• Korean Journal of Remote Sensing
• /
• v.23 no.3
• /
• pp.221-227
• /
• 2007

We present an analysis of urban development and growth with reconnaissance satellite photographs of Columbus metropolitan area acquired by the Corona program in 1965. A two-dimensional polynomial linear transformation was used to rectify the photos against United State Geological Survey (USGS) Large-scale Digital Line Graph (DLG) data georeferenced to Universal Transverse Mercator (UTM) coordinates. The boundaries of the Columbus metropolitan area were extracted from the rectified Corona image mosaic using a Bayesian approach to image segmentation. The inferred 1965 urban boundaries were compared with 1976 USGS Land Use and Land Cover (LULC) data and boundaries derived from 1988 and 1994 Landsat TM images. The urban area in and around Columbus approximately doubled from 1965 to 1994 (${\sim}110%$) along with population growth from 1960 to 1998 (${\sim}50%$). Most of the urban expansion results from development of residential units.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.289-296
• /
• 2022

In this paper, we developed a deep learning-based recyclable object detection model. The model is developed based on YOLOv5 that is a one-stage detector. The deep learning model detects and classifies the recyclable object into 7 categories: paper, carton, can, glass, pet, plastic, and vinyl. We propose two methods for recyclable object detection models to solve problems during training. Bounding Box CutMix solved the no-objects training images problem of Mosaic, a data augmentation used in YOLOv5. Standardized Distance-based IoU replaced DIoU using a normalization factor that is not affected by the center point distance of the bounding boxes. The recyclable object detection model showed a final mAP performance of 0.91978 with Bounding Box CutMix and 0.91149 with Standardized Distance-based IoU.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.63-72
• /
• 2005

This paper proposes a new method to construct a panorama image from video sequences captured by the video camcoder revolving on the center axis of the tripod. The proposed method is consisted of two algorithms; frame selection and image mosaics. In order to select frames to construct the panorama image, we employ the interpolation search using the information in overlapped areas. This method can search suitable frames quickly. We construct an image mosaic using the projective transform induced from four pairs of quasi-features. The conventional methods select feature points by using only texture information, but the presented method in this paper uses the position of each feature point as well. We make an experiment on the proposed method with real video sequences. The results show that the proposed method is better than the conventional one in terms of image quality.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.2
• /
• pp.39-48
• /
• 2015

Lately, Unmanned Aerial Vehicles(UAV), Unmanned Aerial Systems(UAS) or also often known as drones, as a data acquisition platform and as a measurement instrument are becoming attractive for many photogrammetric surveying applications, especially generation of the high density point clouds(HDPC). This paper presents the performance evaluation of a low-cost rotary wing quadrocopter UAS for generation of the HDPC in a test bed environment. Its performance was assessed by comparing the coordinates of UAS based HDPC to the results of Network RTK GNSS surveying with 62 ground check points. The results indicate that the position RMSE of the check points are ${\sigma}_H={\pm}0.102m$ in Horizonatal plane, and ${\sigma}_V={\pm}0.209m$ in vertical, and the maxium deviation of Elevation was 0.570m within block area of ortho-photo mosaic. Therefore the required level of accuracy at NGII for production of ortho-images mosaic at a scale of 1:1000 was reached, UAS based imagery was found to make use of it to update scale 1:1000 map. And also, since this results are less than or equal to the required level in working rule agreement for airborne laser scanning surveying of NGII for Digital Elevation Model generation of grids $1m{\times}1m$ and 1:1000 scale, could be applied with production of topographic map and ortho-image mosaic at a scale of 1:1000~1:2500 over small-scale areas.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.51-59
• /
• 1999

In this paper we propose the technique for tracking players and a ball and for obtaining players' ground traces using image mosaic in general soccer sequences. Here, general soccer sequences mean the case that there is no extreme zoom-in or zoom-out of TV camera. Obtaining player's ground traces requires that the following three main problems be solved. There main problems: (1) ground field extraction (2) player and ball tracking and team indentification (3) player positioning. The region of ground field is extracted on the basis of color information. Players are tracked by template matching and Kalman filtering. Occlusion reasoning between overlapped players in done by color histogram back-projection. To find the location of a player, a ground model is constructed and transformation between the input images and the field model is computed using four or more feature points. But, when feature points extracted are insufficient, image-based mosaic technique is applied. By this image-to-model transformation, the traces of players on the ground model can be determined. We tested our method on real TV soccer sequence and the experimental results are given.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.265-272
• /
• 2005

