Human Action Recognition in Compressed Domain using PBL-McRBFN Approach

Large variations in human actions lead to major challenges in computer vision research. Several algorithms are designed to solve the challenges. Algorithms that stand apart, help in solving the challenge in addition to performing faster and efficient manner. In this paper, we propose a human cognition inspired projection based learning for person-independent human action recognition in the H.264/AVC compressed domain and demonstrate a PBL-McRBEN based approach to help take the machine learning algorithms to the next level. Here, we use gradient image based feature extraction process where the motion vectors and quantization parameters are extracted and these are studied temporally to form several Group of Pictures (GoP). The GoP is then considered individually for two different bench mark data sets and the results are classified using person independent human action recognition. The functional relationship is studied using Projection Based Learning algorithm of the Meta-cognitive Radial Basis Function Network (PBL-McRBFN) which has a cognitive and meta-cognitive component. The cognitive component is a radial basis function network while the Meta-Cognitive Component(MCC) employs self regulation. The McC emulates human cognition like learning to achieve better performance. Performance of the proposed approach can handle sparse information in compressed video domain and provides more accuracy than other pixel domain counterparts. Performance of the feature extraction process achieved more than 90% accuracy using the PTIL-McRBFN which catalyzes the speed of the proposed high speed action recognition algorithm. We have conducted twenty random trials to find the performance in GoP. The results are also compared with other well known classifiers in machine learning literature.

A Featureless Approach to 3D Polyhedral Building Modeling from Aerial Images

This paper presents a model-based approach for reconstructing 3D polyhedral building models from aerial images. The proposed approach exploits some geometric and photometric properties resulting from the perspective projection of planar structures. Data are provided by calibrated aerial images. The novelty of the approach lies in its featurelessness and in its use of direct optimization based on image rawbrightness. The proposed framework avoids feature extraction and matching. The 3D polyhedral model is directly estimated by optimizing an objective function that combines an image-based dissimilarity measure and a gradient score over several aerial images. The optimization process is carried out by the Differential Evolution algorithm. The proposed approach is intended to provide more accurate 3D reconstruction than feature-based approaches. Fast 3D model rectification and updating can take advantage of the proposed method. Several results and evaluations of performance from real and synthetic images show the feasibility and robustness of the proposed approach.

Bright-field and fluorescence chip-scale microscopy for biological imaging

Optical microscopy is an essential tool in biological science and one of the gold standards for medical examinations. Miniaturization of microscopes can be a crucial stepping stone towards realizing compact, cost-effective and portable platforms for biomedical research and healthcare. This thesis reports on implementations of bright-field and fluorescence chip-scale microscopes for a variety of biological imaging applications. The term “chip-scale microscopy” refers to lensless imaging techniques realized in the form of mass-producible semiconductor devices, which transforms the fundamental design of optical microscopes.

Our strategy for chip-scale microscopy involves utilization of low-cost Complementary metal Oxide Semiconductor (CMOS) image sensors, computational image processing and micro-fabricated structural components. First, the sub-pixel resolving optofluidic microscope (SROFM), will be presented, which combines microfluidics and pixel super-resolution image reconstruction to perform high-throughput imaging of fluidic samples, such as blood cells. We discuss design parameters and construction of the device, as well as the resulting images and the resolution of the device, which was 0.66 µm at the highest acuity. The potential applications of SROFM for clinical diagnosis of malaria in the resource-limited settings is discussed.

Next, the implementations of ePetri, a self-imaging Petri dish platform with microscopy resolution, are presented. Here, we simply place the sample of interest on the surface of the image sensor and capture the direct shadow images under the illumination. By taking advantage of the inherent motion of the microorganisms, we achieve high resolution (~1 µm) imaging and long term culture of motile microorganisms over ultra large field-of-view (5.7 mm × 4.4 mm) in a specialized ePetri platform. We apply the pixel super-resolution reconstruction to a set of low-resolution shadow images of the microorganisms as they move across the sensing area of an image sensor chip and render an improved resolution image. We perform longitudinal study of Euglena gracilis cultured in an ePetri platform and image based analysis on the motion and morphology of the cells. The ePetri device for imaging non-motile cells are also demonstrated, by using the sweeping illumination of a light emitting diode (LED) matrix for pixel super-resolution reconstruction of sub-pixel shifted shadow images. Using this prototype device, we demonstrate the detection of waterborne parasites for the effective diagnosis of enteric parasite infection in resource-limited settings.

Then, we demonstrate the adaptation of a smartphone’s camera to function as a compact lensless microscope, which uses ambient illumination as its light source and does not require the incorporation of a dedicated light source. The method is also based on the image reconstruction with sweeping illumination technique, where the sequence of images are captured while the user is manually tilting the device around any ambient light source, such as the sun or a lamp. Image acquisition and reconstruction is performed on the device using a custom-built android application, constructing a stand-alone imaging device for field applications. We discuss the construction of the device using a commercial smartphone and demonstrate the imaging capabilities of our system.

