• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.6
• /
• pp.42-57
• /
• 2022

This study aims to create a basic model for classifying the activity photos that urban park users shared on social media using Deep Learning through Artificial Intelligence. Regarding the social media data, photos related to urban parks were collected through a Naver search, were collected, and used for the classification model. Based on the indicators of Naturalness, Potential Attraction, and Activity, which can be used to evaluate the characteristics of urban parks, 21 classification categories were created. Urban park photos shared on Naver were collected by category, and annotated datasets were created. A custom CNN model and a transfer learning model utilizing a CNN pre-trained on the collected photo datasets were designed and subsequently analyzed. As a result of the study, the Xception transfer learning model, which demonstrated the best performance, was selected as the urban park user activity image classification model and evaluated through several evaluation indicators. This study is meaningful in that it has built AI as an index that can evaluate the characteristics of urban parks by using user-shared photos on social media. The classification model using Deep Learning mitigates the limitations of manual classification, and it can efficiently classify large amounts of urban park photos. So, it can be said to be a useful method that can be used for the monitoring and management of city parks in the future.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.21-30
• /
• 2005

In general, the robust estimation method is well known for a good statistical estimator that is insensitive to small departures from the idealized assumptions for which the estimation is optimized. While there are many existing robust estimation techniques that have been proposed in the literature, two main techniques used in computer vision are M-estimators and least-median of squares (LMS). Among these. we utilized the M-estimators since they are known to provide an optimal estimation of affine motion parameters. The M-estimators have higher statistical efficiency but tolerate much lower percentages of outliers unless properly initialized. To resolve these problems, we proposed an adaptive M-estimators algorithm that effectively separates outliers from non-outliers and estimate affine model parameters, using a continuous sigmoid weight function. The experimental results show the superiority of our method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.525-531
• /
• 2019

Efforts to utilize human gestures to effectively implement a more natural and interactive interface between humans and computers have been ongoing in recent years. In this paper, we propose a new algorithm that accepts consecutive three-dimensional (3D) depth images, defines a hand model, and robustly extracts the human hand region based on six palm joints and 15 finger joints. Then, the 3D depth images are adaptively binarized to exclude non-interest areas, such as the background, and accurately extracts only the hand of the person, which is the area of interest. Experimental results show that the presented algorithm detects only the human hand region 2.4% more accurately than the existing method. The hand region extraction algorithm proposed in this paper is expected to be useful in various practical applications related to computer vision and image processing, such as gesture recognition, virtual reality implementation, 3D motion games, and sign recognition.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.9
• /
• pp.818-826
• /
• 2015

This paper presents a novel methodology for estimating vehicle ego-motion, i.e. tri-axis linear velocities and angular velocities by using stereo vision sensor and 2G1Y sensor (longitudinal acceleration, lateral acceleration, and yaw rate). The estimated ego-motion information can be utilized to predict future ego-path and improve the accuracy of 3D coordinate of obstacle by compensating for disturbance from vehicle movement representatively for collision avoidance system. For the purpose of incorporating vehicle dynamic characteristics into ego-motion estimation, the state evolution model of Kalman filter has been augmented with lateral vehicle dynamics and the vanishing point estimation has been also taken into account because the optical flow radiates from a vanishing point which might be varied due to vehicle pitch motion. Experimental results based on real-world data have shown the effectiveness of the proposed methodology in view of accuracy.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.25-33
• /
• 2023

The purpose of this study is to evaluate the impact of intermediate features on FER performance. To achieve this objective, intermediate features were extracted from the input images at specific layers (FM1~FM4) of the pre-trained network (Resnet-18). These extracted intermediate features and original images were used as inputs to the vision transformer (ViT), and the FER performance was compared. As a result, when using a single image as input, using intermediate features extracted from FM2 yielded the best performance (training accuracy: 94.35%, testing accuracy: 75.51%). When using the original image as input, the training accuracy was 91.32% and the testing accuracy was 74.68%. However, when combining the original image with intermediate features as input, the best FER performance was achieved by combining the original image with FM2, FM3, and FM4 (training accuracy: 97.88%, testing accuracy: 79.21%). These results imply that incorporating intermediate features alongside the original image can lead to superior performance. The findings can be referenced and utilized when designing the preprocessing stages of a deep learning model in FER. By considering the effectiveness of using intermediate features, practitioners can make informed decisions to enhance the performance of FER systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.274-286
• /
• 2022

