• Proceedings of the KSRS Conference
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.125-127
• /
• 2004

High-resolution satellite images offer abundance information of the earth surface for remote sensing applications. The information includes geometry, texture and attribute characteristic. The pixel-based image classification can't satisfy high-resolution satellite image's classification precision and produce large data redundancy. Object-oriented information extraction not only depends on spectrum character, but also use geometry and structure information. It can provide an accessible and truly revolutionary approach. Using Beijing Spot 5 high-resolution image and object-oriented classification with the eCognition software, we accomplish the cultures' precise classification. The test areas have five culture types including water, vegetation, road, building and bare lands. We use nearest neighbor classification and appraise the overall classification accuracy. The average of five species reaches 0.90. All of maximum is 1. The standard deviation is less than 0.11. The overall accuracy can reach $95.47\%.$ This method offers a new technology for high-resolution satellite images' available applications in remote sensing culture classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제6권2호
• /
• pp.282-287
• /
• 2002

This paper action tracing by techniques to do image sequence component to watch invader based on Mobile internet use. First, detect frame in animation that film fixed area, and make use of image subtraction between two frame that adjoin, segment fixed backing and target who move. Segmentalized foreground object detected and did so that can presume middle value of gouge that is abstracted to position that is specified and watch invader by analyzing action gouge. Those watch information is stored, and made Mobile client send out SMS Message about situation of watch place to server being stored to sensed serial numbers, date, Image file with recording of time.

• The Journal of Korea Robotics Society
• /
• 제13권1호
• /
• pp.38-44
• /
• 2018

In this paper, we propose Intelligent Driver Assistance System (I-DAS) for driver safety. The proposed system recognizes safety and danger status by analyzing blind spots that the driver cannot see because of a large angle of head movement from the front. Most studies use image pre-processing such as face detection for collecting information about the driver's head movement. This not only increases the computational complexity of the system, but also decreases the accuracy of the recognition because the image processing system dose not use the entire image of the driver's upper body while seated on the driver's seat and when the head moves at a large angle from the front. The proposed system uses a convolutional neural network to replace the face detection system and uses the entire image of the driver's upper body. Therefore, high accuracy can be maintained even when the driver performs head movement at a large angle from the frontal gaze position without image pre-processing. Experimental result shows that the proposed system can accurately recognize the dangerous conditions in the blind zone during operation and performs with 95% accuracy of recognition for five drivers.

• Journal of Fashion Business
• /
• 제15권4호
• /
• pp.43-54
• /
• 2011

Printing process has been a major sector in the textile industries for a long period of time. With the advent of digital textile printing, the complex procedures of printing preparations and after-treatment processes have been streamlined. For the design of the motives of images to be printed, the use of image handling software, e.g. Photoshop(Adobe), has been of prime importance. Even though the software is extremely useful and functionally versatile, there are many laborious steps involved for the specific textile printing process. The use of a CAD-based textile printing function may help the textile printing process in streamlining the complex processing stages. The image qualities of the output designs have been compared objectively with the aid of several image similarity evaluation schemes including the SSIM, and FSIM Index methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제25권7A호
• /
• pp.1044-1049
• /
• 2000

Projection that can be used as a feature for image representation, includes much available informations such as approximated shape and location. But when we retrieve image using it, there are some disadvantage such as requiring much index data and making different length of projected vector for differenr image size. In order to overcome these problems, we propose a method of using block variance for the projected vector. We use block variance of the projection vector to localize the characteristics of image and to reduce the number of index data in database. Proposed algorithm can make use of statistical advantage through database including various size of images and be executed with fast response time in implementation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.227-232
• /
• 1999

We have been making researches on 3-D displays using computer-generated holograms(CGHs). Our CGHs are binary Fresnel holograms that reconstruct point light sources and are recorded by using high resolution laser printers (image setters). We use an image setter with a resolution of 5080 dots per inch. It is possible to reconstruct CGHs with light-emitting points. As the resolution of the image setter is not so high, it is better to use a spherical wave as a reference beam. We considered the recordable points objects are restricted by the low resolution, and proposed the multiplex type hologram to reduce the number of point objects recorded in the unit area of the CGH. We proposed a method to make computer-generated color hologram which could reconstruct color point light sources, by combining RGB color filters with the stripe CGHs corresponding to each color. We considered two kinds of gradation method on our binary CGHs. In this paper, we propose a multiple reconstruction method for improving the narrow viewing field.

• The Transactions of the Korea Information Processing Society
• /
• 제5권8호
• /
• pp.2027-2040
• /
• 1998

In this paper, we present efficient reconfigurable mesh algorithms for transforming between a binary image and its corresponding boundary code. These algorithms use $n\timesn\timesn$ processors when the size of the binary image is $n\timesn$. Recent published results show that these transformations can be done in O(1) time using $O(n^4)$ processors. The number of processors used by these algorithms is very large compared to the number of pixels in the image. Here, we present fast transformation algorithms which use $n^3 processors only. the transformation from a houndary code to a binary image takes O(1) time, and the converse transformation takes O(log n) time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제12권8호
• /
• pp.1481-1487
• /
• 2008

In this paper, we propose a novel interactive 3D floating image pointing device for the use of 3D environment. The proposed system consists of the 3D floating image generation system by use of a floating lens array and the a user interface based on real-time finger detection. In the proposed system, a user selects single image among the floating images so that the interaction function are performed effectively by pressing the button event through the finger recognition using two cameras. To show the usefulness of the proposed system, we carry out the experiment and the preliminary results are presented.

• Journal of Broadcast Engineering
• /
• 제25권7호
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.

• Journal of Korea Multimedia Society
• /
• 제25권9호
• /
• pp.1273-1283
• /
• 2022

This paper presents a locally adaptive HDR algorithm using the integral image and MSRCR for LDR images with inadequate exposure. There are two categories in controlling the dynamic range, which are global and local tone mappings. Since the global ones are relatively simple but have some limitations at considering regional characteristics, the local ones are often utilized and MSRCR is a representative method. MSRCR gives moderate results, but it requires lots of computations for multi-scale surround Gaussian functions and produces the Halo effect around the edges. Therefore, in order to resolve these main problems, the proposed algorithm remarkably reduces the computation of the surrounds due to the use of the integral image. And a set of variable-sized windows is adopted to decrease the Halo effect, according to the type of pixel's region. In addition, an offset controlling function is presented, which is mainly affected to the subjective image quality and based on the global input and the desired output means. As the results, the proposed algorithm no more use Gaussian functions and can reduce the computation amount and the Halo effect.