• Proceedings of the Korea Contents Association Conference
• /
• 2011.05a
• /
• pp.83-84
• /
• 2011

초분광 영상은 기존의 다중분광 영상보다 많은 밴드를 통해 넓은 범위의 파장 영역에 대한 반사율을 담고 있는 고차원 데이터이다. 이와 같은 고차원 데이터를 기존의 R-Tree, X-Tree와 같은 다차원 색인 방법을 사용하게 되면 차원의 저주(Course of Dimensionality)라는 문제가 발생한다. 본 논문에서는 차원의 저주 문제를 해결하기 위해 피라미드 기법을 사용하여 초분광 영상 라이브러리의 색인을 구축하였다. 파라미드 기법은 D차원의 데이터를 2D차원의 피라미드에 사상하고, B+-트리를 이용하여 1차원적으로 색인하는 방법이다. 실험 결과 스펙트럼 매칭을 위한 영역질의 방법이 후보자 추출 시간, 데이터 접근 빈도 측면에서 순차적 접근 방법보다 좋은 성능을 나타냈다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.872-874
• /
• 2021

본 논문은 외형 특징을 사용하지 않는 효율적인 다중 물체 추적 방법을 제안한다. 본 논문의 목적은 다중 물체 추적 방법이 합성곱 신경망 등의 외형 특징을 사용하지 않고 순수한 모션 모델의 힘으로 도달할 수 있는 최대의 성능을 찾는 것이다. 많은 다중 물체 추적 방법들이 추적 대상들 간의 유사성을 파악하기 위해 외형 특징을 사용한다. 하지만 다양한 외형 특징들을 갖는 방법들은 기본 특징 추출 알고리즘이 다르고, 다중 추적의 성능 향상이 어느 부분으로부터 오는지 정확히 파악할 수 없다. 또한, 각각 다른 매칭 알고리즘과 특징 디자인은 서로 다른 알고리즘의 효과를 순수하게 비교할 수 없다. 이러한 관점에서, 본 연구에서는 어떠한 외형 특징을 사용하지 않고 명확하게 추적 알고리즘의 효율성을 비교할 수 있는 가이드라인을 제시한다. 외형 특징을 사용하지 않고도 실용적으로 사용 가능한 성능에 도달할 수 있음을 공인 MOT2016, MOT2016 데이터셋에 대한 실험을 통해 증명한다. 이러한 방법은 GPU 를 사용하지 않고 200 fps 이상의 높은 속도를 보여 실시간 속도를 요구하는 임베디드 시스템 상의 어플리케이션에 적합하다.

• Spatial Information Research
• /
• v.21 no.1
• /
• pp.87-100
• /
• 2013

Recently, the use of locational information is growing rapidly. GPS technology has been adopted generally for obtaining locational information in outdoor spaces. In the other hand, the researches on indoor positioning have been carried out applying WLAN, RFID or Bluetooth technology because of the multi-path interference of GPS signal caused by the physical obstacles such as walls or columns in buildings. However, such technologies for indoor positioning cost too much to build sensing infrastructure and compute-intensive processes are involved. Furthermore, the accuracy of location estimation is variable caused by interior structures in buildings. In this study, to make up for the limitations, descriptive data such as phone number, unique room numbers, or business names readily available in mixed-use buildings is used for extracting location information. Furthermore, during the process, a geocoding method using character matching is applied to this study enabling prompt location estimation and sublating the fluctuation of accuracy caused by interior structures. Based on the proposed method in this study, an architecture is designed, and three-dimensional viewer program is developed for the implementation of this study. Also, this research is quantitatively analyzed through match rate and processing time of proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.100-107
• /
• 2012

Recently the need for advanced security technologies are increasing as the occurrence of intelligent crime is growing fastly. Previous methods for face disguise detection are required for the improvement of accuracy in order to be put to practical use. In this paper, we propose a new disguise detection method using the template matching and Adaboost algorithm. The proposed system detects eyes based on multi-scale Gabor feature vector in the first stage, and uses template matching technique in oreder to increase the detection accuracy in the second stage. The template matching plays a role in determining whether or not the person of the captured image has sunglasses on. Adaboost algorithm is used to determine whether or not the person of the captured image wears a mask. Experimental results indicate that the proposed method is superior to the previous methods in the detection accuracy of disguise faces.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.6
• /
• pp.667-675
• /
• 2011

