• 한국통신학회논문지
• /
• 제38A권1호
• /
• pp.1-9
• /
• 2013

본 논문에서는 CS-LBP (Center-Symmetric Local Binary Pattern) 특징과 공간 피라미드를 이용한 BoF (Bag of Features)를 생성하고 이를 랜덤 포레스트(Random Forest) 분류기에 적용하여 인간의 행동을 인식하는 알고리즘을 제안한다. BoF를 생성하기 위해 영상을 균일한 패치로 나누고, 각 패치 마다 CS-LBP 특징을 추출한다. 행동 분류 성능을 향상시키기 위해 패치들마다 추출한 특징벡터들에 대해 K-mean 클러스터링을 적용하여 코드 북을 생성한다. 본 논문에서는 영상의 지역적인 특성을 고려하기 위해 공간 피라미드 방법을 적용하고 각 공간 레벨에서 추출된 BoF에 대해 가중치를 적용하여 최종적으로 하나의 특징 벡터로 결합한다. 행동 분류를 위해 결정트리의 앙상블로 이루어진 랜덤 포레스트는 학습 단계에서 각 행동 클래스를 위한 분류 모델을 만든다. 가중 BoF가 적용된 랜덤 포레스트는 다양한 인간 행동 영상을 포함하고 있는 Standford Actions 40 데이터를 성공적으로 분류하였다. 또한 기존 방법에 비해 분류 성능이 유사하거나 우수하며, 한 장의 영상에 대해 빠른 인식속도를 보였다.

• ETRI Journal
• /
• 제24권5호
• /
• pp.373-380
• /
• 2002

This paper presents a new method for a visual cryptography scheme that uses phase masks and an interferometer. To encrypt a binary image, we divided it into an arbitrary number of slides and encrypted them using an XOR process with a random key or keys. The phase mask for each encrypted image was fabricated nuder the proposed phase-assignment rule. For decryption, phase masks were placed on any path of the Mach-Zehnder interferometer. Through optical experiments, we confirmed that a secret binary image that was sliced could be recovered by the proposed method.

• 전자공학회논문지
• /
• 제52권6호
• /
• pp.107-116
• /
• 2015

고성능 컴퓨터와 디지털 카메라의 보급으로 컴퓨터를 이용한 객체 탐지 및 추적은 컴퓨터 비전의 다양한 응용분야에서 중요한 문제로 대두 되고 있다. 또한, 지능형 자동화 감시 장치, 영상 분석 장치, 자동화된 로봇 분야 등에서 그 필요성이 점점 부각 되고 있다. 객체 추적은 카메라를 이용하여 움직이는 객체의 위치를 찾는 처리 과정을 의미 하며, 강건한 객체 추적을 위해서는 객체의 스케일, 형태 변화, 회전에 강건하고 정확한 객체의 위치를 파악할 수 있어야한다. 본 논문에서는 랜덤 포레스트를 이용한 강건한 객체 추적에 대한 알고리즘을 제안하였다. 정확한 객체의 위치를 찾기 위해 지역 공분산과 ZNCC (Zeros Mean Normalized Cross Correlation)를 사용하여 객체를 검출하고 검출된 객체를 5개의 부분으로 나누어 랜덤 포레스트로 객체가 잘 검출 되었는지 검증 한다. 검증된 객체 중 모델을 선택하여 객체 검출이 잘못 되었다고 판단된 경우 입력 모델을 변경하여 정확한 객체를 찾도록 하였다. 제안된 알고리즘과 기존의 알고리즘들을 비교 하였을 때 비교적 정확한 객체의 위치를 잘 찾아 가는 것을 확인하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.

• ETRI Journal
• /
• 제40권2호
• /
• pp.246-256
• /
• 2018

A spatial augmented reality (SAR) system enables a virtual image to be projected onto the surface of a real-world object and the user to intuitively control the image using a tangible interface. However, occlusions frequently occur, such as a sudden change in the lighting environment or the generation of obstacles. We propose a robust object tracker based on a multithreaded system, which can track an object robustly through occlusions. Our multithreaded tracker is divided into two threads: the detection thread detects distinctive features in a frame-to-frame manner, and the tracking thread tracks features periodically using an optical-flow-based tracking method. Consequently, although the speed of the detection thread is considerably slow, we achieve real-time performance owing to the multithreaded configuration. Moreover, the proposed outlier filtering automatically updates a random sample consensus distance threshold for eliminating outliers according to environmental changes. Experimental results show that our approach tracks an object robustly in real-time in an SAR environment where there are frequent occlusions occurring from augmented projection images.

• 대한원격탐사학회지
• /
• 제26권5호
• /
• pp.489-495
• /
• 2010

초분광 영상은 넓은 범위의 파장 영역의 유용한 정보를 많은 수의 밴드를 통해 취득한다. 하지만, 인접 밴드 간의 상관관계, 계산량, 노이즈로 인해 전처리없이 활용할 경우 부정확한 결과를 도출한다. 따라서 영상에서 노이즈 밴드 추출하여 제거하는 작업이 반드시 필요하다. 기존의 연구들은 영상 전체에 대한 특성치 만을 이용하였기 때문에 영상의 국지적 특성을 고려해야 한다. 본 연구에서는 Hyperion 영상을 대상으로 하였으며, 자료구조 기법 중 하나인 Quadtree와 이용하여 노이즈 밴드를 추출하였다. Quadtree 구조로 분할된 영역의 프랙탈 차원을 계산하고 프랙탈 차원의 분산을 이용하였다. Hyperion 영상에 존재하는 노이즈 종류 중 무작위 노이즈를 포함하고 있는 밴드 추출에 초점을 맞추었으며, 시각적으로 판단하여 작성한 참조자료와 비교하였다. 제안된 알고리즘 적용 결과 무작위 노이즈가 포함된 밴드 대부분이 추출되었으며, 영상에 관계없이 30개 이상의 노이즈 밴드를 제거할 수 있음을 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.48-54
• /
• 2019

