• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.6360-6367
• /
• 2015

The location selection of the element that should guarantee easy visual perception, like the landmark, is the a topic that appears much in the design process. Recently, a graph analysis technique using computers has been applied in order to evaluate the visibility of the visual element, but the analytic frame is flat and the setting of the visual pont and the matrix are fixed so there were great limitations in obtaining the results of the practical analysis. Thus, this study presented Nondirectional Multi-Dimensional Calculation (MDVC-N), an analytic methodology available for the analysis of the dynamic visual point in the 3D environment. It thus attempted to establish the analytic application using the 3D computer graphics technology and designed a script structure to set the visual point and the matrix. In addition to that, this study tried to verify the analytic methodology by applying the complex land as an example model, where buildings in various heights of terrains with a high-differences are located, verifying the same analytic methodology. It thus tried to identify the visual characteristics of each alternative location. The following results were gained from the study. 1) The visibility can be measured quantitatively trough the application of the 6-alternatives. 2) Using the 3dimensional graph, intuitive analysis was possible. 3) It attempted to improve the analytic applicability by calculating the results corrected as a variable behavior from the local integration variable of the space syntax.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.264-264
• /
• 2000

In this paper, we propose a method to automatically extract stable visual landmarks from observed data for a mobile robot with stereo vision system. The robot selects as stable landmarks vertical line segments which are distinct and on planar surfaces, because they are expected to be observed reliably from various view-points. When the robot moves, it uses several, less uncertain landmarks for estimating its motion. Experimental results in real scenes show the validity of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.9
• /
• pp.379-390
• /
• 2019

In this paper, we propose a novel deep neural network model for Vision-and-Language Navigation (VLN) named LVLN (Landmark-based VLN). In addition to both visual features extracted from input images and linguistic features extracted from the natural language instructions, this model makes use of information about places and landmark objects detected from images. The model also applies a context-based attention mechanism in order to associate each entity mentioned in the instruction, the corresponding region of interest (ROI) in the image, and the corresponding place and landmark object detected from the image with each other. Moreover, in order to improve the success rate of arriving the target goal, the model adopts a progress monitor module for checking substantial approach to the target goal. Conducting experiments with the Matterport3D simulator and the Room-to-Room (R2R) benchmark dataset, we demonstrate high performance of the proposed model.

• Journal of Environmental Science International
• /
• v.11 no.4
• /
• pp.271-279
• /
• 2002

The purpose of this study is to focus on the townscape of Daegu based on the urban characteristics of the landscape cognition and images captured by citizens. The analysis was performed by the data obtained from questionnaires and interviews. This study methods were deals the cognition characteristics, landmark landscape, visual preference landscape, image and satisfaction. The results are summarized as follows: 1. The orders of cognition landscapes were estimated Apple＞ Weather＞ Texture＞ Mt.Palgong＞ Daegu Tower＞ Pretty Girl＞ Mt. Apsan＞ Dalsung Park＞ Conservative＞ Dongsung Road, etc. That is constructed Nonphysical elements(62.0%) and Physical elements(38.0%) 2. The orders of representative landscape(Landmark) in city were estimated Mt.Palgong＞ Daegu Tower＞ Gat Rock＞ Mt.Apsan＞ Dalsung Park, etc. As a whole middle and old people(over 30gen) preferenced as a history landscape or natural landscape, but youth people(10-20gen) preferenced as visible and interesting artifical places. 3. While the positive attitudes for the image of city were traditional(3.30), intimacy(3.58), and rest(2.90), the negative attitudes were unnewly(2.34), closing(2.37) and narrow(2.40). Also total satisfaction for that was estimated 5.51. 4. Psychological factors, related to the satisfaction of the image of city were composed of four factors, individuality character, pleasure character, amenity character, formation character. And the presumption formula of satisfaction was: Satisfaction = 5.477 ＋ 0.752(Individuality) ＋ 0.470(Pleasure) ＋ 0.413(Amenity) ＋ 0.241(Formation).

