• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.6_3
• /
• pp.1297-1303
• /
• 2023

Research on enhancing the mechanical strength, lightweight properties, electrical conductivity, and thermal conductivity of composite materials by incorporating nano-materials is actively underway. Thermoplastic resins can change their form under heat, making them highly processable and recyclable. In this study, Polyamide-Nylon 6 (PA6), a thermoplastic resin, was utilized, and as reinforcing agents, fused carbon nano-materials (FCN) formed by structurally combining Carbon Nanotube(CNT) and Graphene were employed. Nano-materials often face challenges related to cohesion and dispersion. To address this issue, Silane functional groups were introduced to enhance the dispersion of FCN in PA6. The manufacturing conditions for the composite materials involved determining the use of a dispersant and varying FCN content at 0.05 wt%, 0.1 wt%, and 0.2 wt%. Tensile strength measurements were conducted, and FE-SEM analysis was performed on fracture surfaces. As a result of the tensile strength test, it was confirmed that compared to pure PA6, the strength of the polymer composite with a content of 0.05 wt% was improved by about 60%, for 0.1 wt%, about 65%, and for 0.2 wt%, the strength was improved by 50%. Also, when compared according to the content of FCN, the best strength value was shown when 0.1 wt% was added. The elastic modulus also showed an improvement of about 15% in the case of surface treatment compared to the case without surface treatment, and an improvement of about 70% compared to pure PA6. Through FE-SEM, it was confirmed that the matrix material and silane-modified nanomaterial improved the dispersibility and bonding strength of the interface, helping to support the load evenly and enabling effective stress transfer.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.322-325
• /
• 2018

영상의 관심 영역 검출은 영상처리 및 컴퓨터 비전 응용 분야에서 꾸준하게 사용되고 있는 기법이다. 특히, 근래 심층신경망 연구의 급격한 발전에 힘입어 심층신경망을 이용한 관심 영역 검출 기법에 대한 연구가 활발하게 진행되고 있다. 한편 Fully Convolutional Network(이하 FCN)은 본래 심층 예측(Dense Prediction)을 통한 의미론적 영상 분할(Semantic Segmentation)을 수행하기 위해 제안된 심층신경망 구조이다. FCN을 영상의 관심 영역 검출에 활용하여도 기존 관심 영역 검출 기법과 비교하여 충분히 좋은 성능을 발휘할 수 있다. 그러나 FCN에 사용되는 convolution 층의 수가 많고, 이에 따른 가중치(weight)의 개수도 기하급수적으로 늘어나 검출에 필요한 시간 복잡도가 매우 크다는 문제점이 있다. 따라서 본 논문에서는 기존 FCN이 가진 검출 시간 복잡도의 문제점을 convolution 층의 가중치 관점에서 해결하고자 이를 조절하여 FCN의 관심 영역 검출 속도를 향상시키는 방법을 제안한다. 적절한 convolution 층의 가중치를 조절함으로써, MSRA10K 데이터셋 환경에서 검출 정확도를 크게 저하시키지 않고도 최대 약 20.5%만큼 검출 속도를 향상시킬 수 있었다.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.9-16
• /
• 2020

Recently, various studies are being conducted to integrate Image Segmentation into smart factory industries and autonomous driving fields. In particular, Image Segmentation systems using deep learning algorithms have been researched and developed enough to learn from large volumes of data with higher accuracy. In order to use image segmentation in the autonomous driving sector, sufficient amount of learning is needed with large amounts of data and the streaming environment that processes drivers' data in real time is important for the accuracy of safe operation through highways and child protection zones. Therefore, we proposed a novel DFCN algorithm that enhanced existing FCN algorithms that could be applied to various road environments, demonstrated that the performance of the DFCN algorithm improved 1.3% in terms of "loss" value compared to the previous FCN algorithms. Moreover, the proposed DFCN algorithm was applied to the existing U-Net algorithm to maintain the information of frequencies in the image to produce better results, resulting in a better performance than the classical FCN algorithm in the autonomous environment.

• Proceedings of the Optical Society of Korea Conference
• /
• 2009.02a
• /
• pp.397-398
• /
• 2009

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.403-406
• /
• 2005

The purpose of this paper is to propose ways to remove false color noise (FCN) generated during de-mosaicing on RGB Bayer pattern images. In case of images sensors adapting Bayer pattern color filters array (CFA), de-mosaicing is conducted to recover the RGB color data in single pixels. Here, FCN phenomena would occur where there is clearer silhouette or contrast of colors. The FCN phenomena found during de-mosaicking process appears locally in the edges inside the image and the proposed method of eliminating this is to convert RGB color space to YCbCr space to conduct smoothing process. Moreover, for edges where different colors come together, censoring based smoothing technique is proposed as a way to minimize color blurring effect.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.81-83
• /
• 2018

