Visual learning and recognition of 3-d objects from appearance

The problem of automatically learning object models for recognition and pose estimation is addressed. In contrast to the traditional approach, the recognition problem is formulated as one of matching appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, reflectance properties, pose in the scene, and the illumination conditions. While shape and reflectance are intrinsic properties and constant for a rigid object, pose and illumination vary from scene to scene. A compact representation of object appearance is proposed that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a manifold. Given an unknown input image, the recognition system projects the image to eigenspace. The object is recognized based on the manifold it lies on. The exact position of the projection on the manifold determines the object's pose in the image.A variety of experiments are conducted using objects with complex appearance characteristics. The performance of the recognition and pose estimation algorithms is studied using over a thousand input images of sample objects. Sensitivity of recognition to the number of eigenspace dimensions and the number of learning samples is analyzed. For the objects used, appearance representation in eigenspaces with less than 20 dimensions produces accurate recognition results with an average pose estimation error of about 1.0 degree. A near real-time recognition system with 20 complex objects in the database has been developed. The paper is concluded with a discussion on various issues related to the proposed learning and recognition methodology.     

Visual tracking of known three-dimensional objects

A method is described of visually tracking a known three-dimensional object as it moves with six degrees of freedom. The method uses the predicted position of known features on the object to find the features in images from one or more cameras, measures the position of the features in the images, and uses these measurements to update the estimates of position, orientation, linear velocity, and angular velocity of the object model. The features usually used are brightness edges that correspond to markings or the edges of solid objects, although point features can be used. The solution for object position and orientation is a weighted least-squares adjustment that includes filtering over time, which reduces the effects of errors, allows extrapolation over times of missing data, and allows the use of stereo information from multiple-camera images that are not coincident in time. The filtering action is derived so as to be optimum if the acceleration is random. (Alternatively, random torque can be assumed for rotation.) The filter is equivalent to a Kalman filter, but for efficiency it is formulated differently in order to take advantage of the dimensionality of the observations and the state vector which occur in this problem. The method can track accurately with arbitrarily large angular velocities, as long as the angular acceleration (or torque) is small. Results are presented showing the successful tracking of partially obscured objects with clutter.     

Visual learning and classification of human epithelial type 2 cell images through spontaneous activity patterns

Identifying the presence of anti-nuclear antibody (ANA) in human epithelial type 2 (HEp-2) cells via the indirect immunofluorescence (IIF) protocol is commonly used to diagnose various connective tissue diseases in clinical pathology tests. As it is a labour and time intensive diagnostic process, several computer aided diagnostic (CAD) systems have been proposed. However, the existing CAD systems suffer from numerous shortcomings due to the selection of features, which is commonly based on expert experience. Such a choice of features may not work well when the CAD systems are retasked to another dataset. To address this, in our previous work, we proposed a novel approach that learns a set of filters from HEp-2 cell images. It is inspired by the receptive fields in the mammalian's vision system, since the receptive fields can be thought as a set of filters for similar shapes. We obtain robust filters for HEp-2 cell classification by employing the independent component analysis (ICA) framework. Although, this approach may be held back due to one particular problem; ICA learning requires a sufficiently large volume of training data which is not always available. In this paper, we demonstrate a biologically inspired solution to address this issue via the use of spontaneous activity patterns (SAP). The spontaneous activity patterns, which are related to the spontaneous neural activities initialised by the chemical release in the brain, are found as the typical stimuli for the visual cell development of newborn animals. In the classification system for HEp-2 cells, we propose to model SAP as a set of small image patches containing randomly positioned Gaussian spots. The SAP image patches are generated and mixed with the training images in order to learn filters via the ICA framework. The obtained filters are adopted to extract the set of responses from a HEp-2 cell image. We then employ regions from this set of responses and stack them into “cubic regions”, and apply a classification based on the correlation information of the features. We show that applying the additional SAP leads to a better classification performance on HEp-2 cell images compared to using only the existing patterns for training ICA filters. The improvement on classification is particularly significant when there are not enough specimen images available in the training set, as SAP adds more variations to the existing data that makes the learned ICA model more robust. We show that the proposed approach consistently outperforms three recently proposed CAD systems on two publicly available datasets: ICPR HEp-2 contest and SNPHEp-2.     

