• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.305-307
• /
• 2021

군사 분야에서 사용하는 기존 영상융합체계는 영상에서 미확인 개체를 식별하는 Activity-Based Intelligence(ABI) 기술과 객체들에 대한 지식정보를 관리하는 Structured Observation Management(SOM) 기술을 연동하여 다양한 관점에서 분석하고 있다. 그러나 군사적인 목적을 달성하기 위해서는 미래 정보가 중요하기 때문에 주변 맥락 정보를 통합하여 분석해야 할 필요성이 있으며 이를 위해 주변맥락 정보를 분석하는 딥러닝 모델 적용이 필요하다. 본 논문에서는 딥러닝 모델 기반 영상 판독 시스템 구축을 하기 위한 전처리 과정을 설계하였다. pyhwp 라이브러리를 이용하여 영상 정보 판독 데이터를 파싱 및 전처리를 진행하여 데이터 구축을 진행하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.231-233
• /
• 2010

깊이데이터는 CG 또는 실사 영상에서 획득되는데 입체 영상 분야에서 활용도가 높다. 예를 들어 2D영상의 3D화질 개선, 입체영상의 입체감 개선 등의 활용이 되고 있다. 본 논문에서는 이러한 추세에 맞추어 홀로그램을 생성하는 입력 데이터의 전처리과정으로 통하여 CGH 홀로그램을 개선하는 영상처리 기술을 제안한다. 입력 데이터의 전처리를 통해 생성된 홀로그램 영상의 화질 개선을 제안하고, 실험을 통해 제안 방법의 우수성을 보여준다.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.62-70
• /
• 2013

DIBR(Depth Image Based Rendering) is a kind of view synthesis algorithm to generate images at free view points from the reference color image and its depth map. One of the main challenges of DIBR is the occurrence of holes that correspond to uncovered backgrounds at the synthesized view. In order to cover holes efficiently, two main approaches have been actively investigated. One is to develop preprocessing algorithms for depth maps or parallax maps to reduce the size of possible holes, and the other is to develop hole filling methods to fill the generated holes using adjacent pixels in non-hole areas. Most conventional preprocessing algorithms for reducing the size of holes are based on the smoothing process of depth map. Filtering of depth map, however, attenuates the resolution of depth map and generates geometric distortions. In this paper, we proposes a novel preprocessing algorithm for parallax map to improve the performance of hole-filling by avoiding the drawbacks of conventional methods.

• Journal of Korea Multimedia Society
• /
• v.14 no.6
• /
• pp.719-729
• /
• 2011

This paper presents a research on the fast and accurate method of line detection in the image of a wireless mobile robot (WMR). For the improvement of the processing time to detect lines, the characteristics of the transmitted image from the WMR was analyzed, and the efficient preprocessing method among the existing preprocessing methods was selected. And for the improvement of the accuracy to detect lines, the selection method of local maximum value at the Hough array (HA) which has the result of Hough transform was improved by designing a mask and applying it to HA. The experiment was performed with acquired images from the WMR, and the proposed method outperformed the existing methods in terms of processing time and line detection.

• Journal of Broadcast Engineering
• /
• v.25 no.3
• /
• pp.374-385
• /
• 2020

In this paper, we propose a preprocessing technique to solve the problems of action recognition with Equirectangular Projection (ERP) video. The preprocessing technique proposed in this paper assumes the person object as the subject of action, that is, the Object of Interest (OOI), and the surrounding area of the OOI as the ROI. The preprocessing technique consists of three modules. I) Recognize person object in the image with object recognition model. II) Create a saliency map from the input image. III) Select subject of action using recognized person object and saliency map. The subject boundary box of the selected action is input to the action recognition model in order to improve the action recognition performance. When comparing the performance of the proposed preprocessing method to the action recognition model and the performance of the original ERP image input method, the performance is improved up to 99.6%, and the action is obtained when only the OOI is detected. It can also see the effects of related video summaries.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.35-39
• /
• 2003

