The University of Tokyo · 사회과학
요시키 오가와 교수의 연구실은 도시 환경의 주관적 인식을 고해상도 스트리트 뷰 이미지를 기반으로 정량적으로 평가하는 딥러닝 기반 모델링 기술을 핵심으로 합니다. 특히 도시 스케이프의 미관, 안전성, 쾌적함 등 다양한 주관적 요소를 동시에 측정하는 다중 레이블 분류 모델 개발에 주력하고 있으며, 이는 재난 위험 평가 및 스마트 시티 기술 발전에 기여합니다. 또한, 고해상도 도시 영상과 지리정보시스템(GIS)을 융합한 건물 연도 및 구조물 정보 추정 기술도 개발하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Developing a model to evaluate urban streetscapes based on subjective perceptions is important for quantitative understanding. However, previous studies have only considered limited types of subjective perceptions, neglecting the relationships between them. Further, accurately measuring subjective perception with low computational costs for large-scale urban regions at high spatial resolutions has been difficult. We present a deep-learning-based multilabel classification model that can measure 2
Abstract The Raman and infrared spectra of 2,5-dioxahexane CH3OCH2CH2OCH3, 2,5-dithiahexane CH3SCH2CH2SCH3 and 2-oxa-5-thiahexane CH3OCH2CH2SCH3 were measured for the gaseous, liquid, glassy and crystalline states and were correlated with the normal-vibration calculations. The rotational isomerism was studied and the following conclusions were obtained. (1) The molecular form existing in the crystalline state is a non-extended form, in contrast with the cases of the unbranched ethers or sulfides
Abstract The Raman and infrared spectra of 1-chloro-, 1-bromo-, and 1-iodopropanes, CH3CH2CH2X (X=Cl, Br, and I), and 1-chloro-, 1-bromo-, and 1-iodobutanes, CH3CH2CH2CH2X (X=Cl, Br, and I), were measured for the gaseous, liquid, glassy, and crystalline states. The normal vibration frequencies were calculated, a consistent set of force constants explaining the frequencies of basic halogenoalkanes being assumed. The rotational isomerism was studied on the basis of the spectral observations and th
The built year and structure of individual buildings are crucial factors for estimating and assessing potential earthquake and tsunami damage. Recent advances in sensing and analysis technologies allow the acquisition of high-resolution street view images (SVIs) that present new possibilities for research and development. In this study, we developed a model to estimate the built year and structure of a building using omnidirectional SVIs captured using an onboard camera. We used geographic infor
Global warming is recognized as one of the most important issues in international politics, although specialists are still uncertain about the role which various socio-economic factors play in global warming under a variety of conditions. Among the factors examined in this paper, the burning of fossil fuels bears the greatest responsibility for global C02 emissions. Given the growth in emissions in the LDCs, global action to regulate emissions cannot be effective without their full participation
Abstract The Raman and infrared spectra of n-propyl acetate were observed at low temperatures and the results were analysed on the basis of normal-coordinate calculations. In two crystal modifications the molecules assume different conformations, namely, the trans–gauche form with respect to the two axes CH3(CO)O–CH2–CH2CH3 in Crystal I and the trans–trans form in Crystal II.
Using various types of big data on the Nankai Trough earthquake and tsunami that struck Kochi, we describe a method of simulating how economic damage to inter-enterprise transactions propagates through the supply chain and how subsequent recovery occurs. First, we enter the human losses and material damage caused by the earthquake and tsunami to estimate the material damage and labor capital loss of each enterprise based on the position information of employees. Next, we simulate the damage repe
This paper proposes a new method to join building footprint GIS data with the relevant buildings in a street-view image, taken by a vehicle-mounted camera. This is achieved by segmenting buildings in the street-view images and identifying the relevant building coordinates in the image. The building coordinates on the image are then estimated from the building vertices in the building footprint GIS data and vehicle trajectory history. Finally, the objective building is identified and relevant bui
Abstract Two crystal modifications of l-bromopentane gave entirely different Raman spectra, which undoubtedly indicated simultaneous occurrence of a crystal transformation and a conformational change of molecules in the crystal. The molecular conformation is trans-trans-trans (TTT) in one crystal modification (Crystal I) and trans-trans-gauche (TTG) in the other (Crystal II). The polymorphism of l-iodopentane, which presents a contrast to the case of 1-bromopentane, is also described.
Abstract. Assessments of the human damage caused by the tsunami are required in order to consider disaster prevention at such a regional level. Hence, there is an increasing need for the assessments of human damage caused by earthquakes. However, damage assessments in japan currently usually rely on static population distribution data, such as statistical night time population data obtained from national census surveys. Therefore, human damage estimation that take into consideration time frames
For the establishment of precise disaster prevention measures in response to the Nankai megathrust earthquakes predicted to occur in the future, it is necessary to conduct numerous earthquake simulations and evaluate the vulnerability of the urban environment quantitatively. This vulnerability is evaluated on the basis of factors such as the extent of damage from earthquakes, as well as the attributes of residents, urban infrastructure, and systems in the environment. In this study, we propose a
Currently, the Ministry of Land, Infrastructure, Transport, and Tourism (Japan) is in the process of developing an open 3D city model known as PLATEAU. Abundant measurement data related to buildings, including maps produced by private companies and mobile mapping system point clouds, have been collected to enhance the value of the 3D city model. To achieve this, it is necessary to identify the buildings for which measurement data is available. In this study, we propose and evaluate an efficient
将来予測されている南海トラフ地震が発生した場合における危機管理対応を的確に実施するために，本研究は高知市周辺を対象として，近年の観測技術の向上に伴い蓄積されている観測ビッグデータを用いて被害予測に適用可能なミクロデータを整備することで高精細な被害推定を目指す．そのためにGPS付帯の携帯電話のプローブデータ，住宅地図，電話帳などのジオビッグデータを用いて時空間内挿することで，季節ごとの数日間ずつを対象に15分単位の詳細な人の流動が把握できる人流データを開発した．また，整備した人流データを用いて津波・倒壊・火災による人的被害を統合的に推定する環境を構築した．さらに，多様な被害推定結果を分析することで地域ごとの被害尤度分布を明らかにし，地域ごとに起こり得る最大被害・最尤被害を明らかにした．その結果，地域により被害が大きくなりやすい地域とそうでない地域の分布が明らかになった．