Statistical profiles of highly-rated learning objects

The continuously growth of learning resources available in on-line repositories has raised the concern for the development of automated methods for quality assessment. The current existence of on-line evaluations in such repositories has opened the possibility of searching for statistical profiles of highly-rated resources that can be used as priori indicators of quality. In this paper, we analyzed 35 metrics in learning objects refereed inside the MERLOT repository and elaborated profiles for these resources regarding the different categories of disciplines and material types available. We found that some of the intrinsic metrics presented significant differences between highly rated and poorly-rated resources and that those differences are dependent on the category of discipline to which the resource belongs and on the type of the resource. Moreover, we found that different profiles should be identified according to the type of rating (peer-review or user) under evaluation. At last, we developed an initial model using linear discriminant analysis to evaluate the strength of relevant metrics when performing an automated quality classification task. The initial results of this work are promising and will be used as the foundations for the further development of an automated tool for contextualized quality assessment of learning objects inside repositories.     

Visual learning and recognition of 3D objects using two-dimensional principal component analysis: A robust and an efficient approach

Inspired by the conviction that the successful model employed for face recognition [M. Turk, A. Pentland, Eigenfaces for recognition, J. Cogn. Neurosci. 3(1) (1991) 71-86] should be extendable for object recognition [H. Murase, S.K. Nayar, Visual learning and recognition of 3-D objects from appearance, International J. Comput. Vis. 14(1) (1995) 5-24], in this paper, a new technique called two-dimensional principal component analysis (2D-PCA) [J. Yang et al., Two-dimensional PCA: a new approach to appearance based face representation and recognition, IEEE Trans. Patt. Anal. Mach. Intell. 26(1) (2004) 131-137] is explored for 3D object representation and recognition. 2D-PCA is based on 2D image matrices rather than 1D vectors so that the image matrix need not be transformed into a vector prior to feature extraction. Image covariance matrix is directly computed using the original image matrices, and its eigenvectors are derived for feature extraction. The experimental results indicate that the 2D-PCA is computationally more efficient than conventional PCA (1D-PCA) [H. Murase, S.K. Nayar, Visual learning and recognition of 3-D objects from appearance, International J. Comput. Vis. 14(1) (1995) 5-24]. It is also revealed through experimentation that the proposed method is more robust to noise and occlusion.     

Boundary objects in collaborative work and learning

Boundary objects are artifacts, processes, concepts and other entities that provide bridges across boundaries and act as shared references that are meaningful for learners and collaborators with different backgrounds. In this paper, we explore cooperation in a cross-disciplinary and cross-cultural context, focusing on the opportunities for learning that arise at different boundaries and on corresponding boundary objects to facilitate both collaboration and learning. We present and discuss a study we conducted within a Cooperation Technology course. The discussion provides implications for collaboration support across boundaries, including insights on why they are important, how to facilitate their creation, and how to use technologies for that. The implications are formulated as instruction for designing university courses, but can be used in a wider context.     

自然场景中的视觉显著对象检测

显著对象检测是视觉注意机制的一个重要应用基础研究,对于图像检索、场景分析、图像标注与对象识别都有着重要的研究意义。基于Tresiman特征整合理论和Koch计算框架,提出一种自然场景中视觉显著对象的检测方法。该方法首先建立适用于彩色自然场景的视觉显著度模型,计算多种不同特征的显著度,然后在融合不同特征的综合显著度图中提取显著对象。实验结果表明,与经典的Itti模型相比,这种方法不仅检测快速而且更准确地将视觉显著对象从背景中分离出来,更符合人眼的真实视觉注意过程。     

Architectural styles, design patterns, and objects

Architectural styles, object-oriented design and design patterns all hold promise as approaches that simplify software design and reuse by capturing and exploiting system design knowledge. This article explores the capabilities and roles of the various approaches, their strengths and their limitations     

Visual learning for science and engineering

This survey looks at visualization techniques used in science and engineering education to enhance student learning and encourage underrepresented students to pursue technical degrees. This article aims to encourage faculty in science, technology, engineering, and math (STEM) disciplines to use visual methods to communicate to their students. Visual learning is an important method for exploiting students' visual senses to enhance learning and engage their interest. This methodology also has the potential to increase the number of students in STEM fields, especially of women and minority students. A visual approach to science and engineering enhances communication. This visualization revolution shows that letting scientists engage the higher cognitive parts of the brain by thinking and communicating visually improved how they performed their research.     

