Database Indexing Methods for 3D Hand Pose Estimation

Estimation of 3D hand pose is useful in many gesture recognition applications, ranging from human-computer interaction to automated recognition of sign languages. In this paper, 3D hand pose estimation is treated as a database indexing problem. Given an input image of a hand, the most similar images in a large database of hand images are retrieved. The hand pose parameters of the retrieved images are used as estimates for the hand pose in the input image. Lipschitz embeddings of edge images into a Euclidean space are used to improve the efficiency of database retrieval. In order to achieve interactive retrieval times, similarity queries are initially performed in this Euclidean space. The paper describes ongoing work that focuses on how to best choose reference images, in order to improve retrieval accuracy.

Image-based localization and pose recovery using scale invariant features

In this paper, we propose a vision based mobile robot localization strategy. Local scale-invariant features are used as natural landmarks in unstructured and unmodified environment. The local characteristics of the features we use prove to be robust to occlusion and outliers. In addition, the invariance of the features to viewpoint change makes them suitable landmarks for mobile robot localization. Scale-invariant features detected in the first exploration are indexed into a location database. Indexing and voting allow efficient recognition of global localization. The localization result is verified by epipolar geometry between the representative view in database and the view to be localized, thus the probability of false localization will be decreased. The localization system can recover the pose of the camera mounted on the robot by essential matrix decomposition. Then the position of the robot can be computed easily. Both calibrated and un-calibrated cases are discussed and relative position estimation based on calibrated camera turns out to be the better choice. Experimental results show that our approach is effective and reliable in the case of illumination changes, similarity transformations and extraneous features. © 2004 IEEE.

Estimating 3D Hand Pose from a Cluttered Image

A method is proposed that can generate a ranked list of plausible three-dimensional hand configurations that best match an input image. Hand pose estimation is formulated as an image database indexing problem, where the closest matches for an input hand image are retrieved from a large database of synthetic hand images. In contrast to previous approaches, the system can function in the presence of clutter, thanks to two novel clutter-tolerant indexing methods. First, a computationally efficient approximation of the image-to-model chamfer distance is obtained by embedding binary edge images into a high-dimensional Euclide an space. Second, a general-purpose, probabilistic line matching method identifies those line segment correspondences between model and input images that are the least likely to have occurred by chance. The performance of this clutter-tolerant approach is demonstrated in quantitative experiments with hundreds of real hand images.

Not published, not indexed: issues in generating and finding hospice and palliative care literature.

INTRODUCTION: Accessing new knowledge as the evidence base for hospice and palliative care grows has specific challenges for the discipline. This study aimed to describe conversion rates of palliative and hospice care conference abstracts to journal articles and to highlight that some palliative care literature may not be retrievable because it is not indexed on bibliographic databases. METHODS: Substudy A tracked the journal publication of conference abstracts selected for inclusion in a gray literature database on www.caresearch.com.au . Abstracts were included in the gray literature database following handsearching of proceedings of over 100 Australian conferences likely to have some hospice or palliative care content that were held between 1980 and 1999. Substudy B looked at indexing from first publication until 2001 of three international hospice and palliative care journals in four widely available bibliographic databases through systematic tracing of all original papers in the journals. RESULTS: Substudy A showed that for the 1338 abstracts identified only 15.9% were published (compared to an average in health of 45%). Published abstracts were found in 78 different journals. Multiauthor abstracts and oral presentations had higher rates of conversion. Substudy B demonstrated lag time between first publication and bibliographic indexing. Even after listing, idiosyncratic noninclusions were identified. DISCUSSION: There are limitations to retrieval of all possible literature through electronic searching of bibliographic databases. Encouraging publication in indexed journals of studies presented at conferences, promoting selection of palliative care journals for database indexing, and searching more than one bibliographic database will improve the accessibility of existing and new knowledge in hospice and palliative care.

Graph matching : fast candidate elimination using machine learning techniques

Graph matching is an important class of methods in pattern recognition. Typically, a graph representing an unknown pattern is matched with a database of models. If the database of model graphs is large, an additional factor in induced into the overall complexity of the matching process. Various techniques for reducing the influence of this additional factor have been described in the literature. In this paper we propose to extract simple features from a graph and use them to eliminate candidate graphs from the database. The most powerful set of features and a decision tree useful for candidate elimination are found by means of the C4.5 algorithm, which was originally proposed for inductive learning of classication rules. Experimental results are reported demonstrating that effcient candidate elimination can be achieved by the proposed procedure.