In this paper, we propose a technique which is speedily searching for correspondent points of two images using Voronoi-Distance, as an image registration method for feature based image mosaics. It extracts feature points in two images by the SUSAN corner detector, and then create not only the Voronoi Surface which has distance information among the feature points in the base image using a priority based Voronoi distance algorithm but also select the model area which has the maximum variance value of coordinates of the feature points in the model image. We propose a method for searching for the correspondent points in the Voronoi surface of the base image overlapped with the model area by use of the partitive search algorithm using queues. The feature of the method is that we can rapidly search for the correspondent points between adjacent images using the new Voronoi distance algorithm which has $O(width{\times}height{\times}logN)$ time complexity and the the partitive search algerian using queues which reduces the search range by a fourth at a time.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.4C
• /
• pp.417-425
• /
• 2006

This Paper Proposes a method of building a panoramic video from several videos captured from adjacent cameras. The panoramic image which constructed from adjacent and overlapped images is used for photogrammetry, satellite photo or many computer graphic applications. The perspective transformation, which is estimated from the appropriate corresponding pairs of images, can be used to construct the panoramic image without unwarranted distortion and its quality is decided by how to find the features needed for transform estimation. We used the corner points for the corresponding features, and morphological structures were utilized for fast and robust corner detection. We used the criterion of the corner strength, which guarantees the robust detection of the corner in most situations. For the transformation, 8 parameters were estimated from perspective equations which use matched points of adjacent images, and bilinear color blending was used to construct a soapless panoramic video. The experiments showed that the proposed method yields fast results with good quality under various conditions.

• Aerospace Engineering and Technology
• /
• v.13 no.1
• /
• pp.174-183
• /
• 2014

The Value-Added Processing System(VAPS) was developed for post-processing the KOMPSAT imagery. Recently software version and hardware specification of VAPS were changed for improving the VAPS performance. The purpose of this study is to describe about the improvement of existing VAPS(ver.1.0) and systematically evaluate the performance of the improved VAPS(ver.2.0). To this end, test-bed areas in South and North Korea were selected and then image processing tests were conducted using KOMPSAT-2 and KOMPSAT-3 imagery in both areas. In conclusion, VAPS(ver.2.0) had an ability to generate the high level products like ortho images and mosaic images. Image processing time using the Graphic Processing Unit(GPU) on ver.2.0 was enhanced up to 10 times than ver.1.0.

• Journal of the Korea Computer Graphics Society
• /
• v.17 no.1
• /
• pp.25-31
• /
• 2011

Photomosaic is a method of representation an input image in forms of mosaics by a set of small tile images. Generally, equal rectangular tiles are used in photo mosaics. Therefore, there are limitations to expression of mosaic according to characteristic of images. In this paper, photo mosaics using quad-tree structure is proposed to create tiles in varies sizes. Initially, color variance per each level of an input image is computed using the mipmap of graphic hardware. Depending on the value of Valiance, the input image is divided into tiles in varies sizes. Each tile finds the most similar reference image and replaces with it. As a result, the method provides another pictorial effectiveness by dividing the input image into tiles in varies sizes depending on color held by the input image. In addition, whole processing is done on the graphic hardware and thereby we achieve faster performance.

• Journal of Oral Medicine and Pain
• /
• v.21 no.1
• /
• pp.37-54
• /
• 1996

In this thesis, a new superimposition scheme using a computer vision system was proposed with 7 pairs of skull and ante-mortem photographs, which were already identified through other tests and DNA fingerprints at the Korea National Institute of Scientific Investigation. At this computer vision system, an unidentified skull was caught by video-camcoder with the MPEG and a ante-mortem photograph was scanned by scanner. These two images were processed and superimposed using pixel processing. Recognition of the individual identification by anatomical references was performed on the two superimposed images. These results were as followings. 1. For the enhancement of skull and ante-mortem photographs, various image processing schemes, such as SMOOTH, SHARPEN, EMBOSS, MOSAIC, ENGRAVE, INVERT, NEON and COLOR TO MONO, were applied using 3*5 window processing. As an image processing result of these methods, the optimal techniques were NEON, INVERT and ENGRAVE for the edge detection of skull and ante-mortem photograph. 2. Using various superimposition image processing techniques (SRCOR, SRCAND, SRCINVERT, SRCERASE, DSTINVERT, MERGEPAINT) were compared for the enhancement of image recognition. 3. By means of the video camera, the skull image was inputed directly to a computer system : superimposing it on the ante-mortem photograph made the identification more precise and time-saving. As mentioned above, this image processing techniques for the superimposition of skull and ante-mortem photographs simply used the previous approach, In other wrods, taking skull photographs and developing it to the same size as the ante-mortem photographs. This system using various image processing techniques on computer screen, a more precise and time-saving superimposition technique could be able to be applied in the area of individual identification in forensic practice.