• Smart Structures and Systems
• /
• 제33권6호
• /
• pp.449-463
• /
• 2024

Automated crack detection is crucial for structural health monitoring and post-earthquake rapid damage detection. However, realizing high precision automatic crack detection in the absence of corresponding manual labeling presents a formidable challenge. This paper presents a novel crack segmentation transfer learning method and a novel crack segmentation model called Swin-CrackFormer. The proposed method facilitates efficient crack image style transfer through a meticulously designed data preprocessing technique, followed by the utilization of a GAN model for image style transfer. Moreover, the proposed Swin-CrackFormer combines the advantages of Transformer and convolution operations to achieve effective local and global feature extraction. To verify the effectiveness of the proposed method, this study validates the proposed method on three unlabeled crack datasets and evaluates the Swin-CrackFormer model on the METU dataset. Experimental results demonstrate that the crack transfer learning method significantly improves the crack segmentation performance on unlabeled crack datasets. Moreover, the Swin-CrackFormer model achieved the best detection result on the METU dataset, surpassing existing crack segmentation models.

• 대한원격탐사학회지
• /
• 제36권5_2호
• /
• pp.975-988
• /
• 2020

변화탐지는 서로 다른 시점에 촬영된 영상에서 일어난 변화를 관측하는 기술로 위성영상을 활용한 원격탐사 분야에서 중요한 기술이다. 변화탐지 기법 중 하나인 무감독 변화탐지 기법은 단시간 내에 변화지역을 추출할 수 있는 장점을 지니지만, 임계값을 통해 변화된 지역을 이진영상으로 나타내기 때문에 토지피복변화를 파악하기 어렵다는 단점이 있다. 본 연구는 이러한 무감독 변화탐지의 단점을 보완하기 위해 공간정보를 기반으로 생성된 격자 포인트를 이용하여 위성영상의 토지피복변화 및 정확도 평가를 수행하였다. 변화탐지 알고리즘은 Spectral Angle Mapper(SAM)를 사용하였으며, 김제자유무역지역 일대를 촬영한 KOMPSAT-3A(K3A) 위성영상을 대상으로 진행하였다. 변화탐지결과는 자동 임계값 추출 알고리즘들 중 Otsu, Kittler, Kapur, Tsai 방법을 사용하여 이진영상으로 나타냈다. 또한, 변화탐지에 사용된 두 시점의 위성영상은 계절에 의한 식생 변화가 존재하기 때문에 확률밀도함수를 통한 Differenced Normalized Difference Vegetation Index(dNDVI)의 임계값으로 계절적 영향을 받는 지역을 제거하였다. 연구 결과, 자동 임계값 추출 알고리즘 중 Otsu와 Kapur의 정확도가 58.16%로 나타났고, dNDVI를 통해 계절적 영향을 제거하였을 때 85.47%로 정확도가 개선된 결과를 보였다. 본 연구결과를 기반으로 생성된 알고리즘은 무감독 변화탐지를 수행할 때 정확도 평가와 토지피복변화를 정량적으로 파악하여 기존의 단점을 보완할 수 있다고 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• 비파괴검사학회지
• /
• 제37권2호
• /
• pp.106-114
• /
• 2017

This paper presents an automated subsurface micro void detection technique based on pulsed infrared thermography for inspecting epoxy molding compounds (EMC) used in electronic device packaging. Subsurface micro voids are first detected and visualized by extracting a lock-in amplitude image from raw thermal images. Binary imaging follows to achieve better visualization of subsurface micro voids. A median filter is then applied for removing sparse noise components. The performance of the proposed technique is tested using 36 EMC samples, which have subsurface (below $150{\mu}m{\sim}300{\mu}m$ from the inspection surface) micro voids ($150{\mu}m{\sim}300{\mu}m$ in diameter). The experimental results show that the subsurface micro voids can be successfully detected without causing any damage to the EMC samples, making it suitable for automated online inspection.

• 한국가구학회지
• /
• 제12권1호
• /
• pp.27-37
• /
• 2001

Automation of wood processing is strongly required to improve the productivity and quality of wood products in wood industry which is one of the most labor-intensive industries. Classification of surface defects on wood boards such as knots is one of the important steps towards a completely automated wood processing system. In this study the possibility of detection of knots by image processing technique was investigated. Algorithm for the automatic determination of threshold value was developed to enhance the flexibility of image processing system. Two different approaches, grid method and tile method, were developed to enhance the speed in extracting features from images. Grid method showed slightly higher processing speed and tile method proved much more stable in determining threshold values. Tile size of $5{\times}5$ pixels or $6{\times}6$ pixels was found to be proper to get stable results with resonable processing time.

