,电子耦合器件)的脉搏多维信息测量装置,采集得到脉搏动态时变图像序列。重新设计传感器触头为绘有网格点的软性双层薄膜结构,在此基础上,建立了测量原理模型,论证了该装置获取脉搏多维信息的可行性。随后,通过对网格点图像的处理,成功提取了脉搏波的形态、频率、节律及脉宽信息,所得结果与测量模型分析一致。研究表明,该系统能够有效提取多维脉搏特征信息,为脉搏信息的检测和表征提供了一种全新的手段和方法。

其他

TP242.62 2002021254手眼立体视觉的算法与实现=Algorithm for hand- eye stereo vision and implementation[刊,中]/熊春山,黄心汉,王敏(华中科技大学控制系.湖北,武汉(430074))∥机器人.—2001,23(2).—113-117,122基于直接将图像坐标映射到机器人参考坐标的"黑箱"思想。

Review of Remotely Sensed Imagery Classification Patterns Based on Object-oriented Image Analysis

With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remotely sensed information classification pattern and a literature review of related research progress, this paper sums up 4 developing phases of object-oriented classification pattern during the past 20 years. Then, we discuss the three aspects of method- ology in detail, namely remotely sensed imagery segmentation, feature analysis and feature selection, and classification rule generation, through comparing them with remotely sensed information classification method based on per-pixel. At last, this paper presents several points that need to be paid attention to in the future studies on object-oriented RS in- formation classification pattern: 1) developing robust and highly effective image segmentation algorithm for multi-spectral RS imagery; 2) improving the feature-set including edge, spatial-adjacent and temporal characteristics; 3) discussing the classification rule generation classifier based on the decision tree; 4) presenting evaluation methods for classification result by object-oriented classification pattern.

Lamb Wave Arrival Time Extraction Using Hilbert-Huang Transform for Improved Tomography Image

Travel time Lamb wave tomography has been shown to be an effective nondestructive evaluation （NDE） technique for plate-like structures. The methods used previously to extract arrival times of the fastest or multi Lamb wave modes are mostly based on various timefrequency methods such as Wigner-Ville distribution, shorttime Fourier transform, and recently explored wavelet transform（WT）. Frankly speaking, uses of these signal processing methods improve the accuracy of the arrival time extraction to a great extent relative to directly extract arrival times in time-domain from Lamb waveforms. Hilbert-Huang transform（HHT） is also an efficient way for analyzing and processing non-stationary signals. The resolving power of time and frequency is restricted from Heisenberg principle in wavelet analysis, while in HHT, the time resolving power is precise and steady, and frequency resolving power is adaptive according to signal intrinsic characteristics. Conclusion can be made that the HI-IT method is more adaptive than WT anal;/sis in ~.!~M~ zing non-stationary signals. Based on the abo~, ~tiaf method is attempted to extract arrival times from Lamb waveforms in this paper. The Lamb wave tomography images generated with arrival times from HHT method were compared with those of WT. The results show that the new method improves the quality of tomography image, which demonstrates the applicability of HHT method in extracting arrival times of Lamb waves.

Theoretical and Experimental Analysis of Vortex Origin

Several investigations refer to the issue of creation and identification of vortices in flows with different regime and presence of obstacles. Reasons have to do with the crucial role that vortices play in nature and industrial processes （sediment transport, mixing, radiation, noise, etc.）. Despite the contributions, further work is needed in order to perform more analysis of the mathematical arguments used to explain this phenomenon. In this idea order, the paper presents some advances in mathematical analysis and experimental results. In the first section, we do a description of the fluid motion from a fractional view through a sequence of three steps： Darcy＇s law, Navier-Stokes equations and Reynolds equations. Next, a representation of the temporal change of kinetic energy is found, which allows the possibility of the two signs. We obtain a description of the process of vortex creation. A length that represents the transition between flow and vortex intensity is found; then a succession of lengths is established that allows scaling from micro to macro. In the second section, experimental results are present; we consider vortex creation and its detection upstream of a bed form similar to that found in rivers, installed in an open channel, equipped with a water circulation system. For vortex detection, a methodology based on the particle image velocimetry PIV technique is proposed. So, we fulfill two objectives： vortex identification and its passage frequencies behind the bed form installed in the channel. Such procedure allows a computer process time reduction in vortices identification task.

Temporal and spatial analysis of changes in snow cover in western Sichuan based on MODIS images

We developed a method for analyzing the change in snow cover using MODIS imagery.The method was applied to images of western Sichuan Province,China taken between 2002 and 2008.The model for extracting data on snow cover from MODIS images was created by spectral analysis.The multi-temporal snow layers were used to evaluate the temporal and spatial change in the area under snow cover between 2002 and 2008 using overlay and statistical analysis in ARCGIS.The majority(60.4%) of western Sichuan was rarely covered by snow and only 0.3% was covered by perennial snow in 2002.Snow cover was pri-marily distributed in Garzê and Aba.The area under snow cover was significantly and negatively correlated with the average monthly temperature and rainfall in 2002.The largest area under snow cover was measured in 2006 and the smallest was in 2007.Similarly,the area of snowmelt was the highest in 2006 and lowest in 2007.In general,the elevation of the snow line in-creased throughout the period 2002-2008;however,the elevation decreased in some years.Our results provide an important insight into the distribution of snow in this region,and may be useful for climate modeling and predicting the availability of water resources and the occurrence of floods and droughts.