Automatic color segmentation algorithms-with application to skintumor feature identification

Two color-image segmentation methods are described. The first is based on a spherical coordinate transform of original RGB data. The second is based on a mathematically optimal transform, the principal components transform (also known as eigenvector, discrete Karhunen-Loeve, or Hotelling transform). These algorithms are applied to the extraction from skin tumor images of various features such as tumor border, crust, hair scale, shiny areas, and ulcer. The results of this research will be used in the development of a computer vision system that will seve as the visual front-end of a medical expert system to automate visual feature identification for skin tumor evaluation     

基于特征提取和多示例学习的图像区域标注

随着web2.0的不断发展,在Flickr等图像共享网站中越来越多的用户在上传图像的同时提供了标注,因此如何确定这些已有的标注在图像中的相关性区域成了一个热门的研究问题。提出了一种基于图像低层视觉特征和多示例学习方法的图像区域标注方法,文中的方法首先对图像进行分割,对分割后的图像区域提取低层视觉特征作为它的区域特征,最后通过多示例学习问题的多样性密度算法思想来对图像进行区域标注。实验中对已被标注的大量数据集进行分析,正确率达到了85%,与已有的图像区域标注方法相比,在区域标注的正确率上有着明显的改善。     

Multiple visual targets tracking via probability hypothesis density filter and feature measurement

The probability hypothesis density (PHD) filter is a practical alternative to the optimal Bayesian multiple‐targets filter based on random finite sets (RFS). It propagates the posterior intensity of the random sets of targets. In this paper, we apply the PHD filter to track a random number of moving targets in visual sequences. The PHD filter is implemented using a Gaussian mixture. Obtaining the PHD only for one visual frame at a time remains a challenge. To meet this challenge, we propose a method to approximate the posterior intensity using feature measurement. To improve the representability of tracking target, we adopt an adaptive weight to fuse the color and local binary pattern (LBP) features which are extracted by the Monte Carlo method. Experimental results demonstrate the effectiveness of our method. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

ASMI-BCI 特征调制及分类性能研究

基于运动想象(MI)的脑-机接口(BCI)近年来被应用于肢体运动功能的可塑性康复。采用视觉辅助刺激可以有效增强MI-BCI系统的分类性能,但视觉障碍患者无法使用。因此本文设计了基于听觉辅助刺激的ASMI-BCI,发现动态声音辅助刺激可以提高大脑运动相关皮层的兴奋性,增强系统的可分性特征。10名在校大学生(5男5女,平均22.6岁)3类实验范式(C-SW、C-DA、C-DV)的平均结果表明,C-SW范式分类正确率最低、C-DA次之、C-DV范式正确率最高。听觉辅助刺激范式的最优分类正确率可达76.03%,相比传统MI-BCI范式显著性提升了8.83%,且60%的被试使用该范式的分类正确率可高于70%。使用动态听觉辅助刺激范式可以为视觉障碍患者提供一种特征调制和BCI性能增强的新模式、新方法。     

复杂光流场运动分析与特征提取

针对车辆行车前方场景视频图像序列这-复杂光流场,提出一种基于光流分析的车辆行车环境特征实时提取方法:对同定在驾驶室的摄像机所拍摄的驾驶员视野前方行车视频图像序列进行区域分割,得到3个特征区域,采用五置信点光流算法对其中两个区域的光流场进行光流估计,并应用数理统计方法对其作置信空间和算术平均处理,提高了光流估计的鲁棒性,...     

汽车雨刮电机电磁干扰特征提取方法

针对汽车内部严重的电磁兼容问题,需要对车内电磁干扰源进行准确的分析.采用小波变换方法对汽车雨刮电机干扰信号进行多尺度分解,利用分解得到的各高频子带的小波系数特点,提出了小波域内突变参数和不平衡参数的计算方法,分并且提取各小波系数的累积能量参数、突变参数以及不平衡参数,并与重构后的各层细节信号的波形特征作了对比分析.结果表明,小波系数的累积能量参数、突变参数和不平衡参数能够准确描述原始信号中不同成分信号的特征,对电磁干扰源的识别和分类具有指导价值.此外,这种方法对其他电磁干扰信号的特征提取具有参考价值.     

