In this correspondence we propose two modifications to the block truncation coding techniques. The first modification allows the partitioning of the image into variable size blocks rather than fixed size. The second m...
详细信息
In this correspondence we propose two modifications to the block truncation coding techniques. The first modification allows the partitioning of the image into variable size blocks rather than fixed size. The second modification is the use of an optimal threshold to quantize the blocks based on minimizing the mean square error.
A method for mobile robot localization using natural environmental features is presented. An attributed graph boundary representation of free space is used. A local sensor model is registered with a global model by a ...
详细信息
A method for mobile robot localization using natural environmental features is presented. An attributed graph boundary representation of free space is used. A local sensor model is registered with a global model by a subgraph isomorphism technique. Geometric and structural knowledge is used to search for mappings. The set of possible mappings is incrementally determined. Simultaneously, the associated coordinate transformation between the global and local models is refined. The model registration technique is implemented in software, and two examples are shown.< >
This paper describes the use of the blackboard architecture for the high level programming and control of autonomous mobile robots in a hazardous material spill emergency situation. The purpose of the robot is to perf...
详细信息
Feature selection is an important phase in most pattern recognition problems, especially when the space of the extracted features is very large. Feature selection methods attempt to reduce the feature space to satisfy...
详细信息
Feature selection is an important phase in most pattern recognition problems, especially when the space of the extracted features is very large. Feature selection methods attempt to reduce the feature space to satisfy certain objectives. We propose the concept of defining a performance potential as a measure of the effectiveness of the set of selected features. This paper begins by outlining a ranking scheme for features based on a feature’s calculated “performance potential”. The performance potential is made up of a number of performance measures: extraction time, memory requirements, variance, covariance and classification success. An adaptive scheme is proposed to process a number of initial features and arrive at the “best” subset based on their performance potential. The approach is applied to a texture analysis problem. The results of the testing of the approach point to conclusions concerning its effectiveness.
A representation for uncertain states within the context of robot task planning is described. This includes the probabilistic description of objects, relationships between objects, and operators. It is one component o...
详细信息
A representation for uncertain states within the context of robot task planning is described. This includes the probabilistic description of objects, relationships between objects, and operators. It is one component of a task planner designed for use in uncertain task domains. The planner is based on a game theoretic-approach which views the environment as an opponent (often fallible). Multiple outcomes arising from operator application in an uncertain world are attributed to moves of the opponent. These are called reaction operators. Their representation and effect on the planning process are discussed.< >
In this paper we are concerned with techniques for processing database queries that are not required to be formulated based on complete and precise knowledge of the query specification as defined in the database manag...
详细信息
In this paper we are concerned with techniques for processing database queries that are not required to be formulated based on complete and precise knowledge of the query specification as defined in the database management system. In specific, we consider processing queries that are ill-defined, not complete and fuzzy . We propose a query translator that tries to bridge the gap between the user's semantically stated query and its full specification as required by the database. The translator utilizes a graph based structure to represent queries and relations in the database. The translation process involves transforming incomplete query graphs into complete query graphs using attribute covering where the entities of the query are mapped to real entities of the database and functional dependency resolution, where the relational joins between these entities are established. The proposed translator is an attempt at incorporating intelligence in query processing systems to support user- friendly features such as cooperative and corrective responses from database systems.
The problem of finding the relative orientation between the reference frames of a line-mounted sensor and the link is formulated as a kinematic equation of the form A/sub a/A/sub x/=A/sub x/A/sub b/, which has to be s...
详细信息
The problem of finding the relative orientation between the reference frames of a line-mounted sensor and the link is formulated as a kinematic equation of the form A/sub a/A/sub x/=A/sub x/A/sub b/, which has to be solved for the rotational transformation matrix A/sub x/ given the transformations A/sub a/ and A/sub b/. This equation can be transformed to its equivalent form in terms of quaternion and then simplified to a well-structured linear system of equations of the form Bx=0. Since B is rank-deficient, the solution is not unique. The generalized-inverse method using singular-value decomposition (SVD) is applied. Although the solution is reached using the analysis of SVD, the SVD is derived symbolically; therefore, the actual implementation of SVD is not required. A method for obtaining a unique solution is proposed where a system of nonlinear equations is solved using Newton-Raphson iteration. The iteration is simplified by a dimension-reduction technique that provides a set of closed-form formulas for solving the resulting linear system of equations.< >
In the field of electronic fault detection much of the evaluation is performed by a human operator using a visual inspection system. One such system displays the current versus voltage (I-V) characteristics, referred ...
详细信息
In the field of electronic fault detection much of the evaluation is performed by a human operator using a visual inspection system. One such system displays the current versus voltage (I-V) characteristics, referred to as the impedance trace, of the electronic component under test. The shape of the impedance trace indicates the integrity of the component. The subjectivity and poor repeatability of the visual inspection have been identified as major deficiencies in the existing systems. A microprocessor-based system has been proposed to store and provide a quantitative classification of the impedance traces. The primary objective of this system is to provide an efficient automated system for classifying the impedance traces of different electronic components. Thus three trace representations and two classification schemes are proposed, based upon techniques developed in the field of pattern recognition. An experiment contrasts the different classification approaches. A Fourier series representation, combining both magnitude and phase features, was determined to provide the best overall performance when used in conjunction with a developed distance measure.
暂无评论