• 로봇학회논문지
• /
• 제14권1호
• /
• pp.1-7
• /
• 2019

Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.218-221
• /
• 2019

본 논문은 최근 MPEG-I 에서 논의되고 있는 전방위 6 자유도 영상의 가상시점 합성의 기존 공개 소프트웨어의 문제점 해결방안을 제안한다. 참조시점을 사용하여 합성된 가상시점의 영상을 대상으로 묶음 조정(bundle adjustment) 개념의 딥 러닝을 적용하여 영상 간 시공간적 품질 차이를 낮춘다. 실험에 따르면 중간시점 영상 합성 후 같은 시간적 특성을 같은 묶음을 MF-CNN (Multi-Frame Convolutional Neural Networks)에 적용함으로써 단순 VVS2.0 의 합성 결과 대비 평균 공간적으로 0.34dB, 시간적으로 0.81dB의 성능 향상을 제공하였다.

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.129-134
• /
• 2024

Object Detection is an emerging technology in the field of Computer Vision and Image Processing that deals with detecting objects of a particular class in digital images. It has considered being one of the complicated and challenging tasks in computer vision. Earlier several machine learning-based approaches like SIFT (Scale-invariant feature transform) and HOG (Histogram of oriented gradients) are widely used to classify objects in an image. These approaches use the Support vector machine for classification. The biggest challenges with these approaches are that they are computationally intensive for use in real-time applications, and these methods do not work well with massive datasets. To overcome these challenges, we implemented a Deep Learning based approach Convolutional Neural Network (CNN) in this paper. The Proposed approach provides accurate results in detecting objects in an image by the area of object highlighted in a Bounding Box along with its accuracy.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.235-238
• /
• 2019

In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

• ETRI Journal
• /
• 제43권4호
• /
• pp.684-693
• /
• 2021

This paper presents a low-cost two-stage approximate multiplier for bfloat16 (brain floating-point) data processing. For cost-efficient approximate multiplication, the first stage implements Mitchell's algorithm that performs the approximate multiplication using only two adders. The second stage adopts the exact multiplication to compensate for the error from the first stage by multiplying error terms and adding its truncated result to the final output. In our design, the low-cost multiplications in both stages can reduce hardware costs significantly and provide low relative errors by compensating for the error from the first stage. We apply our approximate multiplier to the convolutional neural network (CNN) inferences, which shows small accuracy drops with well-known pre-trained models for the ImageNet database. Therefore, our design allows low-cost CNN inference systems with high test accuracy.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.83-87
• /
• 2021

By the increase of internet usage, communicating online became an everyday thing. Thereby various people have experienced profanity by anonymous users. Nowadays lots of studies tried to solve this problem using artificial intelligence, but most of the solutions were for non-real time situations. In this paper, we propose a Telegram plugin that detects swear words using word2vec, and an algorithm to find the target of the sentence. We vectorized the input sentence to find connections with other similar words, then inputted the value to the pre-trained CNN (Convolutional Neural Network) model to detect any swears. For target recognition we proposed a sequential algorithm based on KoNLPY.

• 디지털산업정보학회논문지
• /
• 제19권4호
• /
• pp.127-136
• /
• 2023

Many research results on the traffic enforcement of illegal driving of twowheeled motor vehicles using license plate recognition are introduced. Deep learning convolutional neural networks can be used for character and word recognition of license plates because of better generalization capability compared to traditional Backpropagation neural networks. In the plates of twowheeled motor vehicles, the interdependent government and city words are included. If we implement the mutually independent word recognizers using error correction rules for two word recognition results, efficient license plate recognition results can be derived. The CPU based convolutional neural network without library under real time processing has an advantage of low cost real application compared to GPU based convolutional neural network with library. In this paper twowheeled motor vehicle license plate recognition algorithm is introduced using CPU based deep-learning convolutional neural network. The experimental results show that the proposed plate recognizer has 96.2% success rate for outdoor twowheeled motor vehicle images in real time.