Compressed sensing reconstruction of hyperspectral images jointly using spatial smoothing feature and spectral correlation

A compressed sensing (CS) reconstruction algorithm of hyperspectral images jointly using spatial and spectral characteristics is considered. Specifically, in the sampling process, each band image is sampled by the block CS method independently. In the reconstruction process, how to utilize the spatial smoothing feature of each band image and spectral correlation between different band images to formulate the joint optimization problem is the focus of this paper. The total variation (TV) norm and multihypothesis prediction are introduced to express the spatial smoothing feature and the spectral correlation, respectively. Thus, the TV norm and the prediction residual are used as the regularization items in the reconstruction optimization problem. The resulting ill‐posed problem is solved by the augmented Lagrange multiplier method and alternating direction method in an iterative way, and the implementation process of the reconstruction algorithm is presented. Experimental results on four hyperspectral datasets reveal that the proposed algorithm significantly outperforms alternative strategies in terms of peak signal‐to‐noise ratio as well as visual quality. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

纹理特征提取的不变矩探讨

针对目标形状发生变化引起图像特征提取困难等问题,采用不变矩作为特征量的特征匹配算法,以纹理图像为研究对象,分析不变矩的基本理论,探讨具有全局统计信息的不变矩设计方法。仿真实验中,分别利用Hu矩和Zernike矩提取纹理图像的视觉特征,比较2种统计矩在纹理特征提取中的应用范围。实验结果表明,不变矩可以作为目标形状改变后的一种图像特征。然而,对于新的不变矩的构建仍需作进一步研究。     

基于显著特征区域和条件随机场的目标跟踪

针对目标跟踪中的遮挡问题,提出一种基于局部显著特征区域和条件随机场模型(CRF)的跟踪算法。利用目标区域中的显著特征区域相互之间的空间位置关系以及时间域上相邻区域的影响,并结合各个显著特征区域自身的局部信息建立目标的CRF模型;利用CRF模型对 Mean Shift算法的跟踪结果进行概率推断,融合各个显著特征区域的权重,精确定位运动目标的最终位置。在多个视频序列上的实验结果表明,与改进的 MS算法、粒子滤波算法以及分块跟踪方法相比,文中算法具有较高的跟踪精度;尤其是当目标被遮挡时,该算法具有较好的跟踪鲁棒性。该算法充分利用了显著特征区域自身的局部特征和区域之间的空间结构信息以及各个显著特征区域在时间域上的约束条件,能够实现复杂情况下的运动目标的鲁棒跟踪。     

Autonomous Navigation of Vehicles from a Visual Memory Using a Generic Camera Model

In this paper, we present a complete framework for autonomous vehicle navigation using a single camera and natural landmarks. When navigating in an unknown environment for the first time, usual behavior consists of memorizing some key views along the performed path to use these references as checkpoints for future navigation missions. The navigation framework for the wheeled vehicles presented in this paper is based on this assumption. During a human-guided learning step, the vehicle performs paths that are sampled and stored as a set of ordered key images, as acquired by an embedded camera. The visual paths are topologically organized, providing a visual memory of the environment. Given an image of the visual memory as a target, the vehicle navigation mission is defined as a concatenation of visual path subsets called visual routes. When autonomously running, the control guides the vehicle along the reference visual route without explicitly planning any trajectory. The control consists of a vision-based control law that is adapted to the nonholonomic constraint. Our navigation framework has been designed for a generic class of cameras (including conventional, catadioptric, and fisheye cameras). Experiments with an urban electric vehicle navigating in an outdoor environment have been carried out with a fisheye camera along a 750-m-long trajectory. Results validate our approach.     