Finally, we report on the implementation of fluorescence chip-scale microscope, based on a silo-filter structure fabricated on the pixel array of a CMOS image sensor. The extruded pixel design with metal walls between neighboring pixels successfully guides fluorescence emission through the thick absorptive filter to the photodiode layer of a pixel. Our silo-filter CMOS image sensor prototype achieves 13-µm resolution for fluorescence imaging over a wide field-of-view (4.8 mm × 4.4 mm). Here, we demonstrate bright-field and fluorescence longitudinal imaging of living cells in a compact, low-cost configuration.

Towards Application of One-Class Classification Methods to Medical Data

In the problem of one-class classification (OCC) one of the classes, the target class, has to be distinguished from all other possible objects, considered as nontargets. In many biomedical problems this situation arises, for example, in diagnosis, image based tumor recognition or analysis of electrocardiogram data. In this paper an approach to OCC based on a typicality test is experimentally compared with reference state-of-the-art OCC techniques-Gaussian, mixture of Gaussians, naive Parzen, Parzen, and support vector data description-using biomedical data sets. We evaluate the ability of the procedures using twelve experimental data sets with not necessarily continuous data. As there are few benchmark data sets for one-class classification, all data sets considered in the evaluation have multiple classes. Each class in turn is considered as the target class and the units in the other classes are considered as new units to be classified. The results of the comparison show the good performance of the typicality approach, which is available for high dimensional data; it is worth mentioning that it can be used for any kind of data (continuous, discrete, or nominal), whereas state-of-the-art approaches application is not straightforward when nominal variables are present.

Um sistema para o reconhecimento da feição edificação em imagem digital com agentes inteligentes.

O objetivo desta dissertação foi criar uma nova abordagem para identificar de maneira automática feições do tipo edificação em uma imagem digital. Tal identificação seria de interesse de órgãos públicos que lidam com planejamento urbano para fins de controle da ocupação humana irregular. A abordagem criada utilizou agentes de software especialistas para proceder com o processamento da segmentação e reconhecimento de feições na imagem digital. Os agentes foram programados para tratar uma imagem colorida com o padrão Red, Green e Blue (RGB). A criação desta nova abordagem teve como motivação o fato das atuais técnicas existentes de segmentação e classificação de imagens dependerem sobremaneira dos seus usuários. Em outras palavras, pretendeu-se com a abordagem em questão permitir que usuários menos técnicos pudessem interagir com um sistema classificador, sem a necessidade de profundos conhecimentos de processamento digital de imagem. Uma ferramenta protótipo foi desenvolvida para testar essa abordagem, que emprega de forma inusitada, agentes inteligentes, com testes feitos em recortes de ortofotos digitais do Município de Angra dos Reis (RJ).

Management and Analysis of Unstructured Construction Data Types

Compared with structured data sources that are usually stored and analyzed in spreadsheets, relational databases, and single data tables, unstructured construction data sources such as text documents, site images, web pages, and project schedules have been less intensively studied due to additional challenges in data preparation, representation, and analysis. In this paper, our vision for data management and mining addressing such challenges are presented, together with related research results from previous work, as well as our recent developments of data mining on text-based, web-based, image-based, and network-based construction databases.

Data Analysis on Complicated Construction Data Sources: Vision, Research, and Recent Developments

Compared with construction data sources that are usually stored and analyzed in spreadsheets and single data tables, data sources with more complicated structures, such as text documents, site images, web pages, and project schedules have been less intensively studied due to additional challenges in data preparation, representation, and analysis. In this paper, our definition and vision for advanced data analysis addressing such challenges are presented, together with related research results from previous work, as well as our recent developments of data analysis on text-based, image-based, web-based, and network-based construction sources. It is shown in this paper that particular data preparation, representation, and analysis operations should be identified, and integrated with careful problem investigations and scientific validation measures in order to provide general frameworks in support of information search and knowledge discovery from such information-abundant data sources.

Design and formulation of functional pluripotent stem cell-derived cardiac microtissues.

Access to robust and information-rich human cardiac tissue models would accelerate drug-based strategies for treating heart disease. Despite significant effort, the generation of high-fidelity adult-like human cardiac tissue analogs remains challenging. We used computational modeling of tissue contraction and assembly mechanics in conjunction with microfabricated constraints to guide the design of aligned and functional 3D human pluripotent stem cell (hPSC)-derived cardiac microtissues that we term cardiac microwires (CMWs). Miniaturization of the platform circumvented the need for tissue vascularization and enabled higher-throughput image-based analysis of CMW drug responsiveness. CMW tissue properties could be tuned using electromechanical stimuli and cell composition. Specifically, controlling self-assembly of 3D tissues in aligned collagen, and pacing with point stimulation electrodes, were found to promote cardiac maturation-associated gene expression and in vivo-like electrical signal propagation. Furthermore, screening a range of hPSC-derived cardiac cell ratios identified that 75% NKX2 Homeobox 5 (NKX2-5)+ cardiomyocytes and 25% Cluster of Differentiation 90 OR (CD90)+ nonmyocytes optimized tissue remodeling dynamics and yielded enhanced structural and functional properties. Finally, we demonstrate the utility of the optimized platform in a tachycardic model of arrhythmogenesis, an aspect of cardiac electrophysiology not previously recapitulated in 3D in vitro hPSC-derived cardiac microtissue models. The design criteria identified with our CMW platform should accelerate the development of predictive in vitro assays of human heart tissue function.

