• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1301-1304
• /
• 2022

최근 인공지능 신경망에 대한 활발한 연구를 바탕으로 다양한 분야에서의 적용에 대해 많은 시도들이 이루어지고 있다. 이러한 흐름에 맞추어 화학 문서에서 화학 구조를 인식하는 문제 또한 딥러닝을 이용하여 해결하려는 시도들이 생겨나고 있다. 본 논문에서는 화학 문서에서 화학 구조를 인식하는 모델을 학습시키기 위한 합성 데이터셋을 제안하였다. 문서의 구조를 이용하여 정교하게 화학 구조들을 문서에 합성하여 데이터셋을 생성하였고, 이를 최신 딥러닝 모델 중 하나인 Mask R-CNN[7]에 학습시켜 제안한 데이터셋을 이용하여 문서에서 화학 구조를 인식할 수 있음을 보였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.88-90
• /
• 2021

본 논문은 화학 문서 내에 존재하는 표를 검출하는 문제를 다룬다. 우선 문서에서 표가 있을 만한 영역만을 남긴 후, 객체 검출 분야에서 좋은 성능을 보이는 Cascade Mask R-CNN을 이용하여 화학 문서 내 표 검출을 수행하였다. 더 나아가 감마 보정과 스캔 잡음을 이용하여 학습 데이터를 증강함으로써 다양한 스타일의 표들을 강인하게 검출할 수 있도록 하였다. 합성 화학문서와 실제 화학 문서에 대해 제안한 방법을 적용하여 표 검출 성능을 측정하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.47-50
• /
• 2020

최근 Panorama와 360도 영상이 대표되는 몰입형(Immersive) 미디어 콘텐츠의 사용이 증가하고 있다. 몰입형 영상 콘텐츠는 사용자에게 현장감을 제공해야 하지만, 촬영 카메라 간의 시차(Parallax)로 인해 영상 콘텐츠에서 시차 왜곡이 발생할 수 있고, 이는 사용자의 콘텐츠 몰입을 제한하기 때문에 해당 영상 콘텐츠의 제작 기술인 영상 스티칭의 높은 정확도가 요구되고 있다. 지금까지 스티칭 영상의 시차 왜곡을 줄이기 위하여 다중 호모그래피 추정 방법과 Seam Optimization 방법이 제안되었지만, 영상 내 사물 배치에 따라 기술 적용이 제한될 수 있다. 이에 본 논문에서는 Mask R-CNN을 활용하여 사물을 세그먼트화하고, 사물의 종류에 따라 각각 다른 가중치 적용을 통해 시차 왜곡을 방지하며, 영상 내 사물의 배치에 따라 시차 왜곡이 발생할 상황에서는 사용자의 인지 중요도가 낮은 사물로 시차 왜곡을 유도하는 영상 스티칭 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.562-565
• /
• 2021

스타일 변환 모델은 이미지 전체나 이미지 내에서 사용자가 지정한 영역을 대상으로 스타일을 변환시킨다. 이런 방식은 이미지 내의 다수의 객체에 대해 스타일 변환을 시행할 때 일일이 영역을 지정해 줘야 한다는 불편함과 결과물의 전체 해상도가 떨어진다는 한계를 가지고 있다. 본 논문에서는 이런 한계들을 극복하기 위해 객체탐지 모델과 스타일변환 모델을 연동한 객체스타일변환모델을 제안하고 모델 간 연동방법에 대해 자세히 서술한다. 객체탐지모델인 Mask R-CNN 을 통해 필요한 객체를 탐지하고 탐지한 객체의 특징맵들을 스타일변환 모델인 zi2zi 의 입력 값으로 전달하여 이미지 내의 필요한 객체들만 스타일변환이 이루어지도록 모델이 동작한다. 이러한 모델은 기존에 있는 두 모델을 재사용함으로써 모델을 처음부터 새로 설계할 필요가 없다는 장점이 있으며, 공개된 다양한 모델들을 서로 융합하여 사용할 수 있는 방법을 제시하는데 도움을 줄 것이다.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.271-281
• /
• 2022

