• Current Industrial and Technological Trends in Aerospace
• /
• v.4 no.2
• /
• pp.40-48
• /
• 2006

SAR(Synthetic Aperture Radar, 이하 SAR) 위성영상은 광학 영상과는 달리 기상조건의 영향을 거의 받지 않아 대상지역의 주기적인 모니터링이 가능하며, 특정주파수 영역밴드에서는 지표면 투과탐지가 가능하여 재난, 재해, 국방, 환경 분야 등 점차 활용범위가 확대되고 있는 추세이다. 그간의 고해상도 광학위성영상의 기술 개발이 지속적으로 이루어진 상황이라면 그에 비해 영상처리절차가 비교적 까다롭고 복잡한 SAR 영상에 관한 기술개발은 영상 활용의 가치를 가늠해 볼 때 특히 국내 경우 많이 저조한 실정이다. 이와 같은 상황을 고려해 볼 때 현재 개발되고 앞으로 계획단계에 있는 SAR 지구관측 위성의 개발 동향을 파악함으로서 SAR 영상 활용기반구축 마련 및 장기적인 연구개발 계획수립에도 효과적으로 이용될 수 있을 것으로 생각한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.3
• /
• pp.189-196
• /
• 2010

In this paper, we proposed the adaptive local sigma filter reducing noises generated by an image sensor. The small noises generated by the image sensor are amplified by increased an analog gain and an exposure time of the image sensor together with information. And the goal of this work was the system design that is reduce the these amplified noises. Edge data are extracted by Flatness Index Map algorithm. We made the threshold adaptively changeable by the luminance average in this algorithm that extracts the edge data not in high luminance, but just low luminance. The Local Sigma Filter performed only about the edge pixel that were extracted by Flatness Index Map algorithm. To verify the performance of the designed filter, we made the Window test program. The hardware was designed with HDL language. We verified the hardware performance of Local Sigma Filter system using FPGA Demonstration board and HD image sensor, $1280{\times}720$ image size and 30 frames per second.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.85-95
• /
• 2018

With the popularity of smartphones, most peoples have been using mobile cameras to capture photographs. However, due to insufficient amount of lights in a low lighting condition, unwanted noises can be generated during image acquisition. To remove the noise, a method of using deep convolutional neural networks is introduced. However, this method still lacks the ability to describe textures and edges, even though it has made significant progress in terms of visual quality performance. Therefore, in this paper, the HOG (Histogram of Oriented Gradients) images that contain information about edge orientations are used. More specifically, a method of learning deep convolutional neural networks is proposed by stacking noise and HOG images into an input tensor. Experiment results confirm that the proposed method not only can obtain excellent result in visual quality evaluations, compared to conventional methods, but also enable textures and edges to be improved visually.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.197-203
• /
• 2005

In this paper, we propose an emotion recognition using facial Images to effectively design human interface. Facial database consists of six basic human emotions including happiness, sadness, anger, surprise, fear and dislike which have been known as common emotions regardless of nation and culture. Emotion recognition for the facial images is performed after applying the discrete wavelet. Here, the feature vectors are extracted from the PCA and LDA. Experimental results show that human emotions such as happiness, sadness, and anger has better performance than surprise, fear and dislike. Expecially, Japanese shows lower performance for the dislike emotion. Generally, the recognition rates for Korean have higher values than Japanese cases.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.634-636
• /
• 2023

Surveillance systems play a pivotal role in ensuring the safety and security of various environments, including public spaces, critical infrastructure, and private properties. However, detecting abnormal human behavior in lowlight conditions is a critical yet challenging task due to the inherent limitations of visual data acquisition in such scenarios. This paper introduces a spatiotemporal framework designed to address the unique challenges posed by low-light environments, enhancing the accuracy and efficiency of human abnormality detection in surveillance camera systems. We proposed the pre-processing using lightweight exposure correction, patched frames pose estimation, and optical flow to extract the human behavior flow through t-seconds of frames. After that, we train the estimated-action-flow into autoencoder for abnormal behavior classification to get normal loss as metrics decision for normal/abnormal behavior.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.12
• /
• pp.131-141
• /
• 2012

This paper proposes a method of analyzing unrecognizable numbers of license plate images, which are degraded by various factors such as low resolution, low light level, geometric distortion, and periodic noise, to name a few. With existing vehicle license plate recognition methods, it is difficult to recognize license plate if images are not recognizable in the pre-process of removing degradation factors. Although images of license plate have not been improved to be recognizable in the pre-process, the proposed method makes it possible to recognize numbers of license by distorting pre-saved reference images of license plate numbers same as sample plates, and by assuming likelihood ratio using statistical methods. The proposed method also makes it possible to identify suspect vehicle license plate under unstable light conditions and with low resolution images that are unrecognizable by the naked eye. This method has been used in real criminal investigation to recognize numbers of license plate of criminal vehicle, and has proved to be useful as criminal evidence through experiments under various conditions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.4
• /
• pp.92-101
• /
• 1996

Due to I:he rapid increase of vehicles and poor availability of roads, traffic congestion problem is about to explode. To solve this problem, we need real time information about traffic flow to control traffic signals dynamically. Until now loop coil is the most prevalent sensor used for obtaining traffic flow information. However, it is not able to track individual vehicles which is essential in estimating the average vehicle speed. As a result, image sensors started to find their role in this problem domain. Several systems based on image sensors were proposed which assumes either gray level or color image sequence. In this paper, we propose moving vehicle tracking method based on fizzy clustering assuming a wlor image sequenc.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1044-1051
• /
• 2018

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.135-145
• /
• 2020

Recently, deep-learning based methods for low-light image enhancement accomplish great success through supervised learning. However, they still suffer from the lack of sufficient training data due to difficulty of obtaining a large amount of low-/normal-light image pairs in real environments. In this paper, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP), which gives the constraint that the brightest pixel in a small patch is likely to be close to 1. With this prior, pseudo ground-truth is first generated to establish an unsupervised loss function. The proposed enhancement network is then trained using the proposed unsupervised loss function. To the best of our knowledge, this is the first attempt that performs a low-light image enhancement through unsupervised learning. In addition, we introduce a self-attention map for preserving image details and naturalness in the enhanced result. We validate the proposed method on various public datasets, demonstrating that our method achieves competitive performance over state-of-the-arts.

• Journal of Internet Computing and Services
• /
• v.9 no.1
• /
• pp.171-177
• /
• 2008

In this paper we compared the performance of interpolation algorithms for Bayer patterned image sensors under the various illumination intensities. As the interpolation algorithms, we used bilinear color interpolation and adaptive fuzzy color interpolation and our experimentation shows that performance of interpolation algorithms depend on the lighting conditions; in low intensity of illumination, bilinear color interpolation with median filter performs best, in high intensity of illumination, adaptive fuzzy color interpolation performs best, and in between bilinear color interpolation performs best. This study suggested an interpolation scheme which applies different interpolation algorithm according to the intensity of the input image, resuting in the better image quality.