• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.31-38
• /
• 2017

In this paper, we propose a system which estimates Manhattan coordinate systems for urban scene images using a convolutional neural network (CNN). Estimating the Manhattan coordinate system from an image under the Manhattan world assumption is the basis for solving computer graphics and vision problems such as image adjustment and 3D scene reconstruction. We construct a CNN that estimates Manhattan coordinate systems based on GoogLeNet [1]. To train the CNN, we collect about 155,000 images under the Manhattan world assumption by using the Google Street View APIs and calculate Manhattan coordinate systems using existing calibration methods to generate dataset. In contrast to PoseNet [2] that trains per-scene CNNs, our method learns from images under the Manhattan world assumption and thus estimates Manhattan coordinate systems for new images that have not been learned. Experimental results show that our method estimates Manhattan coordinate systems with the median error of $3.157^{\circ}$ for the Google Street View images of non-trained scenes, as test set. In addition, compared to an existing calibration method [3], the proposed method shows lower intermediate errors for the test set.

• Journal of the Korean Institute of Educational Facilities
• /
• v.20 no.2
• /
• pp.3-14
• /
• 2013

The purpose of this study is to analyze patterns of public school building layout types, open space and relationship with communities in the Manhattan grid plan. The study illustrates how building layout patterns of school facilities are influenced by societal demands in the urban grid environment. During the nineteenth century, the Island of Manhattan was transformed into a physical representation of the Cartesian coordinate system via the development of the grid street plan. In order to take advantage of streets as urban space, it is quite important to understand characteristics of communities and open space relationships between buildings and streets. Moreover, the strategic planning of schools' outdoor space vitalizes public streets as a critical community anchor. This research reviews 118 Manhattan public schools and categorizes them by (1) building layout type, (2) site type, (3) circulation and public open space, which are the biggest factors that determine the layout patterns of the public schools in Manhattan. As a result of analysis, the layout patterns are classified into seven types : "ㅡ", "L", "ㄷ", "ㅁ", "H", "T" and "other" type. Of these, "ㅡ" type and "L" type occur most frequently, because these configurations most flexibly fit into the limited grid-locked blocks, the various types of site & topography, and adapt most dynamically to the open spaces created by using avenues and streets. The ultimate objective of this study is to provide a case study for future efforts to plan open spaces for campuses that effectively utilize the streets in proximity.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.8-19
• /
• 2004

In this paper, we propose an efficient method for locating destination address block on both of machine-Printed and handwritten Korean mail piece images. The proposed method extracts connected components from the binary mail piece image, generates text lines by merging them, and then groups the text fines into nine clusters. The destination address block is determined by selecting some clusters. Considering the geometric characteristics of address information on Korean mail piece, we split a mail piece image into nine areas with an equal size. The nine clusters are initialized with the center coordinate of each area. A modified Manhattan distance function is used to compute the distance between text lines and clusters. We modified the distance function on which the aspect ratio of mail piece could be reflected. The experiment done with live Korean mail piece images has demonstrated the superiority of the Proposed method. The success rate for 1, 988 testing images was about 93.56%.