Manual seed classification challenges can be overcome using a reliable and autonomous seed purity identification and classification technique. It is a highly practical and commercially important requirement of the agricultural industry. Researchers can create a new data mining method with improved accuracy using current machine learning and artificial intelligence approaches. Seed classification can help with quality making, seed quality controller, and impurity identification. Seeds have traditionally been classified based on characteristics such as colour, shape, and texture. Generally, this is done by experts by visually examining each model, which is a very time-consuming and tedious task. This approach is simple to automate, making seed sorting far more efficient than manually inspecting them. Computer vision technologies based on machine learning (ML), symmetry, and, more specifically, convolutional neural networks (CNNs) have been widely used in related fields, resulting in greater labour efficiency in many cases. To sort a sample of 3000 seeds, KNN, SVM, CNN and CNN-SVM hybrid classification algorithms were used. A model that uses advanced deep learning techniques to categorise some well-known seeds is included in the proposed hybrid system. In most cases, the CNN-SVM model outperformed the comparable SVM and CNN models, demonstrating the effectiveness of utilising CNN-SVM to evaluate data. The findings of this research revealed that CNN-SVM could be used to analyse data with promising results. Future study should look into more seed kinds to expand the use of CNN-SVMs in data processing.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.469-481
• /
• 2018

DL (Deep Learning) is getting popular in various fields to implement artificial intelligence that resembles human learning and cognition. DL based on complicate structure of the ANN (Artificial Neural Network) requires computing power and computation cost. Variety of DL models with improved performance have been developed with powerful computer specification. The main purpose of this paper is to detect buildings from aerial images and evaluate performance of Mask R-CNN (Region-based Convolutional Neural Network) developed by FAIR (Facebook AI Research) team recently. Mask R-CNN is a R-CNN that is evaluated to be one of the best ANN models in terms of performance for semantic segmentation with pixel-level accuracy. The performance of the DL models is determined by training ability as well as architecture of the ANN. In this paper, we characteristics of the Mask R-CNN with various types of the images and evaluate possibility of the generalization which is the ultimate goal of the DL. As for future study, it is expected that reliability and generalization of DL will be improved by using a variety of spatial information data for training of the DL models.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.944-953
• /
• 2020

Object detection plays a crucial role in a self-driving system. With the advances of image recognition based on deep convolutional neural networks, researches on object detection have been actively explored. In this paper, we proposed a lightweight model of the mask R-CNN, which has been most widely used for object detection, to efficiently predict location and shape of various objects on the road environment. Furthermore, feature maps are adaptively re-calibrated to improve the detection performance by applying an attention module to the neural network layer that plays different roles within the mask R-CNN. Various experimental results for real driving scenes demonstrate that the proposed method is able to maintain the high detection performance with significantly reduced network parameters.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1117-1123
• /
• 2021

Object recognition is to identify the location and class of a specific object by analyzing the given image when a specific image is input. One of the fields in which object recognition technology is actively applied in recent years is autonomous vehicles, and this paper describes the trend of image-based object recognition artificial intelligence technology in autonomous vehicles. The image-based object detection algorithm has recently been narrowed down to two methods (a single-step detection method and a two-step detection method), and we will analyze and organize them around this. The advantages and disadvantages of the two detection methods are analyzed and presented, and the YOLO/SSD algorithm belonging to the single-step detection method and the R-CNN/Faster R-CNN algorithm belonging to the two-step detection method are analyzed and described. This will allow the algorithms suitable for each object recognition application required for autonomous driving to be selectively selected and R&D.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.978-981
• /
• 2020

제품이나 부품의 잔존 수명을 정확하게 예측할 수 있다면 고장이나 중단으로 인한 손실을 방지하는 것이 가능해질 것이다. 제품의 잔존 수명은 시계열 데이터 분석을 통해 예측될 수 있으며, 최근에는 딥러닝을 이용한 잔존 수명 예측 연구가 활발하게 진행되고 있다. 본 연구에서 우리는 컴퓨터 기반 시스템의 주요 고장 요소가 되고 있는 하드디스크의 잔존 수명을 예측하는 문제에 1D CNN-LSTM 을 이용한 모델을 적용하고, RMSE 와 R-Square 값을 이용해 적용한 모델의 성능을 평가하였다.