• Spatial Information Research
• /
• v.18 no.5
• /
• pp.37-45
• /
• 2010

AT(Aerial Triangulation) is the essential procedure for creating orthophoto and transforming coordinates on the photographs into the real world coordinates utilizing GCPs (Ground Control Point) which is obtained by field survey and the external orientation factors from GPS/INS as a reference coordinates. In this procedure, all of the GCPs can be collected from field survey using GPS and Total Station, or obtained from digital maps. Collecting GCPs by field survey is accurate than GCPs from digital maps; however, lots of manpower should be put into the collecting procedure, and time and cost as well. On the other hand, in the case of obtaining GCPs from digital maps, it is very difficult to secure the required accuracy because almost things at each stage in the collecting procedure should rely on the subjective judgement of the performer. In this study, the results from three methods have been compared for the accuracy assessment in order to know if the results of each case is within the allowance error: for the perceivable objects such as road boarder, speed bumps, constructions etc., 1) GCPs selection utilizing the unique LiDAR intensity value reflected from such objects, 2) using LiDAR DSM and 3) GCPs from field survey. And also, AT and error analysis have been carried out w ith GCPs obtained by each case.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.30-38
• /
• 2006

In this paper, we improved to drops recognition rate according to distance using distance and depth information with 3D from stereo face images. A monocular face image has problem to drops recognition rate by uncertainty information such as distance of an object, size, moving, rotation, and depth. Also, if image information was not acquired such as rotation, illumination, and pose change for recognition, it has a very many fault. So, we wish to solve such problem. Proposed method consists of an eyes detection algorithm, analysis a pose of face, md principal component analysis (PCA). We also convert the YCbCr space from the RGB for detect with fast face in a limited region. We create multi-layered relative intensity map in face candidate region and decide whether it is face from facial geometry. It can acquire the depth information of distance, eyes, and mouth in stereo face images. Proposed method detects face according to scale, moving, and rotation by using distance and depth. We train by using PCA the detected left face and estimated direction difference. Simulation results with face recognition rate of 95.83% (100cm) in the front and 98.3% with the pose change were obtained successfully. Therefore, proposed method can be used to obtain high recognition rate with an appropriate scaling and pose change according to the distance.

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.829-837
• /
• 2014

The KOMPSAT-3 can acquire panchromatic stereo image with 0.7 m spatial resolution, and provides Rational Polynomial Coefficient (RPC). In order to determine ground coordinate using the provides RPC, which include interior-exterior orientation errors, its adjustment is needed by using the Ground Control Point (GCP). Several thousands of national Unified Control Points (UCPs) are established and overall distributed in the country by the Korean National Geographic Information Institute (NGII). UCPs therefore can be easily searched and downloaded by the national-control-point-record-issues system. This paper introduced the point-extraction method and the distance-bearing method to detect of UCPs. As results, the distance-bearing method was better detected through the experiment. RPC adjustment using this method was compared with that by only one UCP and GCPs using GPS. The proposed method was more accurate than the other method in the horizontal. As demonstrated in this paper, the proposed UCPs detection method could be replaced GPS surveying for RPC adjustment.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.212-227
• /
• 2008

Since 3D face can be rotated freely in 3D space and illumination effects can be modeled properly, 3D face modeling Is more precise and realistic in face pose, illumination, and expression than 2D face modeling. Thus, 3D modeling is necessitated much in face recognition, game, avatar, and etc. In this paper, we propose a 3D face modeling method based on 3D morphable shape modeling. The proposed 3D modeling method first constructs a 3D morphable shape model out of 3D face scan data obtained using a 3D scanner Next, the proposed method extracts and matches feature points of the face from 2D image sequence containing a face to be modeled, and then estimates 3D vertex coordinates of the feature points using a factorization based SfM technique. Then, the proposed method obtains a 3D shape model of the face to be modeled by fitting the 3D vertices to the constructed 3D morphable shape model. Also, the proposed method makes a cylindrical texture map using 2D face image sequence. Finally, the proposed method builds a 3D face model by rendering the 3D face shape model with the cylindrical texture map. Through building processes of 3D face model by the proposed method, it is shown that the proposed method is relatively easy, fast and precise than the previous 3D face model methods.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.349-353
• /
• 2003