본 연구에서는 1998년 8월 12일 홍수가 발생했을때 충청북도 옥천, 보은 지역을 촬영 한 RADARSAT 위성영상을 이용하여 수계지역 추출 및 홍수지역 모니터링을 수행하였다. 이를 위해서 RADARSAT 영상에 대해 전처리를 수행하고, 전처리된 영상과 수치고도모형으로부터 생성된 경사도 자료를 이용하여 홍수발생시 수계영역을 추출하였다. 추출된 수계영역과 기존의 토지이용 현황도를 이용하여 침수지역의 현황을 분석하고, 토지이용별 침수면적을 산정하였다. 나아가 수치고도모형과 홍수시 수계를 이용하여 금강권 유역의 호우로 인해 증가된 유량을 간접적으로 산정하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2527-2533
• /
• 2011

In this paper we propose a new pre-processing algorithm applied to multi-view video coding using color compensation algorithm based on image features. Multi-view images have a difference between neighboring frames according to illumination and different camera characteristics. To compensate this color difference, first we model the characteristics of cameras based on frame's feature from each camera and then correct the color difference. To extract corresponding features from each frame, we use Harris corner detection algorithm and characteristic coefficients used in the model is estimated by using Gauss-Newton algorithm. In this algorithm, we compensate RGB components of target images, separately from the reference image. The experimental results with many test images show that the proposed algorithm peformed better than the histogram based algorithm as much as 14 % of bit reduction and 0.5 dB ~ 0.8dB of PSNR enhancement.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.41-51
• /
• 2024

In this paper, we explore the enhancement of target detection accuracy in the guided weapon using deep learning object detection on infrared (IR) images. Due to the characteristics of IR images being influenced by factors such as time and temperature, it's crucial to ensure a consistent representation of object features in various environments when training the model. A simple way to address this is by emphasizing the features of target objects and reducing noise within the infrared images through appropriate pre-processing techniques. However, in previous studies, there has not been sufficient discussion on pre-processing methods in learning deep learning models based on infrared images. In this paper, we aim to investigate the impact of image pre-processing techniques on infrared image-based training for object detection. To achieve this, we analyze the pre-processing results on infrared images that utilized global or local information from the video and the image. In addition, in order to confirm the impact of images converted by each pre-processing technique on object detector training, we learn the YOLOX target detector for images processed by various pre-processing methods and analyze them. In particular, the results of the experiments using the CLAHE (Contrast Limited Adaptive Histogram Equalization) shows the highest detection accuracy with a mean average precision (mAP) of 81.9%.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.6
• /
• pp.485-494
• /
• 2017

This study focuses on automatic image registration between multiple IR images using simple preprocessing method and modified local feature extraction algorithm. The input images were preprocessed by using the median and absolute value after histogram equalization, and it could be effectively applied to reduce the brightness difference value between images by applying the similarity of extracted features to the concept of angle instead of distance. The results were evaluated using visual and inverse RMSE methods. The features that could not be achieved by the existing local feature extraction technique showed high image matching reliability and application convenience. It is expected that this method can be used as one of the automatic registration methods between multi-sensor images under specific conditions.

• Journal of Korea Multimedia Society
• /
• v.2 no.3
• /
• pp.297-307
• /
• 1999

A character recognition system, where a large amount of character images arrive continuously in real time, must preprocess character images very quickly. Moreover, information loss due to image trans-formations such as geometric normalization and thinning needs to be minimized especially when character images are small and noisy. Therefore, we suggest a prompt and effective feature extraction method without transforming original images. For this, boundary pixels are defined in terms of the degree in classification, and those boundary pixels are considered selectively in extracting features. The proposed method is tested by a handwritten character recognition and a car plate number recognition. The experiments show that the proposed method is effective in recognition compared to conventional methods. And an overall reduction of execution time is achieved by completing all the required processing by a single image scan.