Vision-based Recognition Algorithm for Up-To-Date Indoor Digital Map Generations at Damaged Buildings

When firefighters are engaged in search and rescue missions inside a building at a risk of collapse,they have difficulty in field command and rescue because they can only simplymonitor the situation inside the building utilizing old building drawings or robots.To propose an efficient solution for fast search and rescue work of firefighters,this study investigates the generation of up-to-date digital maps for disaster sites by tracking the collapse situation,and identifying the information of obstacles which are risk factors,using an artificial intelligence algorithm based on low-cost robots.Our research separates the floor by using the mask regional convolutional neural network(R-CNN)algorithm,and determines whether the passage is collapsed or not.Then,in the case of a passage that can be searched,the floor pattern of the obstacles that exist on the floor that has not collapsed is analyzed,and obstacles are searched utilizing an image processing algorithm.Here,we can detect various unknown as well as known obstacles.Furthermore,the locations of obstacles can be estimated using the pixel values up to the bounding box of an existing detected obstacle.We conduct experiments using the public datasets collected by Carnegie Mellon university(CMU)and data collected by manipulating a low-cost robot equipped with a smartphone while roaming five buildings in a campus.The collected data have various floor patterns for objectivity and obstacles that are different from one another.Based on these data,the algorithm for detecting unknown obstacles of a verified study and estimating their sizes had an accuracy of 93%,and the algorithm for estimating the distance to obstacles had an error rate of 0.133.Through this process,we tracked collapsed passages and composed up-to-date digital maps for disaster sites that include the information of obstacles that interfere with the search and rescue work.

Mapping-Based 3D Hexahedral Finite Element Mesh Generation Method

Mapping mesh generation is widely applied in pre-processes of Finite Element Method （FEM）. In this study, the basic 3D mapping equations by Lagrange interpolating function are founded. Based these equations, a mapping pattern library, which maps essential configurations e.g. line, circle, rotary body, sphere etc. to hexahedral FEM mesh, has been built. Then available FEM mesh will be generated by clipping and assembling the mapped essential objects. Study case illustrates that the proposed method is simple and efficient to generate valid FEM mesh for complex 3D engineering structure.

Wind Energy Generation and Assessment of Resources in India

The gap between energy demand and its generation is constantly widening. People have started giving more emphasis on renewable sources of energy. This paper presents the estimation of potential for wind energy generation maps based on fixed wind turbine capacity. Although wind energy has developed substantially in recent years, we have only wind speed and wind potential density maps. Our attempt here is to generate wind energy generation potential maps. Major step in achieving this goal is modeling of wind energy conversion system using TRNSYS software. The model consists of three main components namely the weather, the turbines and energy conversion parameters. The weather data are provided from the meteorological database, namely Meteonorm. The simulated output is compared with actual wind generation of wind farms. After comparing our model results with the existing wind energy generation data, we have extended to compute the wind energy generation for all locations in India. For simulation, 4691 locations are identified considering 0.25° × 0.25° interval. The energy generation simulated data are compiled and developed into maps that are useful to all wind energy developers. The data generated and presented in the form of maps are for all the 30 states of India.

Heavy Metal Distribution Map in Soil by Using GIS Techniques

A detailed investigation was conducted to understand the contamination characteristics and distributions of heavy metal pollution in terms of contributions of the heavy metal concentrations as mg/kg ofCd, Cr, Cu, Ni, Zn, Pb, Fe and Mn in the urban soil in Eskisehir city center. The amount of these heavy metals were determined from 15 soil sample points collected within urban area and every sample point included 6 separated samples for chemical analyses. The results indicated that concentration values of all metals except Ni and Cr in soils were below the risky limit pollution values which are recommended by Turkey Ministry of Environment and Forestry in some sample points. Spatial distribution maps were created and recoded, in terms of these heavy metals concentrations as contribution to heavy metal pollution in soil, through Geographical Information Systems techniques. As a result, risky areas were modeled in terms of contamination of heavy metal and it is shown that, every different risky area can be interpreted based on buildings in city center quickly and easily.

An optical modulation format generation scheme based on spectral filtering and frequency-to-time mapping

An optical modulation format generation scheme based on spectral filtering and frequency-to-time mapping is experimentally demonstrated. Many modulation formats with continuously adjustable duty radio and bit rate can be formed by changing the dispersion of dispersion element and the bandwidth of shaped spectrum in this scheme. In the experiment, non-return-to-zero(NRZ) signal with bit rate of 29.41 Gbit/s and 1/2 duty ratio return-to-zero(RZ) signal with bit rate of 13.51 Gbit/s are obtained. The maximum bit rate of modulation format signal is also analyzed.

DepthGAN: GAN-based depth generation from semantic layouts

Existing GAN-based generative methodsare typically used for semantic image synthesis. Wepose the question of whether GAN-based architecturescan generate plausible depth maps and find thatexisting methods have difficulty in generating depthmaps which reasonably represent 3D scene structuredue to the lack of global geometric correlations.Thus, we propose DepthGAN, a novel method ofgenerating a depth map using a semantic layout asinput to aid construction, and manipulation of wellstructured 3D scene point clouds. Specifically, wefirst build a feature generation model with a cascadeof semantically-aware transformer blocks to obtaindepth features with global structural information.For our semantically aware transformer block, wepropose a mixed attention module and a semanticallyaware layer normalization module to better exploitsemantic consistency for depth features generation.Moreover, we present a novel semantically weighteddepth synthesis module, which generates adaptivedepth intervals for the current scene. We generate thefinal depth map by using a weighted combination ofsemantically aware depth weights for different depthranges. In this manner, we obtain a more accuratedepth map. Extensive experiments on indoor andoutdoor datasets demonstrate that DepthGAN achievessuperior results both quantitatively and visually for thedepth generation task.