基于多源域迁移学习的行人重识别探讨

文中以多源域迁移学习方法作为支持,对行人重识别策略的应用进行了分析,包括多源域迁移学习算法、行人重识别现状及其发展需求、多源域迁移学习方法下的行人重识别策略。以期为多源域迁移学习方法的合理应用与行人重识别质量的提升提供科学参考,对提高监管区域监控效能具有积极意义。     

多域分级管理的网络视频监控指挥平台的设计与实现

本文重点介绍了一种基于多域分级管理模式的网络视频监控指挥平台该平台采用域的管理概念,将物理链路不通的域之间或彼此有层级从属关系的域之间以分级管理模式达到数据同步、相互通信,使独立的域之间以相互信任的管理模式实现信息互通,从而将并构网络之间、不同单位之间的资源共享,协同指挥部署,达到充分利用信息资源、避免重复建设、提高监控指挥效率的目的本文从系统构架、系统软件平台、系统功能三个方面详细介绍了这一多域分级管理的网络视频监控指挥平台     

基于无人机图像的输电线自动提取技术

对输电线路的检测能够确保电网的安全运行,利用无人机图像实现输电线准确、快速的提取是实现电力巡检的前提.本文提出了一种基于无人机图像的输电线自动提取方法,能够从复杂的背景图像中完成输电线的有效识别.首先,采用Ratio算子提取出电力线像素,并结合Hough变换对直线段进行检测;然后,根据输电线路几何特征设计了完整输电线合...     

一种基于双滤波的空间图像色域映射算法

针对逐点色域映射方法在图像色域映射时出现的细节损失较大的问题,本文提出了一种新的空间图像色域映射方法。新方法采用双滤波技术将输入图像分解为对应边缘轮廓信息的基础层图像和对应纹理细节信息的细节层图像,先对基础层图像进行彩度优先的逐点色域裁剪,然后将细节层信息补偿给色域裁剪后的图像。最后对细节补偿后的图像进行亮度优先的色域裁剪,从而得到最终的映射图像。本文还分析了双滤波参数设置对色域映射结果和光晕的影响,得出了合理的双滤波参数设置。通过心理物理学实验可以验证：新方法的性能与经典的细节补偿类映射方法相当。另外,新方法在色域映射过程中还能更加有效地抑制光晕的产生。     

基于平滑性测度的直方图自适应模糊增强图像分割

本文提出了一种新的基于平滑性测度的直方图自适应模糊增强图像分割方法。该方法通过定义图像的平滑性测度,采用模糊增强技术对图像的灰度直方图进行增强,然后在增强的直方图上,利用自适应多阈值分割方法进行图像分割。实验表明,该方法对强噪声图像具有良好的分割效果。     

基于帧映射算法的无线实时视频监控系统

针对无线实时视频监控系统的特点，提出了一种有效节省网络带宽的算法——帧映射算法，并用此算法实现了一个无线实时视频监控系统的原型系统。     

基于精确特征分布匹配和多域信息融合的跨域行人重识别

无监督域自适应行人重识别（Unsupervised Domain Adaptation for person Re-identification, UDA-ReID）任务致力于将知识从已标记的源域数据转移到目标域。和传统的单源域自适应相比,将多源域的知识迁移到目标域是一项更具挑战性的任务。由于领域上的差距,多数据集的简单组合只能产生有限的改进。针对此问题,提出了一种基于精确特征分布匹配和多域信息融合的多源域对比学习（exact feature distribution Matching and multi-domain information Fusion based Multi-domain Contrastive Learning, MFMCL）方法。该方法首先采用具有混合记忆的自步对比学习提取不同域数据的特征,并对提取到的特征进行构图,然后通过两层残差图卷积网络进行多域特征融合。其次,为了增强交叉分布特征、产生更丰富的信息,通过基于排序算法的精确直方图匹配来实现精确特征分布匹配,以获得更多样化的特征增强。实验表明,与目前先进的无监督域自适应行人重识别方法相比,所提出的MFMCL方法在广泛使用的行人重识别数据集Market1501、MSMT17和Duke上都取得了优越的性能。     

基于图像质量评价的显示器色域映射

针对显示器图像颜色复现问题,提出了一种基于图像质量评价和图像分割-融合策略的色域映射算法。详细分析了各类色域映射算法的特点并选取4种算法作为基本色域映射算法。提出了一种色域映射图像质量评价算法,并选用SLIC超像素算法对源图像分割。使用基本色域映射算法对源图像进行映射处理,并计算每个分块内各映射图像与源图像的相似度。根据每个图像分块的相似度,对基本色域映射图像进行选择综合处理并融合成最终图像。最后以LED显示屏和LCD显示器为例,对本文提出的算法和其他基本色域映射算法进行主观评价对比实验。实验结果证明本文算法在图像颜色保真效果上要明显优于其他算法,但是在计算速度上仍有待优化。     

Multilevel segmentation of histopathological images using cooccurrence of tissue objects

This paper presents a new approach for unsupervised segmentation of histopathological tissue images. This approach has two main contributions. First, it introduces a new set of high-level texture features to represent the prior knowledge of spatial organization of the tissue components. These texture features are defined on the tissue components, which are approximately represented by tissue objects, and quantify the frequency of two component types being cooccurred in a particular spatial relationship. As they are defined on components, rather than on image pixels, these object cooccurrence features are expected to be less vulnerable to noise and variations that are typically observed at the pixel level of tissue images. Second, it proposes to obtain multiple segmentations by multilevel partitioning of a graph constructed on the tissue objects and combine them by an ensemble function. This multilevel graph partitioning algorithm introduces randomization in graph construction and refinements in its multilevel scheme to increase diversity of individual segmentations, and thus, improve the final result. The experiments on 200 colon tissue images reveal that the proposed approach--the object cooccurrence features together with the multilevel segmentation algorithm--is effective to obtain high-quality results. The experiments also show that it improves the segmentation results compared to the previous approaches.     