최근 관심이 증대되고 있는 국토모니터링과 관련하여 기존의 SPOT, IRS, KOMPSAT, LANDSAT 등의 중ㆍ저해상도 위성영상과 IKONOS 등의 고해상도 위성영상을 이용하여 국토의 변화를 탐지하고자 하는 시도가 활발히 진행되고 있다. 이 때 영상의 기하보정은 필수적인 과정이며 영상의 기하보정시 기준점을 취득하는 과정에 많은 시간과 작업비용이 소요된다. 현재 기준점 취득은 수치지도 등을 통해 기존의 지상기준점을 이용하는 방법과 GPS를 이용한 현지 측량방법이 활용되고 있는데 동일지역에 대해 매번 사업 때마다 수행되고 있는 실정이다. 따라서 이러한 과정을 보다 효율적으로 수행하기 위한 하나의 방안으로 본 연구에서는 image chip을 이용하여 GCP를 취득하고 이를 데이터베이스로 구축하여 기존의 작업을 자동화, 체계화하고자 하였다. 이를 통하여 중복측량 방지와 데이터의 균질성을 기할 수 있었다. Image Chip의 영상 정합을 위해서는 상관계수법과 최소제곱정합법을 이용하여 부영상소 단위까지 정합결과를 얻을 수 있었으며 위성의 header 정보로부터의 영상의 표정각과 입사각에 대한 정보를 이용하여 축척과 회전요소를 고려함으로써 영상 정합시 보다 정확한 기준점 정보를 취득할 수 있었다. 또한, 이종 센서간 영상정합 가능성에 대해서 연구한 결과 KOMPSAT과 SPOT간에는 신뢰할 만한 수준의 정합 결과를 얻을 수 있었으나 고해상도 영상의 경우에는 항공사진과 IKONOS의 영상 정합시 센서의 방사학적 특성의 차이로 신뢰할 안한 결과를 얻을 수 없었다. 영상 정합시 정확도에 영향을 미치는 인자들에 관한 실험 결과 센서의 파장, 계절, Chip 영상의 크기 등이 큰 영향을 미쳤으며 영상정합을 위해 영상 GCP를 데이터베이스에서 검색할 때 이에 대한 고려가 우선적으로 이루어져야 할 것으로 사료된다.n of hub-and-spoke system, integration of logistics bases, introduction of (automatic) parking building, diversification of transportation mode, and etc. At the same time, we constructed three practically executable scenarios based on those ideas. The first is "Center Hub" scenario, the second is "Metropolitan Hub" scenario. The third and last scenario is "Regional Consolidation of Warehouses (distribution centers)".f worldly desire' and 'cordiality' that one could be deserved his diligency becoming a part of the harmonious idealistic living place. Fourthly, on the character of story teller. Originally he is a incomer of "Gang-Ho" from real world. so that reason, he is showing dualism not to deny the loyalty oath to his king, while he intends to satisfy with the life in "Gang- Ho" separating himself from real world. As a gentry, at that time, the loyalty oath is inevitable one and that is found from wr

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.4
• /
• pp.77-84
• /
• 2012

Face classification has wide applications in intelligent video surveillance, content retrieval, robot vision, and human-machine interface. Pose and expression changes, and arbitrary illumination are typical problems for face recognition. When the face is captured at a distance, the image quality is often degraded by blurring and noise corruption. This paper investigates the efficacy of multi-classifier decision level fusion for face classification based on the photon-counting linear discriminant analysis with two different cost functions: Euclidean distance and negative normalized correlation. Decision level fusion comprises three stages: cost normalization, cost validation, and fusion rules. First, the costs are normalized into the uniform range and then, candidate costs are selected during validation. Three fusion rules are employed: minimum, average, and majority-voting rules. In the experiments, unfocusing and motion blurs are rendered to simulate the effects of the long distance environments. It will be shown that the decision-level fusion scheme provides better results than the single classifier.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.363-373
• /
• 2020

During last decades numerous studies generating orthoimage have been carried out. Traditional methods require exterior orientation parameters of aerial images and precise 3D object modeling data and DTM (Digital Terrain Model) to detect and recover occlusion areas. Furthermore, it is challenging task to automate the complicated process. In this paper, we proposed a new concept of true orthoimage generation using DL (Deep Learning). DL is rapidly used in wide range of fields. In particular, GAN (Generative Adversarial Network) is one of the DL models for various tasks in imaging processing and computer vision. The generator tries to produce results similar to the real images, while discriminator judges fake and real images until the results are satisfied. Such mutually adversarial mechanism improves quality of the results. Experiments were performed using GAN-based Pix2Pix model by utilizing IR (Infrared) orthoimages, intensity from LiDAR data provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) through the ISPRS (International Society for Photogrammetry and Remote Sensing). Two approaches were implemented: (1) One-step training with intensity data and high resolution orthoimages, (2) Recursive training with intensity data and color-coded low resolution intensity images for progressive enhancement of the results. Two methods provided similar quality based on FID (Fréchet Inception Distance) measures. However, if quality of the input data is close to the target image, better results could be obtained by increasing epoch. This paper is an early experimental study for feasibility of DL-based true orthoimage generation and further improvement would be necessary.