• Journal of IKEEE
• /
• v.21 no.1
• /
• pp.92-95
• /
• 2017

In this paper, we proposed a way to improve function of small scale GP-GPU. Instead of using superscalar which increase scheduling-complexity, we suggested the application of simple core to maximize GP-GPU performance. Our studies also demonstrated that simplified Stream Processor is one of the way to achieve functional improvement in GP-GPU. In addition, we found that developing of optimal thread-assigning method in Warp Scheduler for specific application improves functional performance of GP-GPU. For examination of GP-GPU functional performance, we suggested the thread-assigning way which coordinated with Deep-Learning system; a part of Neural Network. As a result, we found that functional index in algorithm of Neural Network was increased to 90%, 98% compared with Intel CPU and ARM cortex-A15 4 core respectively.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.733-735
• /
• 2018

최근의 차량 주차관리 시설, 출입통제가 필요한 장소 그리고 도로 방범카메라를 통한 단속 등 다양한 곳에서 차량 번호판 자동 인식 기술들이 활용되고 있다. 하지만 현재 사용되고 있는 LPR(License Plate Recognition) 시스템에는 많은 장비와 비용이 들어간다는 큰 단점이 존재한다. 본 논문에서는 하나의 컴퓨터와 최소의 카메라를 가지고 할 수 있는 기계학습을 통한 영상처리를 제안하려 한다. 먼저 딥러닝 프레임워크 중 하나인 YOLO(You Only Look Once) [4]를 활용하여 자동차의 번호판 부분의 영역을 검출하고 Grayscale를 통해 햇빛 또는 조명 등의 영향을 감소시켜 번호판의 특징을 보존시킨다. 전처리 작업이 끝난 후 번호판에서 숫자를 인식 하는 부분에서는 k-NN(k-Nearest Neighbor) 알고리즘을 사용하였으며 한글 문자 인식부분은 Template Matching을 이용하였다. 제안한 알고리즘을 사용하여 기존 LPR 시스템에서 획득한 차량이미지를 대상으로 시뮬레이션 한 결과 좋은 결과를 얻을 수 있어 향후 연구 방향의 시스템 확장성의 가능성을 발견할 수 있었다.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.606-608
• /
• 2018

최근 CCTV나 블랙박스 등 멀티미디어 데이터를 생성해내는 장치의 사용이 늘어나고 있다. 이러한 대용량 멀티미디어 데이터가 증가함에 따라 사용자가 동영상과 같은 멀티미디어 데이터 내의 객체를 식별하기 위해서는 많은 시간을 할애하여 매뉴얼하게 일일이 찾아야 하는 한계점이 있다. 본 논문에서는 사용자가 동영상 및 이미지에서와 같은 멀티미디어 데이터에서 객체를 자동으로 식별할 수 있 수 있는 딥러닝 기반의 객체 식별 및 검색 모델을 제안한다. 제안하는 객체 식별 검색은 이미지 검색과 동영상 검색을 지원한다. 이미지 검색에서는 이미지에 존재하는 동일한 객체를 검색 대상 이미지들에서 객체를 식별하고, 이미지에 존재하는 객체를 검색하여 결과로 반환한다. 또한 동영상 검색에서는 동영상에서 검색하고자 하는 객체를 식별하고 객체가 출현하는 시간을 전처리과정을 통해 기록하며, 검색하고자 하는 동영상 내에 존재하는 객체의 검색이 가능하다. 따라서 사용자가 동영상에서 객체의 검색 시 키워드 검색이 가능하여 동영상을 모두 재생하서 객체를 식별해야 하는 번거로움을 해결할 수 있다.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.419-422
• /
• 2019

The recent increase in single-person households and family income has led to an increase in the number of pet owners. However, due to the owners' difficulty to communicate with them for 24 hours, pets, and especially dogs, tend to display unwanted behavior that can be harmful to themselves and their environment when left alone. Therefore, detecting those behaviors when the owner is absent is necessary to suppress them and prevent any damage. In this paper, we propose a camera-based system that detects a set of normal and unwanted behaviors using deep learning algorithms to monitor dogs when left alone at home. The frames collected from the camera are arranged into sequences of RGB frames and their corresponding optical flow sequences, and then features are extracted from each data flow using pre-trained VGG-16 models. The extracted features from each sequence are concatenated and input to a bi-directional LSTM network that classifies the dog action into one of the targeted classes. The experimental results show that our method achieves a good performance exceeding 0.9 in precision, recall and f-1 score.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.589-591
• /
• 2019

