• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.175-185
• /
• 2020

Three-dimensional registration is a process of matching data with or without a coordinate system to a reference coordinate system, which is used in various fields such as the absolute orientation of photogrammetry and data combining for producing precise road maps. Three-dimensional registration is divided into a method using points and a method using linear features. In the case of using points, it is difficult to find the same conjugate point when having different spatial resolutions. On the other hand, the use of linear feature has the advantage that the three-dimensional registration is possible by using not only the case where the spatial resolution is different but also the conjugate linear feature that is not the same starting point and ending point in point cloud type data. In this study, we proposed a method to determine the scale and the three-dimensional translation after determining the three-dimensional rotation angle between two data using quaternion to perform three-dimensional registration using linear features. For the verification of the proposed method, three-dimensional registration was performed using the linear features constructed an indoor and the linear features acquired through the terrestrial mobile mapping system in an outdoor environment. The experimental results showed that the mean square root error was 0.001054m and 0.000936m, respectively, when the scale was fixed and if not fixed, using indoor data. The results of the three-dimensional transformation in the 500m section using outdoor data showed that the mean square root error was 0.09412m when the six linear features were used, and the accuracy for producing precision maps was satisfied. In addition, in the experiment where the number of linear features was changed, it was found that nine linear features were sufficient for high-precision 3D transformation through almost no change in the root mean square error even when nine linear features or more linear features were used.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.355-361
• /
• 2006

In large scale environments like airport, museum, large warehouse and department store, autonomous mobile robots will play an important role in security and surveillance tasks. Robotic security guards will give the surveyed information of large scale environments and communicate with human operator with that kind of data such as if there is an object or not and a window is open. Both for visualization of information and as human machine interface for remote control, a 3D model can give much more useful information than the typical 2D maps used in many robotic applications today. It is easier to understandable and makes user feel like being in a location of robot so that user could interact with robot more naturally in a remote circumstance and see structures such as windows and doors that cannot be seen in a 2D model. In this paper we present our simple and easy to use method to obtain a 3D textured model. For expression of reality, we need to integrate the 3D models and real scenes. Most of other cases of 3D modeling method consist of two data acquisition devices. One for getting a 3D model and another for obtaining realistic textures. In this case, the former device would be 2D laser range-finder and the latter device would be common camera. Our algorithm consists of building a measurement-based 2D metric map which is acquired by laser range-finder, texture acquisition/stitching and texture-mapping to corresponding 3D model. The algorithm is implemented with laser sensor for obtaining 2D/3D metric map and two cameras for gathering texture. Our geometric 3D model consists of planes that model the floor and walls. The geometry of the planes is extracted from the 2D metric map data. Textures for the floor and walls are generated from the images captured by two 1394 cameras which have wide Field of View angle. Image stitching and image cutting process is used to generate textured images for corresponding with a 3D model. The algorithm is applied to 2 cases which are corridor and space that has the four wall like room of building. The generated 3D map model of indoor environment is shown with VRML format and can be viewed in a web browser with a VRML plug-in. The proposed algorithm can be applied to 3D model-based remote surveillance system through WWW.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.1
• /
• pp.1-9
• /
• 2007

3D data are in great demand for pedestrian navigation recently. For pedestrian navigation, we needs to reconstruct 3D model in detail from people's eye. In order to present spatial features in detail for pedestrian navigation, it is indispensable to develop 3D model not only in outdoor environment but also in indoor environment such as underground shopping complex. However, it is very difficult to acquire 3D data efficiently by mobile mapping without GPS. In this research, 3D shape was acquired by Laser scanner, and texture by CCD(Charge Coupled Device) sensor. Continuous changes position and attitude of sensors were measured by IMU(Inertial Measurement Unit). Moreover, IMU was corrected by relative orientation of CCD images without GPS(Global Positioning System). In conclusion, Reliable, quick, and handy method for acquiring 3D data for indoor environment is proposed by a combination of a digital camera and a laser scanner with IMU.

• Korean Journal of Remote Sensing
• /
• v.19 no.6
• /
• pp.431-445
• /
• 2003

In this paper, we experimentally investigated the precision of 3D positioning using 4S-Van images in photograrmmetric perspective. The 3D calibration target was built over building facade outside and was captured separately by two CCD cameras installed in 4S-Van. After then, we determined the interior orientation parameter for each CCD camera through self-calibration technique. With the interior orientation parameter computed, the bundle adjustment was performed to obtain the exterior orientation parameters simultaneously for two CCD cameras using calibration target image and object coordinates. The reverse lens distortion coefficients were computed and acquired by least squares method so as to introduce lens distortion into epipolar line. It was shown that the reverse lens distortion coefficients could transform image coordinates into lens distorted image coordinates within about 0.5 pixel. The proposed semi-automatic matching scheme incorporated with lens distorted epipolar line was implemented with scene images captured by 4S-Van in moving. The experimental results showed that the precision of 3D positioning from 4S-Van images in photograrmmetric perspective is within 2cm in the range of 20m from the camera.

