• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.255-256
• /
• 2019

본 논문에서는 초고해상도 기술의 복잡도를 줄이기 위하여 픽셀단위 생략 방법을 제안한다. 제안하는 방법은 픽셀 단위로 수평, 수직 방향의 밝기에 대한 2 차 미분치에 기반하여 생략을 결정한다. 제안하는 방법의 성능 평가를 위하여 가장 간단한 초고해상도 알고리즘인 SRCNN 과 제안하는 방법의 PSNR 비교한다. 그 결과 제안하는 방법이 평균적으로 약 47%의 픽셀이 생략이 되면서 SRCNN 대비 0.2dB PSNR 감소를 보인다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1816-1825
• /
• 2022

In this paper, we propose a new approach for tracking each human in a surveillance camera network with various resolution cameras. When tracking human on multiple non-overlapping cameras, the traditional appearance features are easily affected by various camera viewing conditions. To overcome this limitation, the proposed system utilizes facial information along with appearance information. In general, human images captured by the surveillance camera are often low resolution, so it is necessary to be able to extract useful features even from low-resolution faces to facilitate tracking. In the proposed tracking scheme, texture-based face descriptor is exploited to extract features from detected face after face frontalization. In addition, when the size of the face captured by the surveillance camera is very small, a super-resolution technique that enlarges the face is also exploited. The experimental results on the public benchmark Dana36 dataset show promising performance of the proposed algorithm.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.9
• /
• pp.22-30
• /
• 2011

Recently, the rising demand for intelligent video surveillance system leads to high-performance face recognition systems. The solution for low-resolution images acquired by a long-distance camera is required to overcome the distance limits of the existing face recognition systems. For that reason, this paper proposes a hardware design of an image resolution enhancement algorithm for real-time intelligent video surveillance systems. The algorithm is synthesizing a high-resolution face image from an input low-resolution image, with the help of a large collection of other high-resolution face images, called training set. When we checked the performance of the algorithm at 32bit RISC micro-processor, the entire operation took about 25 sec, which is inappropriate for real-time target applications. Based on the result, we implemented the hardware module and verified it using Xilinx Virtex-4 and ARM9-based embedded processor(S3C2440A). The designed hardware can complete the whole operation within 33 msec, so it can deal with 30 frames per second. We expect that the proposed hardware could be one of the solutions not only for real-time processing at the embedded environment, but also for an easy integration with existing face recognition system.

• Proceedings of the Optical Society of Korea Conference
• /
• 2009.02a
• /
• pp.243-245
• /
• 2009

광학 현미경의 분해능이 파장에 따른 회절에 의해 결정된다. 이것을 극복하기 위해서 나노미터까지 분해능을 향상시키기 위해서 근접장 광학이 각광을 받고 있다. 본 보고에서는 흡수 에지 근처의 위상변화 특성에 기인한 초해상을 보고한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.303-308
• /
• 2020

The ReLU(Rectified Linear Unit) function has been dominantly used as a standard activation function in most deep artificial neural network models since it was proposed. Later, Leaky ReLU, Swish, and Mish activation functions were presented to replace ReLU, which showed improved performance over existing ReLU function in image classification task. Therefore, we recognized the need to experiment with whether performance improvements could be achieved by replacing the RELU with other activation functions in the super resolution task. In this paper, the performance was compared by changing the activation functions in EDSR model, which showed stable performance in the super resolution task. As a result, in experiments conducted with changing the activation function of EDSR, when the resolution was converted to double, the existing activation function, ReLU, showed similar or higher performance than the other activation functions used in the experiment. When the resolution was converted to four times, Leaky ReLU and Swish function showed slightly improved performance over ReLU. PSNR and SSIM, which can quantitatively evaluate the quality of images, were able to identify average performance improvements of 0.06%, 0.05% when using Leaky ReLU, and average performance improvements of 0.06% and 0.03% when using Swish. When the resolution is converted to eight times, the Mish function shows a slight average performance improvement over the ReLU. Using Mish, PSNR and SSIM were able to identify an average of 0.06% and 0.02% performance improvement over the RELU. In conclusion, Leaky ReLU and Swish showed improved performance compared to ReLU for super resolution that converts resolution four times and Mish showed improved performance compared to ReLU for super resolution that converts resolution eight times. In future study, we should conduct comparative experiments to replace activation functions with Leaky ReLU, Swish and Mish to improve performance in other super resolution models.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.306-314
• /
• 2019

Since the resolutions of videos increase rapidly, there are continuing needs for effective video compression methods despite an increase in the transmission bandwidth. In order to satisfy such a demand, a reconstructive video coding (RVC) method by using a super resolution has been proposed. Since RVC reduces the resolution of the input video, when frames are compressed to the same size, the number of bits per pixel increases, thereby reducing coding artifacts caused by video coding. However, RVC method using super resolution is not effective in all target bitrates. Comparing the size of the loss generated while downsizing the resolution and the size of the loss caused by the video compression, only when the size of loss generated in the video compression is larger, RVC method can perform the improved compression performance compared to direct video coding. In particular, since HEVC has considerably higher compression performance than the previous standard video codec, it can be experimentally confirmed that the compression distortions become larger than the distortions of downsizing the resolution only in the very low-bitrate conditions. In this paper, we applied RVC based HEVC in various video types and measured the target bitrates that RVC method can be effectively applied.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.608-620
• /
• 2021

Recent deep learning-based face super-resolution (FSR) works showed significant performances by utilizing facial prior knowledge such as facial landmark and dictionary that reflects structural or semantic characteristics of the human face. However, most of these methods require additional processing time and memory. To solve this issue, this paper propose an efficient FSR models using knowledge distillation techniques. The intermediate features of teacher network which contains dictionary information based on major face regions are transferred to the student through adversarial multi-scale features distillation. Experimental results show that the proposed model is superior to other SR methods, and its effectiveness compare to teacher model.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.90-99
• /
• 2023

In this paper, we propose a super resolution network for raw sensor image which data size is lower comparatively to RGB image. But the actual capabilities of raw image super resolution depends on color correction because its absent of camera post processing that leads to unintended result having different white balance, saturation, etc. Thus, we introduce novel color corrector attention network by adopting the idea of precedent raw super resolution research, and tune to the our faced problem from data specification. The result is not superior to former researches but shows decent output on certain performance matrix. In the same time, we encounter new challenging problem of unexpected shadowing artifact around image objects that cause performance declination despite its good result overall. This problem remains a task to be solved in the future research.