基于视差和帧差的图割优化运动目标分割算法

提出一种基于视差和帧差的图割优化运动目标分割算法,在运动目标分割过程中,利用能量函数优化方法得到较为准确的区域视差,同时在此基础上将视差和帧差特征采用图割算法的能量函数进行融合,以此提高前景目标分割的准确性。实验结果表明该方法当区域视差的优化受到灰度因素的影响时,利用图割结合视差和帧差特征能够有效地减少视差优化不够准确的区域被检测为前景目标的可能性,同时也能填补大多数帧差分割的空洞,增强了分割结果的稳定性。     

基于图像差异度的太阳像二值化算法研究

图像二值化是数字图像处理系统中基本而关键的技术,阈值分割是实现二值化的重要途径,假定图像的目标与背景是可以分离且存在一定差异的,则基于图像中目标和背景与原图像的差异,建立恰当的差异度公式。提出相应的算法,并对太阳像进行闽值分割。试验结果表明,与一些传统方法相比,该方法能很好地区分目标和背景,得到了较好的二值化处理效果。     

一种基于FPGA的快速视频背景分割方法

背景的有效分割是实现动目标检测和识别的基础.针对目前众多算法在进行分割时面临的算法复杂度高和占用存储空间过大的问题,在对监视视频序列研究的基础上,使用低成本的Spartan3系列的FPGA平台,以小于16Mbit的存储空间,实现了对视频序列静态场景即时重建.     

熔石英玻璃和白宝石晶体激光损伤的研究

研究不同实验条件对熔石英和白宝石激光损伤阈值和损伤形貌的影响 ,获得了一些有用的实验结果 ,对相应的损伤机理作了分析。同时对熔石英的抗激光加固也进行了研究。结果表明 ,激光预辐照和酸侵蚀处理使熔石英的激光损伤阈值分别提高 70 %和 80 %以上     

短沟Trench MOSFET阈值电压解析模型

传统MOS器件的阈值电压模型被广泛地用于分析Trench MOSFET的阈值电压,这种模型对于长沟道和均匀分布衬底的MOS器件来说很合适.但是对于Trench MOSFET器件来说却显现出越来越多的问题,这是因为Trench MOSFET的沟道方向是垂直的,其杂质分布也是非均匀的.本文基于二维电荷共享模型,给出了Trench MOSFET的一种新的阈值电压解析模型,该模型反映了器件的阈值电压随不同结构和工艺参数变化的规律,模型的结果和器件仿真软件Sivaco TCAD的仿真结果吻合较好.该模型较好地解决了以往所用的Trench MOSFET阈值电压模型计算不准确的问题.     

深度学习算法在颈动脉超声图像斑块分割中的应用研究

近年来,随着计算机技术的进步和数据集的大规模化,越来越多的人把计算机视觉技术应用到超声医学图像中.但在超声图像方面却存在低准确度且不稳定产生的模糊、伪影等使现有算法对模糊、噪声图像误判较高.另外由于病例过多,人为的去检测和识别斑块过于繁琐.为了缓解这些问题,提出了采用inception的网络结构方法快速准确地获取高噪声...     

一种适用于DCO-OFDM系统的DFT信道估计算法

针对直流偏置光正交频分复用系统中传统离散傅里叶变换(DFT)信道估计算法运算复杂度高和循环前缀(CP)内存在非有效信道系数的问题,提出厄米特对称的DFT(H-DFT)阈值改进信道估计算法.首先,根据信道时域响应变换到频域满足厄米特对称的性质,只需对有效子载波的信道频域响应做厄米特对称即可获得全部子载波的信道频域响应;其...     

基于分水岭算法的电感激光热成像图像分割

激光热成像是一种检测电感微裂纹的新方法,但批量自动检测时电感彼此靠近易导致定位错误和误检.根据激光扫描和热成像检测过程分析图像特征,提出求取温度梯度图并利用次大值滤波消除其激励非均匀性,采用形态学操作断开样品粘连处并去除干扰噪声点;通过距离变换结合分水岭算法得到电感图像分割结果.实验结果表明:该方法实现了对批量铁氧体电...     

High speed VLSI architecture for improved region based active contour segmentation technique

Active contour segmentation is an important stage in image analysis applications. In this article, an improved region based active contour segmentation is proposed. The proposed active contour model speeds up the contour convergence by up to 40% while maintaining the advantages of a local region based active contour model by reducing the number of iterations. Moreover, we propose a low-complexity pipelined VLSI architecture for improved region based active contour model targeting FPGA and 90 nm ASIC platforms. The proposed pipelined design offers an increased speed of operation. Its complexity is independent of the size of image.     

Automatic segmentation of color images with transitive closure

In this paper, a mask based automatic segmentation algorithm for color images which uses pixel similarity has been presented. Main concept of the algorithm relies on spatial mask for course segmentation and the Warshall's transitive closure (TC) computation algorithm for region merging. Although the proposed spatial mask approach reduces the computational burden required for segmentation or clustering techniques such as seeded region growing (SRG) or fuzzy c-means (FCM) in which user supplied parameters are essential, it has over segmentation drawback. Therefore, the transitive closure algorithm, which uses adjacency and similarity matrix associated to undirected graph of the over segmented image, has been employed to merge the regions. After comparing to existing methods, the obtained experimental results confirmed that the color images as well as gray level images could be segmented with considerable accuracy. Also computational complexity of image segmentation is significantly reduced. Furthermore, there is no need any user supplied parameter such as the number of clusters or seed points.