본 연구의 목적은 지반침하를 방지하기 위하여 지반에 매립된 파이프 및 공동의 패턴 데이터베이스를 구축하는데 있다. 이를 위하 여 Open CV를 이용한 패턴 템플레이트 알고리즘을 개발하였으며, 이를 토조 GPR 탐사결과에 적용하였다. 그 결과 적절한 패턴 데이터베이스 구축이 가능하였다. 본 연구결과는 제한적인 실험결과만을 근거로 한 것이기 때문에, 향후 다양한 현장자료 및 대규모 테스트베드의 탐사결과 등이 보완되면 보다 실증적인 자료가 구축될 것으로 판단된다.

In a large scale robot system, one of important problems is software integration, which involves three elements: modularity, reusability and stability. By these issues, the degree of convenience of system integration, its required time and the performance of the system stability can be determined. In addition, the convenience of system management can be determined by the degree of completion of service components. This paper explains the template based service component (TBSC) for the integration of service components in networked robot. The important characteristics of TBSC are automatical execution and recovery process by a PnP supporting robot framework, which helps a system operator to manage a robot system comfortably. For easy implementation and system stability, we provide a service component creator and a verification tool to developers.

This paper is concerned with the template-based face recognition from robot camera images with illumination and distance variations. The approaches used in this paper consist of Eigenface, Fisherface, and Icaface which are the most representative recognition techniques frequently used in conjunction with face recognition. These approaches are based on a popular unsupervised and supervised statical technique that supports finding useful image representations, respectively. Thus we focus on the performance comparison from robot camera images with unwanted variations. The comprehensive experiments are completed for a databases with illumination and distance variations.