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.353-364
• /
• 2009

In this paper, a SLAM (Simultaneous Localization and Mapping) method using a single camera and planar fiducial markers is proposed. Fiducial markers are planar patterns that are mounted on the ceiling or wall. Each fiducial marker has a unique hi-tonal identification pattern with square outlines. It can be printed on paper to reduce cost or it can be painted using retro-reflective paint in order to make invisible and prevent undesirable visual effects. Existing localization methods using artificial landmarks have the disadvantage that landmark locations must be known a priori. In contrast, the proposed method can build a map and estimate robot location even if landmark locations are not known a priori. Hence, it reduces installation time and setup cost. The proposed method works good even when only one fiducial marker is seen at a scene. We perform computer simulation to evaluate proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.219-222
• /
• 1996

During the navigation of mobile robot, one of the essential task is to determination the absolute location of mobile robot. In this paper, we proposed a method to determine the position of the camera from a landmark through the visual image of a quadrangle typed landmark using neural network. In determining the position of the camera on the world coordinate, there is difference between real value and calculated value because of uncertainty in pixels, incorrect camera calibration and lens distortion etc. This paper describes the solution of the above problem using BPN(Back Propagation Network). The experimental results show the superiority of the proposed method in comparison to conventional method in the performance of determining camera position.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.32 no.2
• /
• pp.55-67
• /
• 2014

The historic cultural landscape of East lake in Kyung river area during Joseon dynasty was very outstanding that it had many attractions of scenic beauty, however, the Han river of today is being recognized as a natural landscape and as a place with low cultural and historical traits. This study applied landscape characteristics of the cultural space of Joseon Dynasty on visual image elements of Lynch to research the landscape characteristics. The research results are as follows. When East lake was applied to visual image elements, it was recognized as a 'superb' 'paths,' and the 'edge' which signifies the boundary showed its 'superb' clarity of the East lake. For the 'node,' a turning point of direction, Dumopo represented the 'superb' awareness. As East lake, Apgujung, and Jecheonjung represented the 'superb' awareness when 'landmark' among visual image elements of Lynch was applied to the cultural space, the awareness level and reputation were proportional to the visual image elements. When pattern, structure, and meaning of the cultural space were clear and had definite identity, the 'landmark' and 'district' elements were 'superb.' It was also identified that when awareness level of space was higher, the awareness of historic cultural landscape was high as well. Therefore, considering visual awareness level of the historic cultural landscape of Han river during restoration to investigate and to conduct case studies is considered to increase the awareness level of historicity and cultural character as well as restoration of the place.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.100.2-100
• /
• 2002

In this paper we propose a new visual servoing method for door opening with mobile manipulator. We use an eye-to-hand system that stereo camera is mounted on mobile platform, and adopt the position-based method. The previous methods for door opening mostly used eye-in-hand system with mono camera and required predefined knowledge such as radius and position about door grip, which was mainly caused by using mono cam era. This is also a severe constraint for pursuing general-purpose algorithm for door opening. For overcoming such drawback, we use stereo camera and suggest a new method that detect the door grip and estimate its pose from stereo depth information without predefined knowledge. Al...

• Journal of Sensor Science and Technology
• /
• v.13 no.2
• /
• pp.144-151
• /
• 2004

In this paper, we propose an active stereo surveillance system with human-like convergence function. The proposed system uses a bottom-up saliency map model with the human-like selective attention visual function to select an interesting region in each camera. and this system compares the landmarks whether the selective region in each camera finds a same region. If the left and right cameras successfully find a same landmarks, the implemented vision system focuses on the landmark. Using the motor encoder information, we can automatically obtain the depth information and resultantly construct a depth map using the depth information. Computer simulation and experimental results show that the proposed convergence method is very effective to implement the active stereo surveillance system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.206-210
• /
• 2011

Vision-based robot localization is challenging due to the vast amount of visual information available, requiring extensive storage and processing time. To deal with these challenges, we propose the use of features extracted from omni-directional panoramic images and present a method for localization of a mobile robot equipped with an omni-directional camera. The core of the proposed scheme may be summarized as follows : First, we utilize an omni-directional camera which can capture instantaneous $360^{\circ}$ panoramic images around a robot. Second, Nodes around the robot are extracted by the correlation coefficients of Circular Horizontal Line between the landmark and the current captured image. Third, the robot position is determined from the locations by the proposed correlation-based landmark image matching. To accelerate computations, we have assigned the node candidates using color information and the correlation values are calculated based on Fast Fourier Transforms. Experiments show that the proposed method is effective in global localization of mobile robots and robust to lighting variations.