Toward efficient multifeature query processing

In many advanced applications, data are described by multiple high-dimensional features. Moreover, different queries may weight these features differently; some may not even specify all the features. In this paper, we propose our solution to support efficient query processing in these applications. We devise a novel representation that compactly captures f features into two components: The first component is a 2D vector that reflects a distance range ( minimum and maximum values) of the f features with respect to a reference point ( the center of the space) in a metric space and the second component is a bit signature, with two bits per dimension, obtained by analyzing each feature's descending energy histogram. This representation enables two levels of filtering: The first component prunes away points that do not share similar distance ranges, while the bit signature filters away points based on the dimensions of the relevant features. Moreover, the representation facilitates the use of a single index structure to further speed up processing. We employ the classical B+-tree for this purpose. We also propose a KNN search algorithm that exploits the access orders of critical dimensions of highly selective features and partial distances to prune the search space more effectively. Our extensive experiments on both real-life and synthetic data sets show that the proposed solution offers significant performance advantages over sequential scan and retrieval methods using single and multiple VA-files.

Direct mesh: A multiresolution approach to terrain visualization

Terrain can be approximated by a triangular mesh consisting millions of 3D points. Multiresolution triangular mesh (MTM) structures are designed to support applications that use terrain data at variable levels of detail (LOD). Typically, an MTM adopts a tree structure where a parent node represents a lower-resolution approximation of its descendants. Given a region of interest (ROI) and a LOD, the process of retrieving the required terrain data from the database is to traverse the MTM tree from the root to reach all the nodes satisfying the ROI and LOD conditions. This process, while being commonly used for multiresolution terrain visualization, is inefficient as either a large number of sequential I/O operations or fetching a large amount of extraneous data is incurred. Various spatial indexes have been proposed in the past to address this problem, however level-by-level tree traversal remains a common practice in order to obtain topological information among the retrieved terrain data. A new MTM data structure called direct mesh is proposed. We demonstrate that with direct mesh the amount of data retrieval can be substantially reduced. Comparing with existing MTM indexing methods, a significant performance improvement has been observed for real-life terrain data.

Towards effective indexing for very large video sequence database

With rapid advances in video processing technologies and ever fast increments in network bandwidth, the popularity of video content publishing and sharing has made similarity search an indispensable operation to retrieve videos of user interests. The video similarity is usually measured by the percentage of similar frames shared by two video sequences, and each frame is typically represented as a high-dimensional feature vector. Unfortunately, high complexity of video content has posed the following major challenges for fast retrieval: (a) effective and compact video representations, (b) efficient similarity measurements, and (c) efficient indexing on the compact representations. In this paper, we propose a number of methods to achieve fast similarity search for very large video database. First, each video sequence is summarized into a small number of clusters, each of which contains similar frames and is represented by a novel compact model called Video Triplet (ViTri). ViTri models a cluster as a tightly bounded hypersphere described by its position, radius, and density. The ViTri similarity is measured by the volume of intersection between two hyperspheres multiplying the minimal density, i.e., the estimated number of similar frames shared by two clusters. The total number of similar frames is then estimated to derive the overall similarity between two video sequences. Hence the time complexity of video similarity measure can be reduced greatly. To further reduce the number of similarity computations on ViTris, we introduce a new one dimensional transformation technique which rotates and shifts the original axis system using PCA in such a way that the original inter-distance between two high-dimensional vectors can be maximally retained after mapping. An efficient B+-tree is then built on the transformed one dimensional values of ViTris' positions. Such a transformation enables B+-tree to achieve its optimal performance by quickly filtering a large portion of non-similar ViTris. Our extensive experiments on real large video datasets prove the effectiveness of our proposals that outperform existing methods significantly.

