• 한국멀티미디어학회논문지
• /
• 제24권6호
• /
• pp.745-752
• /
• 2021

In this paper, we propose a system that recognizes weed images using a classifier based on ResNeXt model. On the server of the proposed system, the ResNeXt model extracts the fine features of the weed images sent from the user and classifies it as one of the most similar weeds out of 21 species. And the classification result is delivered to the client and displayed on the smartphone screen through the application. The experimental results show that the proposed weed recognition system based on ResNeXt model is superior to existing methods and can be effectively applied in the real-world agriculture field.

• ETRI Journal
• /
• 제46권2호
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권1호
• /
• pp.41-47
• /
• 2022

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.9-18
• /
• 2024

Small streams, despite their rich ecosystems, face challenges in vegetation assessment due to the limitations of traditional, time-consuming methods. This study presents a groundbreaking approach, combining unmanned aerial vehicles(UAVs), convolutional neural networks(CNNs), and the vegetation differential vegetation index (VDVI), to revolutionize both assessment and management of stream vegetation. Focusing on Idong Stream in South Korea (2.7 km long, 2.34 km² basin area)with eight diverse revetment methods, we leveraged high-resolution RGB images captured by UAVs across five dates (July-December). These images trained a ResNeXt101 CNN model, achieving an impressive 89% accuracy in classifying vegetation cover(soil,water, and vegetation). This enabled detailed spatial and temporal analysis of vegetation distribution. Further, VDVI calculations on classified vegetation areas allowed assessment of vegetation vitality. Our key findings showcase the power of this approach:(a) TheCNN model generated highly accurate cover maps, facilitating precise monitoring of vegetation changes overtime and space. (b) August displayed the highest average VDVI(0.24), indicating peak vegetation growth crucial for stabilizing streambanks and resisting flow. (c) Different revetment methods impacted vegetation vitality. Fieldstone sections exhibited initial high vitality followed by decline due to leaf browning. Block-type sections and the control group showed a gradual decline after peak growth. Interestingly, the "H environment block" exhibited minimal change, suggesting potential benefits for specific ecological functions.(d) Despite initial differences, all sections converged in vegetation distribution trends after 15 years due to the influence of surrounding vegetation. This study demonstrates the immense potential of UAV-based remote sensing and CNNs for revolutionizing small-stream vegetation assessment and management. By providing high-resolution, temporally detailed data, this approach offers distinct advantages over traditional methods, ultimately benefiting both the environment and surrounding communities through informed decision-making for improved stream health and ecological conservation.

• 한국공간구조학회논문집
• /
• 제22권2호
• /
• pp.19-27
• /
• 2022

Visual inspection methods have limitations, such as reflecting the subjective opinions of workers. Moreover, additional equipment is required when inspecting the high-rise buildings because the height is limited during the inspection. Various methods have been studied to detect concrete cracks due to the disadvantage of existing visual inspection. In this study, a crack detection technology was proposed, and the technology was objectively and accurately through AI. In this study, an efficient method was proposed that automatically detects concrete cracks by using a Convolutional Neural Network(CNN) with the Orthomosaic image, modeled with the help of UAV. The concrete cracks were predicted by three different CNN models: AlexNet, ResNet50, and ResNeXt. The models were verified by accuracy, recall, and F1 Score. The ResNeXt model had the high performance among the three models. Also, this study confirmed the reliability of the model designed by applying it to the experiment.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권5호
• /
• pp.161-168
• /
• 2021

균열은 건물, 교량, 도로, 수송관 등의 기반시설의 안전성에 영향을 주는 요소이다. 본 연구에서는 검사 비용과 시간을 줄일 수 있는 자동화된 균열 탐지 시스템을 다룬다. 환경과 표면에 강건한 시스템을 구성하기 위해서, 본 연구에서는 여러 사전 연구에서 사용된 다양한 표면의 균열 데이터 셋을 수집하여 통합 데이터 셋을 구축하였다. 이후, 컴퓨터 비전 분야에 높은 성능을 발휘하는 VGG, ResNet, WideResNet, ResNeXt, DenseNet, EfficientNet 딥러닝 모델을 적용하였다. 통합 데이터 셋은 훈련 집합(80%)과 테스트 집합(20%)으로 나누어 모델 성능을 검증하기 위해서 사용했다. 실험 결과, DenseNet121 모델이 높은 마라미터 효율성을 가지면서도 테스트 집합에 대해 96.20%의 정확도를 달성하여 가장 높은 성능을 보여주었다. 딥러닝 모델의 균열 검출 성능 검증을 통해, DenseNet121를 활용하여 컴퓨팅 자원이 적은 소형 디바이스에서도 높은 균열 검출 성능을 보이는 탐지 시스템을 구축이 가능함을 확인했다.

• 한국융합학회논문지
• /
• 제12권11호
• /
• pp.45-51
• /
• 2021

딥러닝의 발전으로 인하여 의미론적 분할 방법은 다양한 분야에서 연구되고 있다. 의료 영상 분석과 같이 정확성을 요구하는 분야에서 분할 정확도가 떨어지는 문제가 있다. 본 논문은 의미론적 분할 시 특징 손실을 최소화하기 위해 딥러닝 기반 분할 방법인 PSPNet을 개선하였다. 기존 딥러닝 기반의 분할 방법은 특징 추출 및 압축 과정에서 해상도가 낮아져 객체에 대한 특징 손실이 발생한다. 이러한 손실로 윤곽선이나 객체 내부 정보에 손실이 발생하여 객체 분류 시 정확도가 낮아지는 문제가 있다. 이러한 문제를 해결하기 위해 의미론적 분할 모델인 PSPNet을 개선하였다. 기존 PSPNet에 제안하는 multi scale attention을 추가하여 객체의 특징 손실을 방지하였다. 기존 PPM 모듈에 attention 방법을 적용하여 특징 정제 과정을 수행하였다. 불필요한 특징 정보를 억제함으로써 윤곽선 및 질감 정보가 개선되었다. 제안하는 방법은 Cityscapes 데이터 셋으로 학습하였으며, 정량적 평가를 위해 분할 지표인 MIoU를 사용하였다. 실험을 통해 기존 PSPNet 대비 분할 정확도가 약 1.5% 향상되었다.