Byung-Uk Choi

Bayesian robot localization using spatial object contexts

We propose a semantic representation and Bayesian model for robot localization using spatial relations among objects that can be created by a single consumer-grade camera and odometry. We first suggest a semantic representation to be shared by human and robot. This representation consists of perceived objects and their spatial relationships, and a qualitatively defined odometry-based metric distance. We refer to this as a topological-semantic distance map. To support our semantic representation, we develop a Bayesian model for localization that enables the location of a robot to be estimated sufficiently well to navigate in an indoor environment. Extensive localization experiments in an indoor environment show that our Bayesian localization technique using a topological-semantic distance map is valid in the sense that localization accuracy improves whenever objects and their spatial relationships are detected and instantiated.

Active-semantic localization with a single consumer-grade camera

This study addressed the problem of active localization, which requires massive computation. To solve the problem, we developed abstracted measurements that consist of qualitative metrics estimated by a single camera. These are contextual representations consisting of perceived landmarks and their spatial relations, and they can be shared by humans and robots. Next, we enhanced the Markov localization method to support contextual representations with which a robots location can be sufficiently estimated. In contrast to passive methodologies, our approach actively uses the greedy technique to select a robots action and improve localization results. The experiment was carried out in an indoor environment, and results indicate that the proposed active-semantic localization yields more efficient localization.

An effective method for approximating the euclidean distance in high-dimensional space

It is crucial to compute the Euclidean distance between two vectors efficiently in high-dimensional space for multimedia information retrieval. We propose an effective method for approximating the Euclidean distance between two high-dimensional vectors. For this approximation, a previous method, which simply employs norms of two vectors, has been proposed. This method, however, ignores the angle between two vectors in approximation, and thus suffers from large approximation errors. Our method introduces an additional vector called a reference vector for estimating the angle between the two vectors, and approximates the Euclidean distance accurately by using the estimated angle. This makes the approximation errors reduced significantly compared with the previous method. Also, we formally prove that the value approximated by our method is always smaller than the actual Euclidean distance. This implies that our method does not incur any false dismissal in multimedia information retrieval. Finally, we verify the superiority of the proposed method via performance evaluation with extensive experiments.

Vector graphic reference implementation for embedded system

We propose the reference implementation with software rendering of OpenVG for the scalable vector graphic hardware acceleration, which the Khronos group standardizes. We present the design scheme that enables EGL and OpenVG to be ported easily in an embedded environment. Moreover, we describe the background of selection of an algorithm, and the mathematical function adopted for the performance improvement, and we propose the optimum rendering method. We present displaying of vector image on a screen through the OpenVG implemented using software rendering method. And, we present the test result of the CTS which is compatibility test tool. And we show the performance comparison against the Hybrid corp.s reference implementation.

Salable Vector Graphics (OpenVG) for Creating Animation Image in Embedded Systems

We propose the reference implementation with software rendering of OpenVG for the scalable vector graphic hardware acceleration, which the Khronos group standardizes. We present the design scheme that enables EGL and OpenVG to be ported easily in an embedded environment. Moreover, we describe the background of selection of an algorithm, and the mathematical function adopted for the performance improvement, and we propose the optimum rendering method. We present displaying of vector image on a screen through the OpenVG implemented using software rendering method. And, we present the test result of the CTS which is compatibility test tool. And we show the performance comparison against the Hybrid corp.s reference implementation.

Indoor Place Classification Using Robot Behavior and Vision Data

To realize autonomous navigation of intelligent robots in a variety of settings, analysis and classification of places, and the ability to actively collect information are necessary. In this paper, visual data are organized into an orientation histogram to roughly express input images by extracting and cumulating straight lines according to direction angle. In addition, behavioral data are organized into a behavioral histogram by cumulating motions performed to avoid obstacles encountered while the robot is executing specified behavioral patterns. These visual and behavioral data are utilized as input data, and the probability that a place belongs to a specific class is calculated by designating the places already learnt by the robot as categories. The naïve Bayes classification method is employed, in which the probability is calculated that the input data belong to each specific category, and the category with the highest probability is then selected. The location of the robot is classified by merging the probabilities for visual and behavioral data. The experimental results are as follows. First, a comparison of behavioral patterns used by the robot to collect data about a place indicates that a rotational behavior pattern provides the best performance. Second, classification performance is more accurate with two types of input data than with a single type of data.

Dimensionality reduction for similarity search with the Euclidean distance in high-dimensional applications

In multimedia information retrieval, multimedia data are represented as vectors in high-dimensional space. To search these vectors efficiently, a variety of indexing methods have been proposed. However, the performance of these indexing methods degrades dramatically with increasing dimensionality, which is known as the dimensionality curse. To resolve the dimensionality curse, dimensionality reduction methods have been proposed. They map feature vectors in high-dimensional space into vectors in low-dimensional space before the data are indexed. This paper proposes a novel method for dimensionality reduction based on a function that approximates the Euclidean distance based on the norm and angle components of a vector. First, we identify the causes of, and discuss basic solutions to, errors in angle approximation during the approximation of the Euclidean distance. Then, this paper propose a new method for dimensionality reduction that extracts a set of subvectors from a feature vector and maintains only the norm and the approximated angle for every subvector. The selection of a good reference vector is crucial for accurate approximation of the angle component. We present criteria for being a good reference vector, and propose a method that chooses a good reference vector. Also, we define a novel distance function using the norm and angle components, and formally prove that the distance function consistently lower-bounds the Euclidean distance. This implies information retrieval with this function does not incur any false dismissals. Finally, the superiority of the proposed approach is verified via extensive experiments with synthetic and real-life data sets.

Cognitive representation and Bayeisan model of spatial object contexts for robot localization

This paper proposes a cognitive representation and Bayesian model for spatial relations among objects that can be constructed with perception data acquired by a single consumer-grade camera. We first suggest a cognitive representation to be shared by humans and robots consisting of perceived objects and their spatial relations. We then develop Bayesian models to support our cognitive representation with which the location of a robot can be estimated sufficiently well to allow the robot to navigate in an indoor environment. Based on extensive localization experiments in an indoor environment, we show that our cognitive representation is valid in the sense that the localization accuracy improves whenever new objects and their spatial relations are detected and instantiated.

Virtual Tactical Map with Tangible Augmented Reality Interface

We propose a new augmented reality (AR)-based approach for training using virtual sand table representations of military battlefields. A virtual tactical map (VTM) can archive simple actions such as moving a marker by hand, to provide more organic realizations in virtual military training. The new tangible AR interface provides a content-authoring tool that is natural, intuitive, and user-friendly. AR-interfaced VTMs exhibit multiple possibilities for military learning and training applications.

News video retrieval using automatic indexing of korean closed-caption

Knowledge-based video retrieval is able to provide the retrieval result that corresponds with conceptual demand of user because of performing automatic indexing with audio-visual data, closed-caption, and so on. In this paper, we present the automatic indexing method of Korean closed-caption for knowledge-based video retrieval and the retrieval scheme using the indexed database. In the experiment, we have applied the proposed method to news video with the closed-caption generated by Korean stenographic system, and have empirically confirmed that the proposed method could provide the retrieval result that corresponds with more meaningful conceptual demand of user.