• Applied Microscopy
• /
• 제51권
• /
• pp.4.1-4.12
• /
• 2021

Fluorescence in situ hybridization (FISH) is a technique to visualize specific DNA/RNA sequences within the cell nuclei and provide the presence, location and structural integrity of genes on chromosomes. A confocal Whole Slide Imaging (WSI) scanner technology has superior depth resolution compared to wide-field fluorescence imaging. Confocal WSI has the ability to perform serial optical sections with specimen imaging, which is critical for 3D tissue reconstruction for volumetric spatial analysis. The standard clinical manual scoring for FISH is labor-intensive, time-consuming and subjective. Application of multi-gene FISH analysis alongside 3D imaging, significantly increase the level of complexity required for an accurate 3D analysis. Therefore, the purpose of this study is to establish automated 3D FISH scoring for z-stack images from confocal WSI scanner. The algorithm and the application we developed, SHIMARIS PAFQ, successfully employs 3D calculations for clear individual cell nuclei segmentation, gene signals detection and distribution of break-apart probes signal patterns, including standard break-apart, and variant patterns due to truncation, and deletion, etc. The analysis was accurate and precise when compared with ground truth clinical manual counting and scoring reported in ten lymphoma and solid tumors cases. The algorithm and the application we developed, SHIMARIS PAFQ, is objective and more efficient than the conventional procedure. It enables the automated counting of more nuclei, precisely detecting additional abnormal signal variations in nuclei patterns and analyzes gigabyte multi-layer stacking imaging data of tissue samples from patients. Currently, we are developing a deep learning algorithm for automated tumor area detection to be integrated with SHIMARIS PAFQ.

• 전자공학회논문지CI
• /
• 제42권4호
• /
• pp.51-58
• /
• 2005

본 논문에서는 비디오 시퀀스의 자동분류를 지원하기 위한 기반기술로서, 변형된 $\chi^2$-테스트와 자동 임계치-결정 알고리즘을 이용한 장면전환 검출 기법을 제안하였다. 변형된 $\chi^2$-테스트는 기존의 컬러 히스토그램에서 컬러의 각 채널공간(RGB)에 NTSC표준에 따른 명암도 등급을 따로 계산하여 채널의 차이 값을 보다 세분화 할 수 있으며, 인접한 두 프레임사이의 상대적인 컬러 값의 차이를 강조하는$\chi^2$- 테스트를 결합하여 보다 강건한 장면전환 곁출을 시도하고 있다. 자동 임계치-결정 알고리즘은 변형된 $\chi^2$-테스트를 통하여 획득된 인접한 프레임들 사이의 차이 값들을 이용한다. 먼저, 차이 값들에 대한 전체 평균값을 계산한 후, 이 평균값을 만족하는 차이 값들만을 이용하여 다시 평균값을 계산하며, 이러한 평균값의 연속적인 계산 및 누적을 통하여 분산된 차이 값들로부터 가장 최적의 중간 평균값을 취하여 임계치로 설정하는 방법이다. 실험결과 제안된 장면전환 검출 방법과 자동 임계치-결정 알고리즘은 기존의 접근방법보다 효과적이며, 그 우수성을 보여주었다.

• 정보보호학회논문지
• /
• 제26권2호
• /
• pp.397-404
• /
• 2016

최근 국내에서 불법 유해정보의 양은 꾸준히 증가하고 있으며, 중소기업, 공공기관 등의 게시판에 불법 유해정보 글들이 많이 게시되고 있다. 불법 유해정보를 통해 범죄로 이어질 가능성이 크기 때문에 이를 탐지하는 시스템이 필요하다. 현재 국내의 불법 유해정보 탐지는 인력에 의해 수동적으로 진행되고 있다. 본 논문에서는 공개출처정보(OSINT)를 통해 불법 유해정보 중 마약 판매 게시글의 URL 탐지를 자동화하는 연구를 진행하였다. 이 시스템은 마약 판매 게시글의 단어를 분석하고, 해당 단어로 검색어 사전을 만들었다. 검색어 사전 기반으로 검색되는 마약판매 의심 URL을 구글 검색엔진을 활용하여 자동으로 수집하였다. 수집 URL을 도메인별로 분류하였으며, 도메인을 수집 URL 개수별로 도식화하여 실제 불법 유해정보를 찾아내었다. 이 자동화 탐지 시스템을 활용하면 모니터 요원의 수동적인 탐지업무로 인한 시간과 노력의 소비 문제를 해결할 것으로 기대된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.668-670
• /
• 1999

We have developed a automatic surface inspection system for cold Rolled strips in steel making process for several years. We have experienced the various kinds of surface inspection systems, including linear CCD camera type and the laser type inspection system which was installed in cold rolled strips production lines. But, we did not satisfied with these inspection systems owing to insufficient detection and classification rate, real time processing performance and limited line speed of real production lines. In order to increase detection and computing power, we have used the Dark Field illumination with Infra_Red LED, Bright Field illumination with Xenon Lamp, Parallel Computing Processor with Area typed CCD camera and full software based image processing technique for the ease up_grading and maintenance. In this paper, we introduced the automatic inspection system and real time image processing technique using the Object Detection, Defect Detection, Classification algorithms. As a result of experiment, under the situation of the high speed processed line(max 1000 meter per minute) defect detection is above 90% for all occurred defects in real line, defect name classification rate is about 80% for most frequently occurred 8 defect, and defect grade classification rate is 84% for name classified defect.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.698-701
• /
• 2006

Remotely sensed data have been utilized efficiently for damage detection immediately after the natural disaster since they provide valuable information on land cover change due to spatial synchronization and multitemporal observation over large areas. Damage information obtained at an early stage is important for rapid emergency response and recovery works. Many useful techniques to analyze the characteristics of the pre- and post-event satellite images in large-scale damage detection have been successfully investigated for emergency management. Since high-resolution satellite images provide a wealth of information on damage occurred in urban areas, they are successfully utilized for damage detection in urban areas. In this research, a method to perform automated damage detection is proposed based on the differences of the textural characteristics in pre- and post- high resolution satellite images.