Toward automating Hammersmith pulled-to-sit examination of infants using feature point based video object tracking

Hammersmith Infant Neurological Examination (HINE) is a set of tests used for grading neurological development of infants on a scale of 0 to 3. These tests help in assessing neurophysiological development of babies, especially preterm infants who are born before (the fetus reaches) the gestational age of 36 weeks. Such tests are often conducted in the follow-up clinics of hospitals for grading infants with suspected disabilities. Assessment based on HINE depends on the expertise of the physicians involved in conducting the examinations. It has been noted that some of these tests, especially pulled-to-sit and lateral tilting, are difficult to assess solely based on visual observation. For example, during the pulled-to-sit examination, the examiner needs to observe the relative movement of the head with respect to torso while pulling the infant by holding wrists. The examiner may find it difficult to follow the head movement from the coronal view. Video object tracking based automatic or semi-automatic analysis can be helpful in this case. In this paper, we present a video based method to automate the analysis of pulled-to-sit examination. In this context, a dynamic programming and node pruning based efficient video object tracking algorithm has been proposed. Pulled-to-sit event detection is handled by the proposed tracking algorithm that uses a 2-D geometric model of the scene. The algorithm has been tested with normal as well as marker based videos of the examination recorded at the neuro-development clinic of the SSKM Hospital, Kolkata, India. It is found that the proposed algorithm is capable of estimating the pulled-to-sit score with sensitivity (80%-92%) and specificity (89%-96%).     

基于方差调节策略耦合结构特征的图像修复算法

针对当前图像修复算法主要采用图像的 R、G、B 信息来获取最优匹配块,忽略了图像的结构特征,导致修复图像中含有 纹理不连续及块现象等问题,设计了方差调节策略耦合结构特征的图像修复算法。 首先,借助图像的梯度模值来构造结构度量 因子,以度量图像的结构特征。 联合置信度项、结构度量因子和数据项,构造优先权函数,以寻求优先修复块。 然后,采用图像 的方差特征,建立方差调节策略,考虑图像纹理的动态变化,寻求与当前纹理情况最吻合的样本块尺寸。 最后,将结构度量因子 引入到最优匹配块的搜索过程中,以弥补通过 R、G、B 信息搜索最优匹配块时所忽略图像结构特征的不足,得出最优匹配块修 复图像,实现损坏区域的复原。 通过实验结果发现,较当前修复方案而言,所提算法的修复图像具备更优的纹理连续性。     

A time-series prediction approach for feature extraction in a brain-computer interface.

This paper presents a feature extraction procedure (FEP) for a brain-computer interface (BCI) application where features are extracted from the electroencephalogram (EEG) recorded from subjects performing right and left motor imagery. Two neural networks (NNs) are trained to perform one-step-ahead predictions for the EEG time-series data, where one NN is trained on right motor imagery and the other on left motor imagery. Features are derived from the power (mean squared) of the prediction error or the power of the predicted signals. All features are calculated from a window through which all predicted signals pass. Separability of features is achieved due to the morphological differences of the EEG signals and each NNs specialization to the type of data on which it is trained. Linear discriminant analysis (LDA) is used for classification. This FEP is tested on three subjects off-line and classification accuracy (CA) rates range between 88% and 98%. The approach compares favorably to a well-known adaptive autoregressive (AAR) FEP and also a linear AAR model based prediction approach.     

基于短路电流小半波特征的短路故障快速检测方法

为使超高压输电线路上的限流器在短路早期快速投入,短路故障快速检测方法的研究至关重要。首先分析了短路电流暂态特征随故障初相角等因素的变化规律,发现部分故障初相角短路工况下电流呈现小半波特征的现象,此时传统检测方法难以满足速动性的要求。然后提出了一种基于短路电流小半波特征的检测判据,利用电流瞬时值或变化率的零点间隔作为检测量,与传统检测判据配合,实现了任意故障初相角下的短路快速检测,并保证了在负荷投切等干扰工况下的可靠性。最后通过离线仿真、现场短路试验验证了该方法的有效性。结果表明所提方法能在2.9 ms内辨识出短路故障。     

A zoom feature for a dynamic programming solution to economicdispatch including transmission losses

An iterative dynamic programming method for solving the economic dispatch problems of a system of thermal generating units including transmission line losses is presented along with a clear explanation of modifying generator cost functions during each iteration. A zoom feature is applied during the iterative process in order to converge to the economic dispatch solution with low computer time and storage requirements, Dynamic programming including a short-term load forecast is briefly discussed. A three-generator example is used to illustrate the method. Computer memory and time requirements are presented, along with results for a 15-unit system     

