• 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.

• 인터넷정보학회논문지
• /
• 제20권5호
• /
• pp.105-111
• /
• 2019

인공지능, 빅데이터, 자율주행 등 4차 산업혁명시대를 이끄는 핵심기술은 컴퓨팅 파워의 급속한 발전과 사물인터넷에 기반한 초연결 네트워크를 통해 구현되고 서비스된다. 본 논문에서는 자율주행을 위한 기본적인 기능으로 다양한 환경에서도 정확하게 주행가능한 영역을 인식하여 추출하는 인공지능 딥러닝 모델들을 구현하고, 그 결과를 비교, 분석한다. 주행가능한 영역을 추출하는 딥러닝 모델은 영상 분할 분야에서 성능이 우수하고 자율주행 연구에서 많이 사용하는 Deep Lab V3+와 Mask R-CNN을 활용하였다. 다양한 환경에서의 주행 정보를 위해 여러 가지 날씨 조건과 주 야간 환경에서의 주행 영상 및 이미지를 제공하는 BDD 데이터셋을 학습데이터로 사용하였다. 활용한 모델들의 실험 결과, DeepLab V3+는 48.97%의 IoU를 보였으며, Mask R-CNN은 68.33%의 IoU로 더 우수한 성능을 보였다. 또한, 구현한 모델로 추출된 주행가능 영역을 이미지에 표시하여 육안으로 검사한 결과, Mask R-CNN은 83%, Deep Lab V3+는 69% 정확도로 Mask R-CNN이 Deep Lab V3+ 보다 주행가능한 영역을 추출하는 분야에서는 더 성능이 높은 것으로 확인하였다.

• 반도체디스플레이기술학회지
• /
• 제19권3호
• /
• pp.12-18
• /
• 2020

In semiconductor manufacturing, defect detection is critical to maintain high yield. Currently, computer vision systems used in semiconductor photo lithography still have adopt to digital image processing algorithm, which often occur inspection faults due to sensitivity to external environment. Thus, we intend to handle this problem by means of using Mask R-CNN instead of digital image processing algorithm. Additionally, Mask R-CNN can be trained with image dataset pre-processed by means of the specific designed digital image filter to extract the enhanced feature map of Convolutional Neural Network (CNN). Our approach converged advantage of digital image processing and instance segmentation with deep learning yields more efficient semiconductor photo lithography inspection system than conventional system.

• 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.

• International journal of advanced smart convergence
• /
• 제8권3호
• /
• pp.131-137
• /
• 2019

This study proposes a method of learning and recognizing the characteristics that are the classification criteria of Hangul using Mask R-CNN, one of the deep learning techniques, to recognize and classify atypical Hangul characters. The atypical characters on the Hangul signboard have a lot of deformed and colorful shapes beyond the general characters. Therefore, in order to recognize the Hangul signboard character, it is necessary to learn a separate atypical Hangul character rather than the existing formulaic one. We selected the Hangul character '닭' as sample data and constructed 5,383 Hangul image data sets and used them for learning and verifying the deep learning model. The accuracy of the results of analyzing the performance of the learning model using the test set constructed to verify the reliability of the learning model was about 92.65% (the area detection rate). Therefore we confirmed that the proposed method is very useful for Hangul signboard character recognition, and we plan to extend it to various Hangul data.

• 지적과 국토정보
• /
• 제48권2호
• /
• pp.213-225
• /
• 2018

3차원 공간정보 구축을 위해 건물 텍스처를 촬영하는 과정에서 폐색영역 문제가 발생한다. 이를 해결하기 위해선 폐색영역을 자동 인식하여 이를 검출하고 텍스처를 자동 보완하는 자동화 기법 연구가 필요하다. 현실적으로 매우 다양한 구조물 형상과 폐색을 발생시키는 경우가 있으므로 이를 극복하는 대안들이 고려되고 있다. 본 연구는 최근 대두되고 있는 딥러닝 기반의 알고리즘을 이용하여 폐색지역 패턴화하고, 학습기반 폐색영역 자동 검출하는 접근을 시도한다. 영상 내 객체 추출에서 우수한 성과를 발표하는 Convolutional Neural Network (CNN) 기법의 향상된 알고리즘인 Faster Region-based Convolutional Network (R-CNN)과 Mask R-CNN 2가지를 이용하여, 건물 벽면 촬영 시 폐색을 유발하는 사람, 현수막, 차량, 신호등에 대한 자동 탐지하는 성능을 알아보기 위해 실험하고, Mask R-CNN의 미리 학습된 모델에 현수막을 학습시켜 자동탐지하는 실험을 통해 적용이 높은 결과를 확인할 수 있었다.

• 디지털콘텐츠학회 논문지
• /
• 제19권6호
• /
• pp.1213-1218
• /
• 2018

최근 비전분야에 소개된 Mask R-CNN은 객체 인스턴스 세분화를위한 개념적으로 간단하고 유연하며 일반적인 프레임 워크를 제시한다. 이 논문에서는 열적외선 카메라로부터 획득한 열감지영상에서 발열체인 인스턴스에 대해 발열부위의 세그멘테이션 마스크를 생성하는 동시에 이미지 내의 오브젝트 발열부분을 효율적으로 탐색하는 알고리즘을 제안한다. Mask R-CNN 기법은 바운딩 박스 인식을 위해 기존 브랜치와 병렬로 객체 마스크를 예측하기 위한 브랜치를 추가함으로써 Faster R-CNN을 확장한 알고리즘이다. Mask R-CNN은 훈련이 간단하고 빠르게 실행하는 고속 R-CNN에 추가된다. 더욱이, Mask R-CNN은 다른 작업으로 일반화하기 용이하다. 본 연구에서는 이 R-CNN기반 적외선 영상 검출알고리즘을 제안하여 RGB영상에서 구별할 수 없는 발열체를 탐지하였다. 실험결과 Mask R-CNN에서 변별하지 못하는 발열객체를 성공적으로 검출하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.71-73
• /
• 2019

차량이 얼마나 존재하고 어디에 존재하는지는 교통정보를 반영하는 GeoAI 기반 도시 환경의 구현에서 필수적으로 파악되어야 할 요소이다. 본 논문에서는 객체 검출 및 추출에 유용한 딥러닝 모델인 Mask R-CNN을 이용하여 차량 데이터를 학습시키고 드론으로 촬영한 실제 항공 영상에서 차량 검출 유무를 검증하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.784-791
• /
• 2022

Tack coat is a thin layer of asphalt between the existing pavement and asphalt overlay. During construction, insufficient tack coat layering can later cause surface defects such as slippage, shoving, and rutting. This paper proposed a method for tack coat inspection improvement using an unmanned aerial vehicle (UAV) and deep learning neural network for automatic non-uniform assessment of the applied tack coat area. In this method, the drone-captured images are exploited for assessment using a combination of Mask R-CNN and Grey Level Co-occurrence Matrix (GLCM). Mask R-CNN is utilized to detect the tack coat region and segment the region of interest from the surroundings. GLCM is used to analyze the texture of the segmented region and measure the uniformity and non-uniformity of the tack coat on the existing pavements. The results of the field experiment showed both the intersection over union of Mask R-CNN and the non-uniformity measured by GLCM were promising with respect to their accuracy. The proposed method is automatic and cost-efficient, which would be of value to state Departments of Transportation for better management of their work in pavement construction and rehabilitation.

• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.275-284
• /
• 2023

Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.