Multi-object tracking has been studied for a long time under computer vision and plays a critical role in applications such as autonomous driving and driving assistance. Multi-object tracking techniques generally consist of a detector that detects objects and a tracker that tracks the detected objects. Various publicly available datasets allow us to train a detector model without much effort. However, there are relatively few publicly available datasets for training a tracker model, and configuring own tracker datasets takes a long time compared to configuring detector datasets. Hence, the detector is often developed separately with a tracker module. However, the separated tracker should be adjusted whenever the former detector model is changed. This study proposes a system that can train a model that performs detection and tracking simultaneously using only the detector training datasets. In particular, a Siam network with augmentation is used to compose the detector and tracker. Experiments are conducted on public datasets to verify that the proposed algorithm can formulate a real-time multi-object tracker comparable to the state-of-the-art tracker models.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2009.11a
• /
• pp.109-112
• /
• 2009

Various environmental problems due to the rapid industralization and urbanization have been worsened as much as to threaten the environmental restitution of globe and become a critical international issue. Korean government presented the green growth as a new state vision for 60 years afterwards and is making efforts to solve the environmental problems. Daegu metropolitan city has faced various environmental problems including overpopulation of cities, traffic pollution, household wastes and green zone problem because of urbanization for the last decades. As such urbanism continues, the quality of residential environment is rapidly deteriorating and the intensive use of land leads to increase of building area raising the temperature of cities. Therefore there have been demands for the healthy, pleasant and satisfying residential environment and the improvement of residential environment and such recognition rises from society in full measure. Nevertheless the current residential complex concentrates only on raising the efficiency of land use. Related laws in the past(Daegu Metropolitan City, Urban Planning Municipal Ordinance as of October 10, 2003) tried to prepare a standard to segmentalize the building-to-land ratio, floor area ratio and regulations of number of floors vertically, but currently it is abolished and the regulations are becoming eased. The purpose of this study was to analyze the characteristics of the floating wind before and after the vertical segmentation of residential areas(Daegu Metropolitan City, Urban Planning Municipal Ordinance as of October 10, 2003) by using KLAM_21, a model that enables analysing and predicting the flow and generation of clod wind, and to present a plan to improve the quality of residential areas afterwards when developing building lot and re-developing housing areas.

• Journal of Korean Library and Information Science Society
• /
• v.47 no.3
• /
• pp.21-39
• /
• 2016

The objective of this study is to propose the operational organization and connective cooperation plan for the Daegu regional central library which will be completed in 2020. The vision of regional central library was presented as 'the library for the happiness of Daegu citizens and the cradle of knowledge and culture', and 10 core functions also proposed. In order to fulfill the roles as a regional central library, it has been suggested to maintain 5 departments including the department of administrative support, the department of library policy, the department of collection development, the department of information service, and the department of cooperative preservation. Lastly, it has also established the model of connective cooperation plans between other regional libraries and the regional central library as follows: the construction and operation of cooperative system, connective cooperation for the construction of Daegu collaborative repository, cooperative library system of ILL/DDS.

• Journal of the Korean association of regional geographers
• /
• v.23 no.2
• /
• pp.269-287
• /
• 2017

While Jeju Free International City was promoted to overcome the economic crisis and build a new national competitiveness in the era of globalization, its development vision as 'the hub city of Northeast Asian economy in the $21^{st}$ century' has not been realized. This paper argues that Jeju Free International City to aim for the 'ideal free market model', 'neoliberal space of exception', and 'a new testing ground for neoliberal deregulation policies' has failed due to worsening of socioeconomic and environmental contradictions, growing conflicts in local community, and the logic of equity enforced by the central government. To support this claim, this article reviews the theoretical discussions of special economic zones, examines the shifts in the development visions of Jeju Free International City, and analyzes how Jeju has become a space of exception with the introduction of various exceptional policies and spatial mechanisms.