• International journal of advanced smart convergence
• /
• 제7권1호
• /
• pp.42-47
• /
• 2018

Recently, as the demand for limited resources continues to rise and problems of resource depletion rise worldwide, the importance of renewable energy is gradually increasing. In order to solve these problems, various methods such as energy conservation and alternative energy development have been suggested, and biogas, which can utilize the gas produced from biomass as fuel, is also receiving attention as the next generation of innovative renewable energy. New and renewable energy using biogas is an energy production method that is expected to be possible in large scale because it can supply energy with high efficiency in compliance with energy supply method of recycling conventional resources. In order to more efficiently produce and manage these biogas, a biogas plant has emerged. In recent years, a large number of biogas plants have been installed and operated in various locations. Organic wastes corresponding to biogas production resources in a biogas plant exist in a wide variety of types, and each of the incoming raw materials is processed in different processes. Because such a process is required, the case where the biogas plant process is inefficiently operated is continuously occurring, and the economic cost consumed for the operation of the biogas production relative to the generated biogas production is further increased. In order to solve such problems, various attempts such as process analysis and feedback based on the feedstock have been continued but it is a passive method and very limited to operate a medium/large scale biogas plant. In this paper, we propose "CNN-based production yield prediction algorithm for increasing process efficiency of biogas plant" for efficient operation of biogas plant process. Based on CNN-based production yield forecasting, which is one of the deep-leaning technologies, it enables mechanical analysis of the process operation process and provides a solution for optimal process operation due to process-related accumulated data analyzed by the automated process.

• 한국재난정보학회 논문집
• /
• 제18권3호
• /
• pp.433-443
• /
• 2022

연구목적: 본 논문에서는 스마트 디바이스의 높은 보급률을 활용하여 근감소증을 추정 및 예측하는 딥러닝 알고리즘을 제안과 연구를 수행한다. 연구방법: 딥러닝 학습을 위해 스마트 디바이스에 내장된 관성센서를 활용하여 실험 데이터를 수집하였다. 데이터를 수집하는 테스트용 어플리케이션 구현하여 '정상'과 '비정상'걸음과 '달리기', '낙상', '스쿼트' 자세의 5 가지 상태를 구분하여 데이터를 수집하였다. 연구결과: LSTM, CNN, RNN model 사용 시 예측 정확도를 분석했고 CNN-LSTM 융합형 모델을 활용하여 이진분류 정확도 99.87%, 다중 분류 92.30%의 정확도를 보였다. 결론: 근감소증이 있는 사람의 경우 걸음걸이의 이상이 생긴다는 점에 착안하여 스마트 디바이스를 활용한 연구를 진행하였다. 본 연구를 활용하여 근감소증으로 인해 생기는 재난안전을 강화 할 수 있을 것이다.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권3호
• /
• pp.217-227
• /
• 2022

In order to provide a location-based services regardless of indoor or outdoor space, it is important to provide position information of the terminal regardless of location. Among the wireless/mobile communication resources used for this purpose, Long Term Evolution (LTE) signal is a representative infrastructure that can overcome spatial limitations, but the positioning method based on the location of the base station has a disadvantage in that the accuracy is low. Therefore, a fingerprinting technique, which is a pattern recognition technology, has been widely used. The simplest yet widely applied algorithm among Fingerprint positioning technologies is k-Nearest Neighbors (kNN). However, in the kNN algorithm, it is difficult to find the optimal K value with the lowest positioning error for each location to be estimated, so it is generally fixed to an appropriate K value and used. Since the optimal K value cannot be applied to each estimated location, therefore, there is a problem in that the accuracy of the overall estimated location information is lowered. Considering this problem, this paper proposes a technique for adaptively varying the K value by using a Convolutional Neural Network (CNN) model among Artificial Neural Network (ANN) techniques. First, by using the signal information of the measured values obtained in the service area, an image is created according to the Physical Cell Identity (PCI) and Band combination, and an answer label for supervised learning is created. Then, the structure of the CNN is modeled to classify K values through the image information of the measurements. The performance of the proposed technique is verified based on actual data measured in the testbed. As a result, it can be seen that the proposed technique improves the positioning performance compared to using a fixed K value.