Weakly supervised learning of interactions between humans and objects

We introduce a weakly supervised approach for learning human actions modeled as interactions between humans and objects. Our approach is human-centric: We first localize a human in the image and then determine the object relevant for the action and its spatial relation with the human. The model is learned automatically from a set of still images annotated only with the action label. Our approach relies on a human detector to initialize the model learning. For robustness to various degrees of visibility, we build a detector that learns to combine a set of existing part detectors. Starting from humans detected in a set of images depicting the action, our approach determines the action object and its spatial relation to the human. Its final output is a probabilistic model of the human-object interaction, i.e., the spatial relation between the human and the object. We present an extensive experimental evaluation on the sports action data set from [1], the PASCAL Action 2010 data set [2], and a new human-object interaction data set.     

Greedy learning of multiple objects in images using robust statistics and factorial learning

We consider data that are images containing views of multiple objects. Our task is to learn about each of the objects present in the images. This task can be approached as a factorial learning problem, where each image must be explained by instantiating a model for each of the objects present with the correct instantiation parameters. A major problem with learning a factorial model is that as the number of objects increases, there is a combinatorial explosion of the number of configurations that need to be considered. We develop a method to extract object models sequentially from the data by making use of a robust statistical method, thus avoiding the combinatorial explosion, and present results showing successful extraction of objects from real images.     

Designing a mobile language learning system based on lightweight learning objects

This paper investigates the possibilities in the area of application of mobile technologies for language learning. The primary goal is to design a mobile system for learning of the Japanese language with a clear separation of content and presentation, and to leverage the learners’ interest in the Japanese language. Both the technical and the language learning perspectives are discussed. A reusable, lightweight model of learning objects with compact content and a reduced metadata set is presented. These objects are stored in a simple learning object repository that can deliver them to any client over the Internet. A mobile application is designed to use the learning object repository as its content provider, while defining its own method of presentation suitable for smaller screens of mobile devices. For the purpose of evaluation, an experiment was conducted within the e-learning system at the Faculty of Organizational Sciences, University of Belgrade. Research findings have indicated that the developed mobile application has a positive effect on the students’ interest in the subject matter.     

Designing a social learning content management system based on learning objects

With the prevalence of social networking services and social media tools, individuals now engage in the production, sharing, and application of diverse content, extending community-based social learning. The most prominent aspect of social learning, which makes it distinct from e-learning, is how content is produced and consumed. That is, people share knowledge with others and learn values via networks in social learning, which requires social media content and social network activity content to be turned into shareable learning objects. In reference to social learning, the present study proposes a Social Learning Content Management System that generates, manages, and publishes learning objects based on content generation models which are also defined here. The proposed system is of significance in that it enables the transformation of social resources into learning objects with the Social Learning Content Management System architecture and data schema defined, and relevant processes designed, based on metadata and learning objects defined for N-screen services.     

Computer support for learning mathematics: A learning environment based on recreational learning objects

In this paper, we introduce an electronic collaborative learning environment based on Interactive Instructors of Recreational Mathematics (IIRM), establishing an alternative approach for motivating students towards mathematics. The IIRM are educational software components, specializing in mathematical concepts, presented through recreational mathematics, conceived as interactive, recreation-oriented learning objects, integrated within the environment. We present the architecture of the learning environment which integrates communication services that support the interaction processes of the learning community, through instant messaging, chat rooms, and multi-player math games. Through the environment’s interface of their personal workspace, students have access to several easy-to-use mechanisms that allows them to customize its content, its layout, and its appearance. At internal levels, the functionality of IIRM is enhanced with features supported by the environment infrastructure. We evaluated different aspects of the learning environment in three short, motivation-oriented math courses given to Mexican high-school students. The results indicate that the use of the IIRM-based electronic learning environment, positively affects student attitudes towards mathematics. We believe that this approach has the potential to promote the mathematics learning process, basically on its motivational aspects.     

A model for multi-label classification and ranking of learning objects

This paper describes an approach that uses multi-label classification methods for search tagged learning objects (LOs) by Learning Object Metadata (LOM), specifically the model offers a methodology that illustrates the task of multi-label mapping of LOs into types queries through an emergent multi-label space, and that can improve the first choice of learners or teachers. In order to build the model, the paper also proposes and preliminarily investigates the use of multi-label classification algorithm using only the LO features. As many LOs include textual material that can be indexed, and such indexes can also be used to filter the objects by matching them against user-provided keywords, we then did experiments using web classification with text features to compare the accuracy with the results from metadata (LO feature).     

