• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.33-42
• /
• 2022

In this paper, we proposed a deep learning model based on multi-scale dilated convolution feature fusion for the segmentation of black ice region in road image to send black ice warning to drivers in real time. In the proposed multi-scale dilated convolution feature fusion network, different dilated ratio convolutions are connected in parallel in the encoder blocks, and different dilated ratios are used in different resolution feature maps, and multi-layer feature information are fused together. The multi-scale dilated convolution feature fusion improves the performance by diversifying and expending the receptive field of the network and by preserving detailed space information and enhancing the effectiveness of diated convolutions. The performance of the proposed network model was gradually improved with the increase of the number of dilated convolution branch. The mIoU value of the proposed method is 96.46%, which was higher than the existing networks such as U-Net, FCN, PSPNet, ENet, LinkNet. The parameter was 1,858K, which was 6 times smaller than the existing LinkNet model. From the experimental results of Jetson Nano, the FPS of the proposed method was 3.63, which can realize segmentation of black ice field in real time.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.199-215
• /
• 2020

A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.7
• /
• pp.659-664
• /
• 2016

In this paper, we suggest operational trans-conductance amplifier(OTA) for current-mode FIR filter that can be used in a digital circuit system requiring high operating frequency and low power consumption. The current-mode signal processing is one of the very innovative design method for a low power consumption system with high operating frequency because it shows a constant power regardless of frequency. From the simulation result using 0.35um CMOS process, when Vdd is 2V, it is confirmed that the proposed circuit showed the dynamic range of the about 1V, about 50% of supply voltage and output current swing of about 0~200uA. Also, the power consumption was evaluated with about 21uW and the active size for an integration was measured with $71um{\times}166um$.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.85-96
• /
• 2023

This study proposes a method for forest vegetation monitoring using high-resolution aerial imagery captured by unmanned aerial vehicles(UAV) and deep learning technology. The research site was selected in the forested area of Mountain Dogo, Asan City, Chungcheongnam-do, and the target species for monitoring included Pinus densiflora, Quercus mongolica, and Quercus acutissima. To classify vegetation species at the pixel level in UAV imagery based on characteristics such as leaf shape, size, and color, the study employed the semantic segmentation method using the prominent U-net deep learning model. The research results indicated that it was possible to visually distinguish Pinus densiflora Siebold & Zucc, Quercus mongolica Fisch. ex Ledeb, and Quercus acutissima Carruth in 135 aerial images captured by UAV. Out of these, 104 images were used as training data for the deep learning model, while 31 images were used for inference. The optimization of the deep learning model resulted in an overall average pixel accuracy of 92.60, with mIoU at 0.80 and FIoU at 0.82, demonstrating the successful construction of a reliable deep learning model. This study is significant as a pilot case for the application of UAV and deep learning to monitor and manage representative species among climate-vulnerable vegetation, including Pinus densiflora, Quercus mongolica, and Quercus acutissima. It is expected that in the future, UAV and deep learning models can be applied to a variety of vegetation species to better address forest management.

• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.316-322
• /
• 2020

Endoscopic spine surgery is an advanced surgical technique for spinal surgery since it minimizes skin incision, muscle damage, and blood loss compared to open surgery. It requires, however, accurate positioning of an endoscope to avoid spinal nerves and to locate the endoscope near the target disk. Before the insertion of the endoscope, a guide needle is inserted to guide it. Also, the result of the surgery highly depends on the surgeons' experience and the patients' CT or MRI images. Thus, for the training, a number of haptic simulators for spinal needle insertion have been developed. But, still, it is difficult to be used in the medical field practically because previous studies require manual segmentation of vertebrae from CT images, and interaction force between the needle and soft tissue has not been considered carefully. This paper proposes AI-based automatic vertebrae CT-image segmentation and haptic rendering method using the proposed need-tissue interaction model. For the segmentation, U-net structure was implemented and the accuracy was 93% in pixel and 88% in IoU. The needle-tissue interaction model including puncture force and friction force was implemented for haptic rendering in the proposed spinal needle insertion simulator.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.26-29
• /
• 2005

In order to compute cloud coverage statistics over Asian region, an operational scheme for masking cloud-contaminated pixels in Advanced Very High Resolution Radiometer (AVHRR) daytime data was developed, evaluated and presented. Dynamic thresholding was used with channell, 2 and 3 to automatically create a cloud mask for a single image. Then the IO-day cloud coverage imagery was generated over the whole Asian region along with cloud-free composite imagery. Finally the monthly based statistics were computed based on the derived cloud coverage imagery in terms of land cover and country. As a result, it was found that 20-day is required to acquire the cloud free data over the whole Asia using NOAA AVHRR. The to-day cloud coverage and cloud-free composite imagery derived in this research is available via the web-site http://webpanda.iis.u-tokyo.ac.jp/CloudCover/.

• Electronics and Telecommunications Trends
• /
• v.33 no.4
• /
• pp.92-102
• /
• 2018

On a global level, the energy problem is a very important policy topic, particularly at a time when the nation relies on imports for more than 95% of its energy demand. The starting point of an energy policy should be in line with the international community's concern and cooperation regarding climate warming, and the logic of the new policy on renewable energy expansion in Korea, the pre-developed energy sector, and policy of deserting coal all support this aspect. In particular, to accommodate the rapid urbanization of mankind, the key words of the 4th Industrial Revolution are linking energy to IoT, artificial intelligence, block chain, cloud, and big data.

• Broadcasting and Media Magazine
• /
• v.20 no.3
• /
• pp.54-65
• /
• 2015

최근 네트워크와 연동된 스마트 기기들의 개발과 보급이 활발하게 이루어지고 있으며, 스마트 기기간의 연동을 통한 상호 협력적인 관계를 지능적으로 형성하는 사물인터넷이 큰 이슈가 되고 있다. 본 논문은 홈 내 스마트 기기 및 IoT 기기들의 기능들이 상호 공유되고 협력적으로 제어됨으로써, 더욱 창의적이고 혁신적인 서비스 구성이 가능한 사물인터넷 기반 스마트 홈 서비스 프레임워크를 제시한다. 본 논문에서는 스마트 홈 서비스를 위한 사물인터넷 기술을 소개하고, 홈 내 기기들의 구성 방법에 따른 스마트 홈 서비스 구성 모델을 제시한다. 또한, 상이한 프로토콜과 메시지 포맷을 사용하는 다양한 홈 기기들의 연동 방법, 효율적인 스마트 홈 서비스 개발을 위한 기기 자원 가상화 및 추상 API를 포함하는 스마트 홈 서비스 프레임워크 기술을 제시한다.