• 한국농공학회논문집
• /
• 제64권3호
• /
• pp.63-73
• /
• 2022

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

• 한국통신학회논문지
• /
• 제28권2C호
• /
• pp.147-161
• /
• 2003

비디오 객체 분할(Video Object Segmentation)은 MPEG-4 부호화의 핵심기술로 실시간 요구사항을 위해 빠르고 정확하여야 한다. 그러나 대부분의 존재하는 알고리즘은 계산량이 많으며 실시간 응용을 위해 적합하지 않다. 또한 이전 MPEG-4 VM(Verification Model) 기본 모델은 MPEG-4 부호화 처리를 위한 기본 알고리즘을 제공하였으나 실시간 요구사항을 위한 카메라 입력 시스템, 실용적인 소프트웨어 개발, 비디오 객체 분할 그리고 압축효율에 많은 제한이 있다. 이에 본 논문은 기본 MPEG-4 VM모델에 내용 기반 비디오 코딩의 핵심인 VOP 추출알고리즘, 실시간 카메라 입력 시스템, 압축율을 높일 수 있는 움직임 감지 알고리즘을 추가하여 최대 180:1의 압축율을 보여주는 실시간 고압축 MPEG-4 전처리 시스템을 개발하였다.

• 한국정보처리학회논문지
• /
• 제7권1호
• /
• pp.286-295
• /
• 2000

본 논문은 MR 영상의 비지도 분할을 위하여 MDL원리를 이용한 통계적 모델기반의 적응적 방법을 제안한다. 이 방법에서 조직 영역을 MRF로 모델링함으로써 잡음에 대응하고, 창으로 정의되는 국소영역 내의 밝기값을 가우스 혼합으로 모델링함으로써 영상의 비균일성을 흡수한다. 분할 알고리즘은 ICM을 기반으로 하며 MAP를 근사적으로 추정하고, 모델 파라미터를 국소영역으로부터 구한다. 파라미터 추정과 분할을 위한 창의 크기는 MDL원리를 이용하여 영상으로부터 추정한다. 실험에서 제안한 방법이 특히 비균일성이 있는 MR영상의 분할에서 국소영역의 영상특성을 잘 반영하였으며, 기존의 방법보다 더 좋은 결과를 보여주었다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• 한국의류학회지
• /
• 제26권11호
• /
• pp.1605-1614
• /
• 2002

The purpose of this study was to identify the consumers who use the level of price as the indicator of the product quality. In order to implement the purpose of this study, Jeans market had been segmented by the mixture regression model, and price response function was calibrated for each segment. Based on the types of price response function, segments were allocated into one of two groups; the group using the level of price as the quality indicator or the group not using the level of price as that. Then, characteristics of both groups were compared in terms of product attributes and demographic variables. Data were co]looted from the sample of the 23o undergraduate and graduate students in Seoul. For the data analysis, mixture regression model, conjoint analysis, and t-test were used. As a result, jeans market was divided into 5 segments. Segment 1,2,3 were allocated into the group not using the level of price as the quality indicator while segment 4,5 were done into the other group. Significant differences existed between two groups in product attributes, not in demographic variables. Mixture model and conjoint analysis were proved to be an effective set of tools in market segmentation.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.88-91
• /
• 2020

Image segmentation is the task of partitioning an image into multiple sets of pixels based on some characteristics. The objective is to simplify the image into a representation that is more meaningful and easier to analyze. In this paper, we apply deep-learning to pre-train the learning model, and implement an algorithm that performs image segmentation in real time by extracting frames for the stream input from the Android device. Based on the open source of DeepLab-v3+ implemented in Tensorflow, some convolution filters are modified to improve real-time operation on the Android platform.

• 디지털융복합연구
• /
• 제19권6호
• /
• pp.251-258
• /
• 2021

본 논문에서는 U-Net 기반의 semantic segmentation 방법에서 정확도를 향상시키기 위해 residual learning을 활용한 인코더-디코더 구조의 모델을 제안하였다. U-Net은 딥러닝 기반의 semantic segmentation 방법이며 자율주행 자동차, 의료 영상 분석과 같은 응용 분야에서 주로 사용된다. 기존 U-Net은 인코더의 얕은 구조로 인해 특징 압축 과정에서 손실이 발생한다. 특징 손실은 객체의 클래스 분류에 필요한 context 정보 부족을 초래하고 segmentation 정확도를 감소시키는 문제가 있다. 이를 개선하기 위해 제안하는 방법은 기존 U-Net에 특징 손실과 기울기 소실 문제를 방지하는데 효과적인 residual learning을 활용한 인코더를 통해 context 정보를 효율적으로 추출하였다. 또한, 인코더에서 down-sampling 연산을 줄여 특징맵에 포함된 공간 정보의 손실을 개선하였다. 제안하는 방법은 Cityscapes 데이터셋 실험에서 기존 U-Net 방법에 비해 segmentation 결과가 약 12% 향상되었다.

• 융합보안논문지
• /
• 제23권5호
• /
• pp.125-133
• /
• 2023

본 논문은 공유형 전동킥보드 시스템 운영 시, 관리 상 발생할 수 있는 주차 문제를 해결하기 위해 반납 인증사진으로 주차, 비주차 구역을 판단하는 AI모델을 제시한다. 본 연구에서는 주차/비주차 구역 배경 관련 객체를 판별하기 위해 ADE20K에 Pre_trained된 Segfomer_b0 모델과 점자블록, 전동킥보드에 Fine_tuning한 Segfomer_b0 모델을 통해 주차/비주차에 관련된 객체의 Segmentation map을 추출하고, Swin 모델을 통해 주차/비주차 구역을 이진 분류하는 방법을 제시하였다. 최종적으로 총 1,689장을 직접 라벨링한 후 진행한 Fine_tuning SegFomer 모델은 mAP가 81.26% 수준으로 전동킥보드와 점자블록을 인식하였으며, 총 2,817장을 훈련한 Classification 모델은 92.11%의 정확도와 91.50%의 F1-Score로 주차구역과 비주차 구역을 분류하는 것이 가능하였다.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.59-70
• /
• 2020

This paper presents a fully automatic tool to recognize the liver region from CT images based on a deep learning model, namely Multiple Filter U-net, MFUnet. The advantages of both U-net and Multiple Filters were utilized to construct an autoencoder model, called MFUnet for segmenting the liver region from computed tomograph. The MFUnet architecture includes the autoencoding model which is used for regenerating the liver region, the backbone model for extracting features which is trained on ImageNet, and the predicting model used for liver segmentation. The LiTS dataset and Chaos dataset were used for the evaluation of our research. This result shows that the integration of Multiple Filter to U-net improves the performance of liver segmentation and it opens up many research directions in medical imaging processing field.

• 한국안전학회지
• /
• 제34권6호
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.