Method of images segmentation by dynamic spectral characteristics

In considered method we use basic principles of biometrics and bioradiolocation for solution of the problem of images segmentation. Using dynamic spectral characteristics, obtained by means of wavelet spectrum we extract biometric indicator in form of signal of brightness pixels modification at the face skin part, specified by heartbeat. It is proposed to use quasi-matched wavelet filters for efficient selection of human heartbeat signal and it is shown the possibility of its frequency measurement practically at real-time mode. Obtained results can be used for many medical applications, security systems, object identification, etc.     

Tracking moving objects in television images

The estimation of the velocity of objects imaged by television cameras is useful in different areas of image processing.The problem is solved by means of a linear estimation algorithm and the effects of noise superimposed to the signal are analyzed. The structure of a real-time estimator is then presented. Experimental results show that a very fine accuracy is obtained. They encourage its application to image coding for redundancy reduction using movement compensation.     

A novel transmission line characterisation based on measurement data reconfirmation

Due to inherent resonance effects and frequency-variant dielectric properties, it is very difficult to experimentally determine the stable and accurate circuit model parameters of thin film transmission line structures over a broad frequency band. In this article, a new, simple and straightforward frequency-variant transmission line circuit model parameter determination method is presented. Experimental test patterns for high-frequency transmission line characterisations are designed and fabricated using a package process. The S-parameters for the test patterns are measured using a vector network analyzer (VNA) from 100 MHz to 26.5 GHz. The parasitic effects due to contact pads are de-embedded. The frequency-variant complex permittivity and resonance-effect-free transmission line parameters (i.e., the propagation constant and characteristic impedance) are then determined in a broad frequency band.     

一种基于区域显著性的红外图像目标分割方法

提出了一种基于区域显著性的红外图像目标分割方法,即首先在方差空间中提取显著性区域,然后根据图像复杂度对显著性区域进行筛选,最后采用阈值分割方法分割显著性区域,获取目标.算法具有较强的适用性和工程实用性.     

Abnormality segmentation in brain images via distributed estimation

The aim of this paper is to introduce a novel semisupervised scheme for abnormality detection and segmentation in medical images. Semisupervised learning does not require pathology modeling and, thus, allows high degree of automation. In abnormality detection, a vector is characterized as anomalous if it does not comply with the probability distribution obtained from normal data. The estimation of the probability density function, however, is usually not feasible due to large data dimensionality. In order to overcome this challenge, we treat every image as a network of locally coherent image partitions (overlapping blocks). We formulate and maximize a strictly concave likelihood function estimating abnormality for each partition and fuse the local estimates into a globally optimal estimate that satisfies the consistency constraints, based on a distributed estimation algorithm. The likelihood function consists of a model and a data term and is formulated as a quadratic programming problem. The method is applied for automatically segmenting brain pathologies, such as simulated brain infarction and dysplasia, as well as real lesions in diabetes patients. The assessment of the method using receiver operating characteristic analysis demonstrates improvement in image segmentation over two-group analysis performed with Statistical Parametric Mapping (SPM).     

用全息双频光栅测量物体的振动

激光束入射至固定在振动物体上的全息双频光栅,其1级衍射光强度受到了振动的调制。本文介绍这种测振法的原理和一些实验结果,并对其应用作简要的讨论。     

3-D adaptive predictive coding of moving images by block segmentation

The performance of adaptive, linear prediction in frame-to-frame coding of a sequence of videotelephonic images is examined. The dependence of the entropy of the prediction error upon order of the predictor and size of the blocks, in which prediction coefficients are adaptively computed, is elicited.A convenient selection of parameters mentioned above and an optimum strategy for quantizing prediction coefficients are put forth, which reduce transmission rate to less than 3 bits/pel while ensuring exact reproduction of the source.By allowing coding with a fidelity criterion (MSSTE), rates as low as 1.68 bits/pel are shown to be achievable without any perceptible quality degradation.     

Original approach for the localisation of objects in images

An original approach is presented for the localisation of objects in an image which approach is neuronal and has two steps. In the first step, a rough localisation is performed by presenting each pixel with its neighbourhood to a neural net which is able to indicate whether this pixel and its neighbourhood are the image of the search object. This first filter does not discriminate for position. From its result, areas which might contain an image of the object can be selected. In the second step, these areas are presented to another neural net which can determine the exact position of the object in each area. This algorithm is applied to the problem of localising faces in images     

Ridge-based vessel segmentation in color images of the retina

A method is presented for automated segmentation of vessels in two-dimensional color images of the retina. This method can be used in computer analyses of retinal images, e.g., in automated screening for diabetic retinopathy. The system is based on extraction of image ridges, which coincide approximately with vessel centerlines. The ridges are used to compose primitives in the form of line elements. With the line elements an image is partitioned into patches by assigning each image pixel to the closest line element. Every line element constitutes a local coordinate frame for its corresponding patch. For every pixel, feature vectors are computed that make use of properties of the patches and the line elements. The feature vectors are classified using a kappaNN-classifier and sequential forward feature selection. The algorithm was tested on a database consisting of 40 manually labeled images. The method achieves an area under the receiver operating characteristic curve of 0.952. The method is compared with two recently published rule-based methods of Hoover et al. and Jiang et al. The results show that our method is significantly better than the two rule-based methods (p < 0.01). The accuracy of our method is 0.944 versus 0.947 for a second observer.