• Journal of KIBIM
• /
• v.10 no.4
• /
• pp.32-39
• /
• 2020

In recent years, the construction industry is getting bigger and more complex, so it is becoming difficult to acquire point cloud data for construction equipments and workers. Point cloud data is measured using a drone and MMS(Mobile Mapping System), and the collected point cloud data is used to create a 3D digital map. In particular, the construction site is located at outdoors and there are many irregular terrains, making it difficult to collect point cloud data. For these reasons, adopting a noise reduction algorithm suitable for the characteristics of the construction industry can affect the improvement of the analysis accuracy of digital maps. This is related to various environments and variables of the construction site. Therefore, this study reviewed and analyzed the existing research and techniques on the noise reduction algorithm. And based on the results of literature review, performance evaluation of major noise reduction algorithms was conducted for digital maps of construction sites. As a result of the performance evaluation in this study, the voxel grid algorithm showed relatively less execution time than the statistical outlier removal algorithm. In addition, analysis results in slope, space, and earth walls of the construction site digital map showed that the voxel grid algorithm was relatively superior to the statistical outlier removal algorithm and that the noise removal performance of voxel grid algorithm was superior and the object preservation ability was also superior. In the future, based on the results reviewed through the performance evaluation of the noise reduction algorithm of this study, we will develop a noise reduction algorithm for 3D point cloud data that reflects the characteristics of the construction site.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.12-19
• /
• 2020

The clustered heterogeneous wireless sensor network is comprised of sensor nodes and cluster heads, which are hierarchically organized for different objectives. In the network, we should especially take care of managing node resources to enhance network performance based on memory and battery capacity constraints. For instances, if some interesting events occur frequently in the vicinity of particular sensor nodes, those nodes might receive massive amounts of data. Data congestion can happen due to a memory bottleneck or link disconnection at cluster heads because the remaining memory space is filled with those data. In this paper, we utilize drones as mobile sinks to resolve data congestion and model the network, sensor nodes, and cluster heads. We also design a cost function and a congestion indicator to calculate the degree of congestion. Then we propose a data congestion map index and a data congestion mapping scheme to deploy drones at optimal points. Using control variable, we explore the relationship between the degree of congestion and the number of drones to be deployed, as well as the number of drones that must be below a certain degree of congestion and within communication range. Furthermore, we show that our algorithm outperforms previous work by a minimum of 20% in terms of memory overflow.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1515-1526
• /
• 2022

Image-based 3D reconstruction is to restore the shape and color of real-world objects, and image sensors mounted on mobile platforms are used for positioning and mapping purposes in indoor and outdoor environments. Due to the increase in accidents in underground space, the location accuracy problem of underground spatial information has been raised. Image-based location estimation studies have been conducted with the advantage of being able to determine the 3D location and simultaneously identify internal damage from image data acquired from the inside of pipeline-type underground facilities. In this study, we studied 3D reconstruction based on the images acquired inside the pipe-type underground facility and reference data. An unmanned mobile system equipped with a stereo camera was used to acquire data and image data within a pipe-type underground facility where reference data were placed at the entrance and exit. Using the acquired image and reference data, the pipe-type underground facility is reconstructed to a geo-referenced 3D shape. The accuracy of the 3D reconstruction result was verified by location and length. It was confirmed that the location was determined with an accuracy of 20 to 60 cm and the length was estimated with an accuracy of about 20 cm. Using the image-based 3D reconstruction method, the position and line-shape of the pipe-type underground facility will be effectively updated.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1D
• /
• pp.135-143
• /
• 2009

Integrating the Global Positioning System (GPS) and Inertial Navigation System (INS) sensor technologies using the precise GPS Carrier phase measurements is a methodology that has been widely applied in those application fields requiring accurate and reliable positioning and attitude determination; ranging from 'kinematic geodesy', to mobile mapping and imaging, to precise navigation. However, such integrated system may not fulfil the demanding performance requirements when the baseline length between reference and mobil user GPS receiver is grater than a few tens of kilometers. This is because their positioning/attitude determination is still very dependent on the errors of the GPS observations, so-called "baseline dependent errors". This limitation can be remedied by the integration of GPS and INS sensors, using multiple reference stations. Hence, in order to derive the GPS distance dependent errors, this research proposes measurement processing algorithms for multiple reference stations, such as a reference station ambiguity resolution procedure using linear combination techniques, a error estimation based on Kalman filter and a error interpolation. In addition, all the algorithms are evaluated by processing real observations and results are summarized in this paper.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.508-519
• /
• 2007

Flash memory based storage has been used in various mobile systems and now is to be used in Laptop computers in the name of Solid State Disk. The Flash memory has not only merits in terms of weight, shock resistance, and power consumption but also limitations like erase-before-write property. To overcome these limitations, Flash memory based storage requires special address mapping software called FTL(Flash-memory Translation Layer), which often performs merge operation for block recycling. In order to reduce block recycling cost in NAND Flash memory based storage, we introduce another block recycling scheme which we call migration. As a result, the FTL can select either merge or migration depending on their costs for each block recycling. Experimental results with Postmark benchmark and embedded system workload show that this cost-based selection of migration/merge operation improves the performance of Flash memory based storage. Also, we present a solution of macroscopic optimal migration/merge sequence that minimizes a block recycling cost for each migration/merge combination period. Experimental results show that the performance of Flash memory based storage can be more improved by the macroscopic optimization than the simple cost-based selection.