• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1459-1466
• /
• 2018

Robots which detect human and recognize action are important factors for human interaction, and many researches have been conducted. Recently, deep learning technology has developed and learning based robot's technology is a major research area. These studies require a database to learn and evaluate for intelligent human perception. In this paper, we propose a multi-modal sensor-based image database condition considering the security task by analyzing the image database to detect the person in the outdoor environment and to recognize the behavior during the running of the robot.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 C
• /
• pp.1832-1834
• /
• 2004

The degree of contamination on outdoor insulator is one of the most importance factors to determine the pollution level of outdoor insulations, and the sea salt is known as the most dangerous pollutant. As shown through the preceding study, the generation of salt pollutant and the pollution degree of outdoor insulator have a close relation with meteorological conditions, such as wind velocity, rainfall, and so on. So, in this paper, we have made database using the past meteorological data and ESDD(equivalent salt deposit density) and then we predicted the pollution degree in the future after analyzing currently meteorological data of database.

• 제어로봇시스템학회논문지
• /
• 제14권11호
• /
• pp.1139-1145
• /
• 2008

A robust position sensing system is proposed in this paper for a ubiquitous mobile robot which moves indoors as well as outdoors. The Differential GPS (DGPS) which has a position estimation error of less than 5 m is a general solution when the mobile robot is moving outdoor, while an active beacon system (ABS) with embedded ultrasonic sensors is reliable as an indoor positioning system. The switching from the outdoor to indoor or vice versa causes unstable measurements on account of the reference coordinates and algorithm changes. To minimize the switching time in the position estimation and to stabilize the measurement, a robust position sensing system is proposed. In the system, to minimize the switching delay, the door positions are stored and updated in a database. Using the database, the approaching status of the mobile robot from indoor to outdoor or vice versa has been checked and the switching conditions are prepared before the mobile robot actually moves out or moves into the door. The reliability and accuracy of the robust positioning system based on DGPS and ABS are verified and demonstrated through the real experiments using a mobile robot prepared for this research.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1647-1658
• /
• 2016

RGB+D database has been widely used in object recognition, object tracking, robot control, to name a few. While rapid advance of active depth sensing technologies allows for the widespread of indoor RGB+D databases, there are only few outdoor RGB+D databases largely due to an inherent limitation of active depth cameras. In this paper, we propose a novel method used to build outdoor RGB+D databases. Instead of using active depth cameras such as Kinect or LIDAR, we acquire a pair of stereo image using high-resolution stereo camera and then obtain a depth map by applying stereo matching algorithm. To deal with estimation errors that inevitably exist in the depth map obtained from stereo matching methods, we develop an approach that estimates confidence of depth maps based on unsupervised learning. Unlike existing confidence estimation approaches, we explicitly consider a spatial correlation that may exist in the confidence map. Specifically, we focus on refining confidence feature with the assumption that the confidence feature and resultant confidence map are smoothly-varying in spatial domain and are highly correlated to each other. Experimental result shows that the proposed method outperforms existing confidence measure based approaches in various benchmark dataset.

• 한국측량학회지
• /
• 제36권3호
• /
• pp.185-196
• /
• 2018

In order to overcome the problem that outdoor and indoor spatial information service are separately utilized, an integration service system of spatial information that is linked from outdoor to indoor has been implemented. As a result of the study, "0001.xml" corresponding to the file index key value, which is the service connection information in the building information of the destination, was extracted from the prototype verification of the system, the search word of 'Kim AB' was transmitted to the indoor map server and converted from the outdoor map service to the indoor map service through confirmation of the navigation service connected information, using service linkage information and search words of the indoor map service was confirmed that the route was displayed from the entrance of the building to the destination in the building through the linkage search DB (Database) table and the search query. Therefore, through this study was examined the possibility of linking indoor and outdoor DB through vector spatial information integration service system. The indoor map and the map engine were implemented based on the same vector map format as the outdoor map engine, it was confirmed that the connectivity of the map engine can be applied.

• 로봇학회논문지
• /
• 제2권3호
• /
• pp.221-226
• /
• 2007

A robust position-sensing system is proposed in this paper for ubiquitous mobile robots which move indoor as well as outdoor. The Differential GPS (DGPS) which has position estimation error of less than 5 m is a general solution when the mobile robots are moving outdoor, while an active beacon system (ABS) with embedded ultrasonic sensors is selected as an indoor positioning system. The switching from the outdoor to indoor or vice versa causes unstable measurements on account of the reference and algorithm changes. To minimize the switching time in the position estimation and to stabilize the measurement, a robust position-sensing system is proposed. In the system, to minimize the switching delay, the door positions are stored and updated in a database. The reliability and accuracy of the robust positioning system based on DGPS and ABS are verified through the real experiments using a mobile robot prepared for this research and demonstrated.