A multimedia indexing and retrieval framework for multimedia database systems

The main challenges of multimedia data retrieval lie in the effective mapping between low-level features and high-level concepts, and in the individual users' subjective perceptions of multimedia content. ^ The objectives of this dissertation are to develop an integrated multimedia indexing and retrieval framework with the aim to bridge the gap between semantic concepts and low-level features. To achieve this goal, a set of core techniques have been developed, including image segmentation, content-based image retrieval, object tracking, video indexing, and video event detection. These core techniques are integrated in a systematic way to enable the semantic search for images/videos, and can be tailored to solve the problems in other multimedia related domains. In image retrieval, two new methods of bridging the semantic gap are proposed: (1) for general content-based image retrieval, a stochastic mechanism is utilized to enable the long-term learning of high-level concepts from a set of training data, such as user access frequencies and access patterns of images. (2) In addition to whole-image retrieval, a novel multiple instance learning framework is proposed for object-based image retrieval, by which a user is allowed to more effectively search for images that contain multiple objects of interest. An enhanced image segmentation algorithm is developed to extract the object information from images. This segmentation algorithm is further used in video indexing and retrieval, by which a robust video shot/scene segmentation method is developed based on low-level visual feature comparison, object tracking, and audio analysis. Based on shot boundaries, a novel data mining framework is further proposed to detect events in soccer videos, while fully utilizing the multi-modality features and object information obtained through video shot/scene detection. ^ Another contribution of this dissertation is the potential of the above techniques to be tailored and applied to other multimedia applications. This is demonstrated by their utilization in traffic video surveillance applications. The enhanced image segmentation algorithm, coupled with an adaptive background learning algorithm, improves the performance of vehicle identification. A sophisticated object tracking algorithm is proposed to track individual vehicles, while the spatial and temporal relationships of vehicle objects are modeled by an abstract semantic model. ^

GRDB: A general purpose relational database system

This article discusses the design and development of GRDB (General Purpose Relational Data Base System) which has been implemented on a DEC-1090 system in Pascal. GRDB is a general purpose database system designed to be completely independent of the nature of data to be handled, since it is not tailored to the specific requirements of any particular enterprise. It can handle different types of data such as variable length records and textual data. Apart from the usual database facilities such as data definition and data manipulation, GRDB supports User Definition Language (UDL) and Security definition language. These facilities are provided through a SEQUEL-like General Purpose Query Language (GQL). GRDB provides adequate protection facilities up to the relation level. The concept of “security matrix” has been made use of to provide database protection. The concept of Unique IDentification number (UID) and Password is made use of to ensure user identification and authentication. The concept of static integrity constraints has been used to ensure data integrity. Considerable efforts have been made to improve the response time through indexing on the data files and query optimisation. GRDB is designed for an interactive use but alternate provision has been made for its use through batch mode also. A typical Air Force application (consisting of data about personnel, inventory control, and maintenance planning) has been used to test GRDB and it has been found to perform satisfactorily.

Coarse-to-fine vision-based localization by indexing scale-invariant features

This paper presents a novel coarse-to-fine global localization approach inspired by object recognition and text retrieval techniques. Harris-Laplace interest points characterized by scale-invariant transformation feature descriptors are used as natural landmarks. They are indexed into two databases: a location vector space model (LVSM) and a location database. The localization process consists of two stages: coarse localization and fine localization. Coarse localization from the LVSM is fast, but not accurate enough, whereas localization from the location database using a voting algorithm is relatively slow, but more accurate. The integration of coarse and fine stages makes fast and reliable localization possible. If necessary, the localization result can be verified by epipolar geometry between the representative view in the database and the view to be localized. In addition, the localization system recovers the position of the camera by essential matrix decomposition. The localization system has been tested in indoor and outdoor environments. The results show that our approach is efficient and reliable. © 2006 IEEE.