3D acquisition of mirroring objects using striped patterns

Objects with mirroring optical characteristics are left out of the scope of most 3D scanning methods. We present here a new automatic acquisition approach, shape-from-distortion, that focuses on that category of objects, requires only a still camera and a color monitor, and produces range scans (plus a normal and a reflectance map) of the target. Our technique consists of two steps: first, an improved environment matte is captured for the mirroring object, using the interference of patterns with different frequencies to obtain sub-pixel accuracy. Then, the matte is converted into a normal and a depth map by exploiting the self-coherence of a surface when integrating the normal map along different paths. The results show very high accuracy, capturing even smallest surface details. The acquired depth maps can be further processed using standard techniques to produce a complete 3D mesh of the object.     

Detecting and tracking mesoscale precipitating objects using machine learning algorithms

Accurate identification of precipitating clouds is a challenging task. In the present work, Support Vector Machines (SVMs), Decision Trees (DT), and Random Forests (RD) algorithms were applied to extract and track mesoscale convective precipitating clouds from a series of 22 Geostationary Operational Environmental Satellite-13 meteorological image sub-scenes over the continental territory of Colombia. This study’s aims are twofold: (i) to establish whether the use of five meteorological spectral channels, rather than a single infrared (IR) channel, improves rainfall objects detection and (ii) to evaluate the potential of machine learning algorithms to locate precipitation clouds. Results show that while the SVM algorithm provides more accurate classification of rainfall cloud objects than the traditional IR brightness temperature threshold method, such improvement is not statistically significant. Accuracy assessment was performed using STEP (shape (S), theme (T), edge (E), and position (P)) object-based similarity matrix method, taking as reference precipitation satellite images from the Tropical Rainfall Measuring Mission. Best thematic and geometric accuracies were obtained applying the SVM algorithm.     

Migrating legacy video lectures to multimedia learning objects

Video lectures are an old distance learning approach that offers only basic interaction and retrieval features to the user. Thus, to follow the new learning paradigms, we need to re‐engineer the e‐learning processes while preserving the investments made in the past. In this paper we present an approach for migrating video lectures to multimedia learning objects. Two essential problems are tackled: the detection of slide transitions and the generation of the learning objects. To this aim, the video of the lecture is scanned to detect the slide changes, while the learning object metadata and the slide pictures are extracted from the presentation document. A tool named VLMigrator (video lecture migrator) has been developed to support the migration of video lectures and the restructuring of their contents in terms of learning objects. Both the migration strategy and the tool have been experimented in a case study. Copyright © 2008 John Wiley & Sons, Ltd.     

Qualitative map learning based on covisibility of objects.

Autonomous map construction is one of the most fundamental and significant issues in intelligent mobile robot research. While a variety of map construction methods have been proposed, most require some quantitative measurements of the environment and a mechanism of precise self-localization. This paper proposes a novel map construction method using only qualitative information about "how often two objects are observed simultaneously." This method is based on heuristics--"closely located objects are likely to be seen simultaneously more often than distant objects" and a well-known multivariate data analysis technique-multidimensional scaling. A significant feature of this method is that it requires neither quantitative sensor measurements nor information about the robot's own position. Simulation and experimental results demonstrated that this method is sufficiently practical for capturing a qualitative spatial relationship among identifiable landmark objects rapidly.     

Web metadata extraction and semantic indexing for learning objects extraction

Secondary-school teachers are in constant need of finding relevant digital resources to support specific didactic goals. Unfortunately, generic search engines do not allow them to identify learning objects among semi-structured candidate educational resources, much less retrieve them by teaching goals. This article describes a multi-strategy approach for semantically guided extraction, indexing and search of educational metadata; it combines machine learning, concept analysis, and corpus-based natural language processing techniques. The overall model was validated by comparing extracted metadata against standard search methods and heuristic-based techniques for Classification Accuracy and Metadata Quality (as evaluated by actual teachers), yielding promising results and showing that this semantically guided metadata extraction can effectively enhance access and use of educational digital material.