• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.99-101
• /
• 2022

이상 행동을 탐지하는 딥러닝 기반 검지 시스템은 동영상 기반 데이터로부터 움직임을 보이는 객체를 추적하고 그 객체의 행동을 분석하여 정상적인 행동 범위를 벗어나는 패턴을 보이는 영역을 이상으로 탐지한다. 특히 생성적 적대 신경망(GAN)과 광학 흐름 추정(Optical flow estimation) 기법을 활용하여 움직임에 대한 특징 정보를 추출하고 이를 학습하여 행동 패턴에 대한 모델링을 수행한다. 모델 학습 및 테스트에 활용되는 데이터셋의 해상도가 낮거나 이상 행동을 표현하는 특징 정보가 부족할 경우 최종 모델 성능에 부정적 영향을 미치게 되며, 특히 광학 흐름이 표현하는 이동량 측면에서 차이가 크게 나지 않는 이상 객체의 경우 탐지가 정확하게 이뤄지지 않는다. 본 연구에서는 동영상 프레임에서 나타나는 객체의 평균 종횡비를 구하고 정상적인 비율을 벗어나는 객체에 대해서 이상 행동을 취하는 샘플로 처리하는 후처리단 모듈을 제안하여 최종적인 모델 성능을 향상시키는 방법을 고안한다.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.6
• /
• pp.23-32
• /
• 2005

Dolittle is a educational programming language that helps students learning principles and concepts of computer science with programming. Learning programming with robot improve learning achievements robot motivate to be interest with programming. However, Dolittle robot programming is a different from Dolittle programming in process of interpretation and execution mechanism. Therefore, students have virtually to learn two languages to control robot and it would reduce the worth of Dolittle as educational programming language. In order to solve this problem, we tried to Unify Dolittle and robot control language using parser that Dolittle program with turtle object convert robot program. But this try couldn't overcome completely this problem because attributes of turtle object is different from robot. In this research we unified Dolittle programming and Dolittle robot programming as a way of adding new robot object in dolittle standard object group. it would improve educational effect of learning programming with robot in Dolittle.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.1290-1293
• /
• 2021

Currently, blind people are experiencing a lot of inconvenience in their daily lives. In order to provide helpful service for the visually impaired, this study was carried out to make a new smart glasses that transmit information monitoring walking environment in real-time object recognition. In terms of object recognition, YOLOv4 was used as the artificial intelligence model. The objects, that should be identified during walking of the visually impaired, were selected, and the learning data was populated from them and re-learning of YOLOv4 was performed. As a result, the accuracy was average of 68% for all objects, but for essential objects (Person, Bus, Car, Traffic_light, Bicycle, Motorcycle) was measured to be 84%. In the future, it is necessary to secure the learning data in more various ways and conduct CNN learning with various parameters using darkflow rather than YOLOv4 to perform comparisons in the various ways.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.593-598
• /
• 2003

Machine learning organizes knowledge for efficient and accurate reuse. This paper is concerned with methods of concept learning from examples, which glean knowledge from a training set of preclassified ‘objects’. Ideally, training facilitates classification of novel, previously unseen objects. However, every learning system relies on processing and representation assumptions that may be detrimental under certain circumstances. We explore the biases of a well-known learning system, ID3, review improvements, and introduce some improvements of our own, each designed to yield accurate and pedagogically sound classification.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.651-660
• /
• 2013

Object oriented design brought up improvement of productivity and software quality by adopting some concepts such as inheritance and encapsulation. However, both the number of software's classes and object couplings are increasing as the software volume is becoming larger. The object coupling between classes is closely related with software complexity, and high complexity causes decreasing software quality. In order to solve the object coupling issue, IT-field researchers adopt a component based development and software quality metrics. The component based development requires explicit representation of dependencies between classes and the software quality metrics evaluates quality of software. As part of the research, we intend to gain a basic data that will be used on decomposing software. We focused on properties of the linkage between classes rather than previous studies evaluated and accumulated the qualities of individual classes. Our method exploits machine learning technique to analyze the properties of linkage and predict the strength of dependency between classes, as a new perspective on analyzing software property.

• Journal of The Korean Association of Information Education
• /
• v.7 no.2
• /
• pp.199-206
• /
• 2003

XML is becoming a new developing tool of web technology because of its ability of data management and flexibility in data presentation. So it's well researched that the reusability and integration with learning objects such as text, image, sound, video and plug-in programs of web contents in computer education. But the research for storing, extracting and integrating metadata about learning object was needed prior to implementing online learning system to integrate and manage it. Therefore this study propose a new method of using web service of DBMS for extracting learning object's metadata in database server which located in 3-tier system. To evaluate the efficiency of proposed method, The test server and two DBMSs(MS SQL Server 2000 and Oracle 9i) which have 30 metadata was implemented and the response time of it was measured. The response time of it was short, but in order to using this method the additional programming with SAX/DOM was necessary.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.