Learning Euclidean Embeddings for Indexing and Classification

BoostMap is a recently proposed method for efficient approximate nearest neighbor retrieval in arbitrary non-Euclidean spaces with computationally expensive and possibly non-metric distance measures. Database and query objects are embedded into a Euclidean space, in which similarities can be rapidly measured using a weighted Manhattan distance. The key idea is formulating embedding construction as a machine learning task, where AdaBoost is used to combine simple, 1D embeddings into a multidimensional embedding that preserves a large amount of the proximity structure of the original space. This paper demonstrates that, using the machine learning formulation of BoostMap, we can optimize embeddings for indexing and classification, in ways that are not possible with existing alternatives for constructive embeddings, and without additional costs in retrieval time. First, we show how to construct embeddings that are query-sensitive, in the sense that they yield a different distance measure for different queries, so as to improve nearest neighbor retrieval accuracy for each query. Second, we show how to optimize embeddings for nearest neighbor classification tasks, by tuning them to approximate a parameter space distance measure, instead of the original feature-based distance measure.

Learning Embeddings for Indexing, Retrieval, and Classification, with Applications to Object and Shape Recognition in Image Databases

Nearest neighbor retrieval is the task of identifying, given a database of objects and a query object, the objects in the database that are the most similar to the query. Retrieving nearest neighbors is a necessary component of many practical applications, in fields as diverse as computer vision, pattern recognition, multimedia databases, bioinformatics, and computer networks. At the same time, finding nearest neighbors accurately and efficiently can be challenging, especially when the database contains a large number of objects, and when the underlying distance measure is computationally expensive. This thesis proposes new methods for improving the efficiency and accuracy of nearest neighbor retrieval and classification in spaces with computationally expensive distance measures. The proposed methods are domain-independent, and can be applied in arbitrary spaces, including non-Euclidean and non-metric spaces. In this thesis particular emphasis is given to computer vision applications related to object and shape recognition, where expensive non-Euclidean distance measures are often needed to achieve high accuracy. The first contribution of this thesis is the BoostMap algorithm for embedding arbitrary spaces into a vector space with a computationally efficient distance measure. Using this approach, an approximate set of nearest neighbors can be retrieved efficiently - often orders of magnitude faster than retrieval using the exact distance measure in the original space. The BoostMap algorithm has two key distinguishing features with respect to existing embedding methods. First, embedding construction explicitly maximizes the amount of nearest neighbor information preserved by the embedding. Second, embedding construction is treated as a machine learning problem, in contrast to existing methods that are based on geometric considerations. The second contribution is a method for constructing query-sensitive distance measures for the purposes of nearest neighbor retrieval and classification. In high-dimensional spaces, query-sensitive distance measures allow for automatic selection of the dimensions that are the most informative for each specific query object. It is shown theoretically and experimentally that query-sensitivity increases the modeling power of embeddings, allowing embeddings to capture a larger amount of the nearest neighbor structure of the original space. The third contribution is a method for speeding up nearest neighbor classification by combining multiple embedding-based nearest neighbor classifiers in a cascade. In a cascade, computationally efficient classifiers are used to quickly classify easy cases, and classifiers that are more computationally expensive and also more accurate are only applied to objects that are harder to classify. An interesting property of the proposed cascade method is that, under certain conditions, classification time actually decreases as the size of the database increases, a behavior that is in stark contrast to the behavior of typical nearest neighbor classification systems. The proposed methods are evaluated experimentally in several different applications: hand shape recognition, off-line character recognition, online character recognition, and efficient retrieval of time series. In all datasets, the proposed methods lead to significant improvements in accuracy and efficiency compared to existing state-of-the-art methods. In some datasets, the general-purpose methods introduced in this thesis even outperform domain-specific methods that have been custom-designed for such datasets.

Content-based video indexing for sports applications using integrated multi-modal approach

This thesis presents a research work based on an integrated multi-modal approach for sports video indexing and retrieval. By combining specific features extractable from multiple (audio-visual) modalities, generic structure and specific events can be detected and classified. During browsing and retrieval, users will benefit from the integration of high-level semantic and some descriptive mid-level features such as whistle and close-up view of player(s). The main objective is to contribute to the three major components of sports video indexing systems. The first component is a set of powerful techniques to extract audio-visual features and semantic contents automatically. The main purposes are to reduce manual annotations and to summarize the lengthy contents into a compact, meaningful and more enjoyable presentation. The second component is an expressive and flexible indexing technique that supports gradual index construction. Indexing scheme is essential to determine the methods by which users can access a video database. The third and last component is a query language that can generate dynamic video summaries for smart browsing and support user-oriented retrievals.