• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.427-430
• /
• 2007

기존의 LVQ(Learning Vector Quantization) 방법을 이용하여 물체를 분류하면 데이터의 학습이 빠르고 연산량이 적어 실시간으로 물체를 분류할 수 있는 장점이 있다. 하지만 데이터의 훈련시 output neuron의 개수를 정확히 예측할 수 없고 output neuron의 개수에 따라 물체를 분류하는 정확도가 매우 달라질 수 있다. 그러므로 본 논문에서는 output neuron의 개수를 데이터의 특성에 맞게 결정해주는 알고리즘을 제시한다. DLVQ(Dynamic Learning Vector Quantization) 알고리즘은 승자로 결정된 가중치 벡터의 부류가 샘플 데이터의 부류와 같으면 업데이트하고 다르면 새로운 가중치 벡터로 생성한다. 제한한 알고리즘의 가장 다른 부분은 미리 output neuron의 개수를 정하는 것이 아니라 훈련 과정에서 동적으로 output neuron의 개수를 생성하는 것이다. 그리고 클러터의 구분 방법을 제시하여 사람, 차, 클러터를 구분할 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.62-65
• /
• 2003

We propose the Distance Communication System that is not only Making Distance Learning Contents but also controlling intellectual moving object. In order to make Distance Learning Contents (Video Contents), we must follow the motion of lecturer. In the former Systems and a person operates Video-Camera because it's not enough to follow the motion, In this research and we make the systems that can match the motion of lecturer naturally. The systems use Intelligent Space software and so the systems recognize lecturer's motion automatically and order Pan/Tilt-Type Camera to follow the motion. And we made possible to operate an intellectual moving object with application of this system.

• Journal of Multimedia Information System
• /
• v.7 no.3
• /
• pp.205-214
• /
• 2020

Crime has become one of the major problems in modern society. Even though visual surveillances through closed-circuit television (CCTV) is extensively used for solving crime, the number of crimes has not decreased. This is because there is insufficient workforce for performing 24-hour surveillance. In addition, CCTV surveillance by humans is not efficient for detecting dangerous situations owing to accuracy issues. In this paper, we propose the autonomous detection of dangerous situations in CCTV scenes using a deep learning model with relational inference. The main feature of the proposed method is that it can simultaneously perform object detection and relational inference to determine the danger of the situations captured by CCTV. This enables us to efficiently classify dangerous situations by inferring the relationship between detected objects (i.e., distance and position). Experimental results demonstrate that the proposed method outperforms existing methods in terms of the accuracy of image classification and the false alarm rate even when object detection accuracy is low.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.465-467
• /
• 1992

This paper shows 3D vision system based on halftone image analysis. Any halftone image has its own surface vector normal to surface patch. To classily the given 3D images, all the patch on 3D object are transformed to black/white halftone. First we extract the general learning patterns which represents required slopes and their attributes. And next we propose 3D segmentation by searching intensity, slope and density. Artificial neural network is found to be very suitable in this approach, because it has powerful learning quality and noise tolerant. In this study, 3D shape reconstruct using pyramidian model. Our results are evaluated to enhance the quality.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.41-44
• /
• 2020

In autonomous driving, object recognition based on machine learning is one of the core software technologies. In particular, the object recognition using deep learning becomes an essential element for autonomous driving software to operate. In this paper, we introduce a drivable area detection method based on Region-based CNN model to support autonomous driving. To effectively detect the drivable area, we used the BDD dataset for model training and demonstrated its effectiveness. As a result, our R-CNN model using BDD datasets showed interesting results in training and testing for detection of drivable areas.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.1
• /
• pp.21-26
• /
• 2016

Canine cataract is developed with aging and can cause the blindness or surgical treatment if not treated timely. The first observation must be made by pet owners but they do not have proper equipment and knowledge to see the abnormalities. In this paper, we propose an intelligent image processing method to extract canine cataract suspicious object from non-professional equipment such as ordinary digital camera and cellular phone photographs so that even casual owners of pet dog can make a pre-diagnosis of such a surgery-needed disease as soon as possible. The experiment shows that the proposed method is successful in most cases except the dog has similar colored hair to the color of cataract.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.297-298
• /
• 2019

본 논문에서는 드론용 오픈 소스 API를 이용하여 셀프 카메라 촬영이 가능한 드론용 앱을 설계한다. 특히, 딥러닝 기반의 YOLO 객체 탐지 기술을 적용하여 배경 속에서 사람을 탐지하여 개인 및 단체 사진 촬영이 가능하도록 설계한다. 개발하는 셀프 카메라 앱은 기체의 자동 회전 및 선회 기반 연속 촬영 기능을 포함하여 다양한 형태의 인물 사진 촬영이 가능하다. 개발된 앱 기술을 기반으로 선회 및 회전을 통한 경비 구역의 침입자 촬영을 위한 시스템 및 드론 제어 기술에 활용하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2444-2463
• /
• 2020

Significant detection of video can more rationally allocate computing resources and reduce the amount of computation to improve accuracy. Deep learning can extract the edge features of the image, providing technical support for video saliency. This paper proposes a new detection method. We combine the Convolutional Neural Network (CNN) and the Deep Bidirectional LSTM Network (DB-LSTM) to learn the spatio-temporal features by exploring the object motion information and object motion information to generate video. A continuous frame of significant images. We also analyzed the sample database and found that human attention and significant conversion are time-dependent, so we also considered the significance detection of video cross-frame. Finally, experiments show that our method is superior to other advanced methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1187-1194
• /
• 2020

We presented a method of deep quiz cropping for automatic construction of quiz pool in online quiz systems. The method detects question boxes and sunda boxes in images captured from test papers by a deep learning-based object detector, and makes pairs of question box and sunda box by the box coupling. We applied the deep quiz cropping to images captured from test papers and achieved successful results.