轨迹测量系统中特征点检测技术研究

针对机器人直线轨迹测量系统中的图像处理鲁棒性问题,开展线结构光光条图像的特征点识别技术研究,提出了一种基于种子点拟合和直线生长的直线分割方法,很好地解决了各种条件下各段拟合直线的端点自动获取问题,提高了系统的环境适应性和测量精度.实验表明,该方法具有很好的鲁棒性.

视觉伺服分类及其动态过程

对视觉伺服进行了综述性的介绍,系统地介绍了机器人视觉伺服控制的发展历史以及现状·从控制模型给出了视觉伺服控制系统的分类·针对两种最基本的分类方式基于位置的视觉伺服和基于图像的视觉伺服进行了重点介绍·对于视觉系统和图像特征的选取问题进行了讨论,此外还对视觉伺服系统的动态过程进行了分析,指出视觉系统的延时是目前伺服控制的研究所面临的最大问题·对未来视觉伺服研究的方向进行了总结·

基于Zernike正交矩的图像亚像素边缘检测算法改进

介绍了Zernike矩及基于Zernike矩的图像亚像素边缘检测原理,针对Ghosal提出的基于Zernike矩的亚像素图像边缘检测算法检测出的图像存在边缘较粗及边缘亚像素定位精度低等不足,提出了一种改进算法.推导了7×7 Zernike矩模板系数,提出一种新的边缘判断依据.改进的算法能较好检测图像边缘并实现了较高的边缘定位.最后,设计了3组不同的实验.实验结果同Canny算子及Ghosal算法相比,证明了改进算法的优越性.

嵌入式智能图像处理在火灾预警系统的应用

传统的火灾检测方法一般采用感烟、感温、感光探测器等进行探测。本文提出了一种嵌入式基于图像视觉特征的火灾检测方法,以TI公司的数字多媒体处理器TMS320DM642为核心,设计实现智能前端火灾探测与自动报警系统。通过DM642对视频图像进行采集并结合相应的智能图像处理与模式识别算法,对森林火险进行实时监控。实验结果表明,该系统比传统系统更进一步减少了误报率且具有响应快、监控范围广等优点。

波动方程偏移速度分析

On the subject of oil and gas exploration, migration is an efficacious technique for imagining structures underground. Wave-equation migration (WEM) dominates over other migration methods in accuracy, despite of higher computational cost. However, the advantages of WEM will emerge as the progress of computer technology. WEM is sensitive to velocity model more than others. Small velocity perturbations result in grate divergence in the image pad. Currently, Kirrchhoff method is still very popular in the exploration industry for the reason of difficult to provide precise velocity model. It is very urgent to figure out a way to migration velocity modeling. This dissertation is mainly devoted to migration velocity analysis method for WEM: 1. In this dissertation, we cataloged wave equation prestack depth migration. The concept of migration is introduced. Then, the analysis is applied to different kinds of extrapolate operator to demonstrate their accuracy and applicability. We derived the DSR and SSR migration method and apply both to 2D model. 2. The output of prestack WEM is in form of common image gathers (CIGs). Angle domain common image gathers (ADCIGs) gained by wave equation are proved to be free of artifacts. They are also the most potential candidates for migration velocity analysis. We discussed how to get ADCIGs by DSR and SSR, and obtained ADCIGs before and after imaging separately. The quality of post stack image is affected by CIGs, only the focused or flattened CIGs generate the correct image. Based on wave equation migration, image could be enhanced by special measures. In this dissertation we use both prestack depth residual migration and time shift imaging condition to improve the image quality. 3. Inaccurate velocities lead to errors of imaging depth and curvature of coherent events in CIGs. The ultimate goal of migration velocity analysis (MVA) is to focus scattered event to correct depth and flatten curving event by updating velocities. The kinematic figures are implicitly presented by focus depth aberration and kinetic figure by amplitude. The initial model of Wave-equation migration velocity analysis (WEMVA) is the output of RMO velocity analysis. For integrity of MVA, we review RMO method in this dissertation. The dissertation discusses the general ideal of RMO velocity analysis for flat and dipping events and the corresponding velocity update formula. Migration velocity analysis is a very time consuming work. Respect to computational convenience, we discus how RMO works for synthetic source record migration. In some extremely situation, RMO method fails. Especially in the areas of poorly illuminated or steep structure, it is very difficult to obtain enough angle information for RMO. WEMVA based on wave extrapolate theory, which successfully overcome the drawback of ray based methods. WEMVA inverses residual velocities with residual images. Based on migration regression, we studied the linearized scattering operator and linearized residual image. The key to WEMVA is the linearized residual image. Residual image obtained by Prestack residual migration, which based on DSR is very inefficient. In this dissertation, we proposed obtaining residual migration by time shift image condition, so that, WEMVA could be implemented by SSR. It evidently reduce the computational cost for this method.