This paper proposed a method of validation data augmentation for improving the grading accuracy of diabetic macular edema (DME) using deep learning. The data augmentation technique is basically applied in order to secure diversity of data by transforming one image to several images through random translation, rotation, scaling and reflection in preparation of input data of the deep neural network (DNN). In this paper, we apply this technique in the validation process of the trained DNN, and improve the grading accuracy by combining the classification results of the augmented images. To verify the effectiveness, 1,200 retinal images of Messidor dataset was divided into training and validation data at the ratio 7:3. By applying random augmentation to 359 validation data, $1.61{\pm}0.55%$ accuracy improvement was achieved in the case of six times augmentation (N=6). This simple method has shown that the accuracy can be improved in the N range from 2 to 6 with the correlation coefficient of 0.5667. Therefore, it is expected to help improve the diagnostic accuracy of DME with the grading information provided by the proposed DNN.

• Journal of information and communication convergence engineering
• /
• 제15권3호
• /
• pp.187-192
• /
• 2017

Autonomous driving vehicle research demands complex road and lane understanding such as lane departure warning, adaptive cruise control, lane keeping and centering, lane change and turn assist, and driving under complex road conditions. A fast and robust road lane detection subsystem is a basic but important building block for this type of research. In this paper, we propose a method that performs road lane detection from black box input. The proposed system applies Random Sample Consensus to find the best model of road lanes passing through divided regions of the input image under HSV color model. HSV color model is chosen since it explicitly separates chromaticity and luminosity and the narrower hue distribution greatly assists in later segmentation of the frames by limiting color saturation. The implemented method was successful in lane detection on real world on-board testing, exhibiting 86.21% accuracy with 4.3% standard deviation in real time.

• International journal of advanced smart convergence
• /
• 제10권1호
• /
• pp.216-224
• /
• 2021

Aim of this research was to classify forest types at Wando in Jeonnam Province and develop warm temperate forest management system with application of Remote Sensing and GIS. Another emphasis was given to the analysis of satellite images to compare forest type changes over 10 year periods from 2009 to 2019. We have accomplished this study by using ArcGIS Pro and ENVI. For this research, Landsat satellite images were obtained by means of terrestrial, airborne and satellite imagery. Based on the field survey data, all land uses and forest types were divided into 5 forest classes; Evergreen broad-leaved forest, Evergreen Coniferous forest, Deciduous broad-leaved forest, Mixed fores, and others. Supervised classification was carried out with a random forest classifier based on manually collected training polygons in ROI. Accuracy assessment of the different forest types and land-cover classifications was calculated based on the reference polygons. Comparison of forest changes over 10 year periods resulted in different vegetation biomass volumes, producing the loss of deciduous forests in 2019 probably due to the expansion of residential areas and rapid deforestation.

• 한국관광식음료학회지:관광식음료경영연구
• /
• 제12권1호
• /
• pp.79-110
• /
• 2001

Tourist Destination is based on tourism attractions. Components of Tourism attraction are included tourism resources, entertainment facilities, transportation, accommodation, infrastructure, assistance facilities & service, hospitality, information facilities & service, and retailing & service. Tourism resources of them is the key to determine destination development pattern, because tourism attraction that attract tourists is based on tourism resources. Therefore, there are need to study what is tourism attraction of destination at the view of tourists and what is destination development pattern based on it to develop tourism attraction that is able appeal tourists. The purpose of this study is to examine what effect of tourism attraction affects destination development pattern. This study defined Haeundae, Kwanganri, Songjung, Taejongdae in Pusan, Korea as research areas. Research data were collected from 300 respondents by a simple random sampling method. A final 284 usable questionaries were used for empirical analysis after data purification process. Reliability and validity of the scale on the tourism attraction, destination image, and facility needs have been evaluated using Cronbach $\alpha$, item-total correlations. This study analyzed the factors of the tourism attraction and destination images. The result obtained that tourism attraction is divided relaxation attraction, local activity attraction, culture . nature attraction and touring circuit attraction, and destination image is divided culture . urban attractiveness, touring attractiveness, local . stay attractiveness, convenience of travel and relativeness for destination investigated. ANOVA and regression (stepwise) were used to test hypotheses. Based on the results of hypotheses testing, major findings of the empirical research are as follow : 1. The tourism attraction and destination image are significantly different, but facility needs are not significantly by destinations (e. g. Haeundae, Kwanganri, Songjung, Taejongdae) . 2. Destination development pattern is a(fact by the tourism attraction in partial. In case of Haeundea, relaxation attraction take effect partially spa, history and marine/spa tourism. 3. The destination development pattern is influenced by the destination image in partial. In case of Kwanganri, the natural . activity attractiveness and urban tourism images have been found as influential factors that affect marine tourism. 4. The destination images are influenced the physical attributes in literature review, but the destination image are taken effect partially the tourism attraction in this study. 5. Destination development pattern are influenced by the tourism attraction and the destination image partially. This research has provided a variety of practical suggestions. Especially, it was suggested that the destination have appeal to tourists by strengthening attraction and improving weakness. Also, we need to specialize destination in same destination development pattern.