• Agribusiness and Information Management
• /
• 제7권1호
• /
• pp.1-9
• /
• 2015

The purpose of this study is to develop a growth prediction model that can predict growth and development information influencing the production of citrus fruits: the growth model algorithm that can predict floral leaf ratio, number of fruit sets, fruit width, and overweight depending on the main period of growth and development with consideration of the applied weather factors. Every year, large scale of manpower was mobilized to investigate the production of outdoor-grown citrus fruits, but it was limited to recycling the data without an observation supporting system to systemize the database. This study intends to create a systematical database based on the basic data obtained through the observation supporting system in application of an algorithm according to the accumulated long term data and prepare a base for its continuous improvement and development. The importance of the observed data is increasingly recognized every year, and the citrus fruit observation supporting system is important for utilizing an effective policy and decision making according to various applications and analysis results through an interconnection and an integration of the investigated statistical data. The citrus fruit is a representative crop having a great ripple effect in Jeju agriculture. An early prediction of the growth and development information influencing the production of citrus fruits may be helpful for decision making in supply and demand control of agricultural products.

• 제어로봇시스템학회논문지
• /
• 제16권3호
• /
• pp.277-285
• /
• 2010

This paper describes an approach to analyze geometrical information of building images for understanding outdoor environment of autonomous navigation robot. Line segments and color information are used to classily a building with the other objects such as sky, trees, and roads. The line segments and their two neighboring regions are extracted from detected edges in image. The model of line segment (MLS) consists of color information of neighbor regions. This model rules out the line segments of non-building face. A building face converges into dominant vanishing points (DVPs) which include one vertical point and one of five horizontal points in maximum. The intersection of vertical and horizontal lines creates a facet of building. The geometrical characteristics such as the center coordinates, area, aspect ratio and aligned coexistence are used for extracting the windows in the building facet. In experiments, 150 building faces and 1607 windows were detected from the database of outdoor environment. We found that this result shows 94.46% detection rate. These experimental images were all taken in Ulsan metropolitan city in Korea under difference of viewpoints, daytime, camera system and weather condition.

• 한국통신학회논문지
• /
• 제40권8호
• /
• pp.1655-1666
• /
• 2015

본 논문에서는 Fingerprint 기법의 Resource로 신호의 세기가 아닌 이미지를 이용해 좌표정보를 포함하는 이미지 기반의 데이터베이스를 구축하고, 사용자로부터 입력되는 이미지와 유사도 비교를 통해 사용자의 위치추정 기법에 대해 제안한다. Fingerprint 기법은 신호 세기뿐만 아니라 환경에 대한 지역적 잡음 정보들까지 모두 추정에 반영하므로 높은 위치 추정 정확도를 제공한다. 이미지의 유사도는 SURF 알고리즘을 통해 데이터베이스와 사용자 입력 이미지의 특징점을 검출하고, 동일한 특징점 간의 매칭을 통해 비교된다. 여기에서 우리는 RANSAC 알고리즘을 함께 사용하여 검출된 특징점의 노이즈 제거를 통해 이미지 유사도 비교의 정확도를 높였다. 제안하는 기법의 검증을 위해 두 건물의 실내와 주변 실외 환경에서 이미지를 획득하여 데이터베이스를 구축하고, 임의의 위치에서 사용자의 위치를 추정하였다. 추정 된 최종 위치는 데이터베이스에 저장 된 이미지가 가지는 좌표가 사용자의 위치와 가장 근접한 좌표로 검출되는지 확인하였으며 RANSAC을 통해 특징점의 노이즈 제거 전과 제거 후에 대한 이미지 유사도 비교의 성능을 분석하였다.

• 대한전자공학회논문지SP
• /
• 제46권5호
• /
• pp.48-55
• /
• 2009

실내외 영상 분류에 대한 연구는 밝기나 에지 정보와 같이 하위 레벨(low-level) 정보의 단순 결합을 이용하여 수행되어 왔다. 그러나 기존의 하위 레벨 영상 정보만을 기반으로 하는 실내외 영상 분류 방법은 다양한 콘텐츠를 극복하는데 한차가 군기 때문에 상위 레벨(high-level) 영상 정보를 함께 이용하는 방법에 대한 연구가 많이 진행되어 왔다. 이러한 연구의 대부분은 영상 내 하늘이나 수풀과 같은 영역을 검출하기 위해 별도의 알고리즘을 수행하기 때문에 특징 벡터의 차원을 증가시키거나 수행 속도를 저하시키는 문제점이 있다. 따라서 본 논문에서는 이러한 문제점을 극복하기 위해 효율적인 실내외 영상 분류 기법을 제안한다. 먼저 효과적인 특징 벡터를 생성하기 위해 영상을 5개의 하위 블록으로 나눈다. 각각의 블록에 대하여, 제안하는 에지 색상 방향 히스토그램(edge and color orientation histogram, ECOH) 기술사(descriptor)를 이용하여 해당 블록을 표현하고 모든 블록의 값을 연결하여 최종적으로 특징 벡터를 생성한다. 제안하는 알고리즘의 효율성과 강건함을 보이기 위해 1200개 이상의 다양한 실내외 영상을 사용하였으며, 학습을 통해 각 영역의 가중치를 결정하여 분류 성능을 향상 시켰다.