본 논문에서는 고도장비의 운용 및 정비를 위한 교육훈련 시스템 개발을 위해 자연어 처리와 딥러닝 기술을 이용하여 항공정비와 관련된 전문분야의 문서 분류가 가능한 방법을 제안하고자 한다. 문서 분류 모델의 개발을 위해 항공정비 교범을 텍스트 파일로 변환하여 총 4917개의 문서를 생성하였으며, 정비사 개인별 정비능력 관리(IMQC)를 기준으로 12개의 범주로 구분하였다. 수집된 문서는 전문분야의 문서인 점을 고려하여 전문용어 사전을 추가하였으며, KoNLPy를 이용하여 전처리를 수행하였다. 전문분야의 문서는 범주에 상관없이 문서 내용의 유사도가 매우 높은 특징을 가지고 있어, 특정 범주내에서 중요한 정도를 잘 표현 할 수 있는 TF-ICF를 이용하여 특징 추출을 하였다. 이후 합성곱 신경망(CNN)을 이용하여 특징 맵을 생성한 후 완전 결합 계층을 통하여 분류하였으며, 테스트 문서 983건을 분류한 결과 평균 73.6%의 분류성능을 보여주었다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.147-158
• /
• 2021

Versatile Video Coding (VVC) is the latest video coding standard developed by Joint Video Exploration Team (JVET). In VVC, the quadtree plus multi-type tree (QT+MTT) structure of coding unit (CU) partition is adopted, and its computational complexity is considerably high due to the brute-force search for recursive rate-distortion (RD) optimization. In this paper, we aim to reduce the time complexity of inter-picture prediction mode since the inter prediction accounts for a large portion of the total encoding time. The problem can be defined as classifying the split mode of each CU. To classify the split mode effectively, a novel convolutional neural network (CNN) called multi-level tree (MLT-CNN) architecture is introduced. For boosting classification performance, we utilize additional information including inter-picture information while training the CNN. The overall algorithm including the MLT-CNN inference process is implemented on VVC Test Model (VTM) 11.0. The CUs of size 128×128 can be the inputs of the CNN. The sequences are encoded at the random access (RA) configuration with five QP values {22, 27, 32, 37, 42}. The experimental results show that the proposed algorithm can reduce the computational complexity by 11.53% on average, and 26.14% for the maximum with an average 1.01% of the increase in Bjøntegaard delta bit rate (BDBR). Especially, the proposed method shows higher performance on the sequences of the A and B classes, reducing 9.81%~26.14% of encoding time with 0.95%~3.28% of the BDBR increase.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1131-1139
• /
• 2018

This paper proposes a method of recognition abandoned objects using convolutional neural networks. The method first detects an area for an abandoned object in image and, if there is a detected area, applies convolutional neural networks to that area to recognize which object is represented. Experiments were conducted through an application system that detects illegal trash dumping. The experiments result showed the area of abandoned object was detected efficiently. The detected areas enter the input of convolutional neural networks and are classified into whether it is a trash or not. To do this, I trained convolutional neural networks with my own trash dataset and open database. As a training result, I achieved high accuracy for the test set not included in the training set.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.904-919
• /
• 2019

Many security systems rely solely on solutions based on Artificial Intelligence, which are weak in nature. These security solutions can be easily manipulated by malicious users who can gain unlawful access. Some security systems suggest using fingerprint-based solutions, but they can be easily deceived by copying fingerprints with clay. Image-based security is undoubtedly easy to manipulate, but it is also a solution that does not require any special training on the part of the user. In this paper, we propose a multi-factor security framework that operates in a three-step process to authenticate the user. The motivation of the research lies in utilizing commonly available and inexpensive devices such as onsite CCTV cameras and smartphone camera and providing fully secure user authentication. We have used technologies such as Argon2 for hashing image features and physically unclonable identification for secure device-server communication. We also discuss the methodological workflow of the proposed multi-factor authentication framework. In addition, we present the service scenario of the proposed model. Finally, we analyze qualitatively the proposed model and compare it with state-of-the-art methods to evaluate the usability of the model in real-world applications.

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.131-142
• /
• 2021

Recently, there has been an active service that provides customized news to news subscribers. In this study, we intend to design a customized news service system through Deep Learning-based Social Network Service (SNS) activity analysis, applying real news and avoiding fake news. In other words, the core of this study is the study of delivery methods and delivery devices to provide customized news services based on analysis of users, SNS activities. First of all, this research method consists of a total of five steps. In the first stage, social network service site access records are received from user terminals, and in the second stage, SNS sites are searched based on SNS site access records received to obtain user profile information and user SNS activity information. In step 3, the user's propensity is analyzed based on user profile information and SNS activity information, and in step 4, user-tailored news is selected through news search based on user propensity analysis results. Finally, in step 5, custom news is sent to the user terminal. This study will be of great help to news service providers to increase the number of news subscribers.