WGC特征描述的人脸表情识别

针对韦伯局部特征(WLD)仅计算中心像素与周围像素差异提取特征的不足,提出了一种韦伯梯度编码(WGC)特征描述的人脸表情识别算法。首先计算当前像素点周围水平、垂直和对角位置上的数值差与当前像素点的差异构成WGC特征的差动激励;然后进一步提出基于水平和对角线优先原则的WGC_HD特征;最后利用最佳分块方式得到行分块WGC_HD特征,采用自动优化参数的SVM分类器完成人脸表情识别。在公共人脸表情库JAFFE和CK库上进行交叉实验,平均识别率及平均特征提取时间分别为95.49%、12.30 ms和97.63%、31.54 ms。行分块WGC_HD特征考虑了不同梯度方向的像素差异,较好描述了表情图像的局部结构信息且具有较低的时间复杂度,与目前典型的表情识别算法结果对比也验证了算法具有较高的识别精度。     

基于EWT-MQE的变压器局部放电特征提取

为了有效提取局部放电信号故障特征,进而对电力变压器故障进行诊断,提出一种基于经验小波变换(Empirical Wavelet Transform, EWT)和多尺度量子熵(Multiscale Quantum Entropy, MQE)的变压器局部放电特征提取方法。首先,该方法利用EWT对局部放电信号进行分解,得到多个不同的固有模态分量(Intrinsic Mode Function, IMF)和残余分量。其次,计算信号分解出的每个IMF的多尺度量子熵序列。然后,对多尺度量子熵序列利用局部切空间排列算法(Local Tangent Space Arrangement, LTSA)进行降维处理。最后,采用层次聚类算法(Hierarchical Agglomerative Clustering, HAC)进行聚类分析,得到不同放电类型的识别结果。通过与不同诊断方法对比,仿真结果及实验数据验证了所提方法的有效性和优越性。     

基于多尺度特征增强DHTCN的电力系统短期负荷预测研究

为充分挖掘蕴含在电力负荷数据中的多尺度时序信息,提升短期电力负荷预测精度,提出了一种多尺度特征增强的改进时间卷积神经网络(improved temporal convolutional network with multi-scale feature enhancement, ECA-MS-DHTCN)模型。首先,使用4种不同尺寸卷积核的因果卷积提取负荷数据特征,并在特征提取层中嵌入高效通道注意力(efficient channel attention network, ECA)模块实现不降维的局部跨通道交互,得到带有通道注意力的多尺度负荷特征。然后,利用双混合扩张卷积层改进基本时间卷积神经网络(temporal convolutional network, TCN)残差块结构,克服TCN模型中扩张卷积结构存在的信息不连续及远距离信息不相关问题,兼顾负荷特征浅层细节及深层联系。最后,将ECA优化的多尺度特征提取层与改进TCN模型结合搭建ECA-MS-DHTCN负荷预测框架,完成短期负荷预测任务。经实际电网负荷数据仿真,结果表明所提出的ECA-MS-DHTCN模型可以在保持较快训练速度的同时有效地提高预测精度。     

Image‐based visual target following for a nonholonomic wheeled mobile robot with a single fixed camera

This paper addresses the problem of visual target following for a nonholonomic wheeled mobile robot with a single fixed camera. For the problem, we propose a control scheme composed of vision‐based trajectory planning and tracking control. We present online trajectory planning based on image‐based visual servoing. The key idea is to compensate the target object motion. In particular, we focus on visual feature motion resulting from the target object motion. Tracking control to the generated trajectory can therefore achieve visual target following precisely even if the target object is moving. Our proposed scheme can be applied to, e.g. robotic systems for autonomous guard and observation. The effectiveness of the control system is evaluated experimentally. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

尺度不变特征点提取算法的改进算法

特征点提取和描述在图像应用中占有重要的地位。尺度不变特征点提取算法提取出的特征点具有对图像仿射、噪音和光线变化具有很好的鲁棒性,该文以尺度不变特征点提取算法为基础,对SIFT算法的特征点描述步骤用主成分分析算法进行了改进,经实验验证,改进后的算法在图像匹配速度比SIVF算法有所提高,在空间上降低了SIFT特征点描述符的维数。