Fully Convolutional Network(FCN)은 기존의 방법보다 뛰어난 성능을 보였지만, FCN은 RGB 정보만을 사용하기 때문에 세밀한 예측이 필요한 장면에서는 다소 부족한 성능을 보였다. 이를 해결하기 위해 인코더-디코더 구조를 이용하여 RGB와 깊이의 멀티 모달을 활용하기 위한 FuseNet이 제안되었다. 하지만, FuseNet에서는 RGB와 깊이 브랜치 사이의 융합은 있지만, 인코더와 디코더 사이의 특징 지도를 융합하지 않는다. 본 논문에서는 FCN의 디코더 부분의 업샘플링 과정에서 이전 계층의 결과와 2배 업샘플링한 결과를 융합하는 스킵 레이어를 적용하여 FuseNet의 모달리티를 잘 활용하여 성능을 개선했다. 본 실험에서는 NYUDv2와 SUNRGBD 데이터 셋을 사용했으며, 전체 정확도는 각각 77%, 65%이고, 평균 IoU는 47.4%, 26.9%, 평균 정확도는 67.7%, 41%의 성능을 보였다.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.5
• /
• pp.423-432
• /
• 2018

Surface water mapping has been widely used in various remote sensing applications. Water indices have been commonly used to distinguish water bodies from land; however, determining the optimal threshold and discriminating water bodies from similar objects such as shadows and snow is difficult. Deep learning algorithms have greatly advanced image segmentation and classification. In particular, FCN (Fully Convolutional Network) is state-of-the-art in per-pixel image segmentation and are used in most benchmarks such as PASCAL VOC2012 and Microsoft COCO (Common Objects in Context). However, these data sets are designed for daily scenarios and a few studies have conducted on applications of FCN using large scale remotely sensed data set. This paper aims to fine-tune the pre-trained FCN network using the CRMS (Coastwide Reference Monitoring System) data set for surface water mapping. The CRMS provides color infrared aerial photos and ground truth maps for the monitoring and restoration of wetlands in Louisiana, USA. To effectively learn the characteristics of surface water, we used pre-trained the DeepWaterMap network, which classifies water, land, snow, ice, clouds, and shadows using Landsat satellite images. Furthermore, the DeepWaterMap network was fine-tuned for the CRMS data set using two classes: water and land. The fine-tuned network finally classifies surface water without any additional learning process. The experimental results show that the proposed method enables high-quality surface mapping from CRMS data set and show the suitability of pre-trained FCN networks using remote sensing data for surface water mapping.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.3
• /
• pp.399-407
• /
• 2019

In Korea, the construction industry has been known to have the highest risk of safety accidents compared to other industries. Therefore, in order to improve safety in the construction industry, several researches have been carried out from the past. This study aims at improving safety of labors in construction site by constructing an effective automatic safety helmet detection system using object detection algorithm based on image data of construction field. Deep learning was conducted using Region-based Fully Convolutional Network (R-FCN) which is one of the object detection algorithms based on Convolutional Neural Network (CNN) with Transfer Learning technique. Learning was conducted with 1089 images including human and safety helmet collected from ImageNet and the mean Average Precision (mAP) of the human and the safety helmet was measured as 0.86 and 0.83, respectively.

• Proceedings of the KSEEG Conference
• /
• 2000.04a
• /
• pp.110-110
• /
• 2000

Temporal and spatial distribution patterns of the magmatic rocks and associated ore deposits in the Mesozoic magmatic - metallogenic belt along the Yangtz River, Anhui Province are used to determine and discuss the crust - mantle interaction processes. The magmatic rocks are Cu - Au mineralized high - K calc - alkalic intermediate ¬acidic (CAK) and Fe - Cu mineralized high - Na alkalic - calc intermediate - basic intrusive rocks (FCN) in the central part of the belt and grade to Cu - Mo - Pb - Zn - Ag mineralized calc - alkalic granitoids (CMG) and A - type granites (AG) in the southern and northern parts of the belt. Samples from the CAK and CMG yield Rb - Sr isochron ages of 137 - 140Ma with $(^{87}Sr/^{86}Sr)_{o}$ = 0.7060 - 0.7101, while those from the FCN and AG yield the ages of 120 - 129Ma with $(^{87}Sr/^{86}Sr)_{o}$ = 0.7047 - 0.7077. The Sr isotope ratios, CriTh ratios 0.4 - 3.1), Eu/Eu* ratios < 0.79 - 1.05) and initial epsilon (Nd) values (-16.6 - -6.3) for the CAK and CMG are consistent with magma derivation from old metamorphic basement rocks rich in metallogenic elements through a two - stage process of mantle - derived magma underplating caused by primary lithosphere extension and subsequent partial melting. On the basis of Sr isotope data, CriTh ratios (3.4 - 13.8), Eu/Eu* ratios (0.86 - 1.13) and initial epsilon (Nd) values (-7.7 - +1.4), the FCN and AG are considered to be formed through syntexis with material input from the mantle that resulted from further lithosphere extension followed by mantle - derived magma underplating on a large scale.