In this paper, we propose an automatic image-to-image registration between high resolution multi-sensor images. To do this, TerraSAR-X image was shifted according to the initial translation differences of the x and y directions between images estimated using Mutual Information method. After that, the Canny edge operator was applied to both images to extract linear features. These features were used to design a cost function that finds matching points based on the similarities of their locations and gradient orientations. For extracting large number of evenly distributed matching points, only one point within each regular grid constructed throughout the image was extracted to the final matching point pair. The model, which combined the piecewise linear function with the global affine transformation, was applied to increase the accuracy of the geometric correction, and the proposed method showed RMSE lower than 5m in all study sites.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.4
• /
• pp.607-616
• /
• 2014

Face recognition is a big challenge in surveillance system since different rotation angles of the face make the difficulty to recognize the face of the same person. This paper proposes a novel method to recognize face with different head poses by using 3D information of the face. Firstly, head pose estimation (estimation of different head pose angles) is accomplished by the POSIT algorithm. Then, 3D face image data is constructed by using head pose estimation. After that, 2D image and the constructed 3D face matching is performed. Face verification is accomplished by using commercial face recognition SDK. Performance evaluation of the proposed method indicates that the error range of head pose estimation is below 10 degree and the matching rate is about 95%.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.49-55
• /
• 2022

In this paper, we propose an obstacle detection method that can operate robustly even in external environmental factors such as weather. In particular, we propose an obstacle detection system that can accurately inform dangerous situations in AR through DB-based feature matching and RANSAC-based multiplane method. Since the approach to detecting obstacles based on images obtained by RGB cameras relies on images, the feature detection according to lighting is inaccurate, and it becomes difficult to detect obstacles because they are affected by lighting, natural light, or weather. In addition, it causes a large error in detecting obstacles on a number of planes generated due to complex terrain. To alleviate this problem, this paper efficiently and accurately detects obstacles regardless of lighting through DB-based feature matching. In addition, a criterion for classifying feature points is newly calculated by normalizing multiple planes to a single plane through RANSAC. As a result, the proposed method can efficiently detect obstacles regardless of lighting, natural light, and weather, and it is expected that it can be used to secure user safety because it can reliably detect surfaces in high and low or other terrains. In the proposed method, most of the experimental results on mobile devices reliably recognized indoor/outdoor obstacles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.1
• /
• pp.1-6
• /
• 2018

In this paper, we propose the method to eliminate repetitive processes for key-point detection on multi-scale image space. The proposed method detects key-points from the original image, and select a good key-points using the cluster filters, and create the key-point clusters. And it select reference objects by using direction angles of the key-point clusters, predict the scale of the original image by using the distributed distance ratio. It transform the scale of the reference image, and apply the detection of key-points to the transformed reference image. In the results of the experiment, the proposed method can be found to improve the key-points detection time by 75 % and 71 % compared to SIFT method and scaled ORB method using the multi-scale images.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.184-187
• /
• 2020

다중 지문 기계독해는 질문과 여러 개의 지문을 입력받고 입력된 지문들에서 추출된 정답 중에 하나의 정답을 출력하는 문제이다. 다중 지문 기계독해에서는 정답이 있을 단락을 선택하는 순위화 방법에 따라서 성능이 크게 달라질 수 있다. 본 논문에서는 단락 안에 정답이 있을 확률을 예측하는 단락 재순위화 모델과 선택된 단락에서 서술형 정답을 위한 세부적인 정답의 경계를 예측하는 세부 단락 선별 기법을 제안한다. 단락 순위화 모델 학습의 경우 모델 학습을 위해 각 단락의 출력에 softmax와 cross-entroy를 이용한 손실 값과 sigmoid와 평균 제곱 오차의 손실 값을 함께 학습하고 키워드 매칭을 함께 적용했을 때 KorQuAD 2.0의 개발셋에서 상위 1개 단락, 3개 단락, 5개 단락에서 각각 82.3%, 94.5%, 97.0%의 재현율을 보였다. 세부 단락 선별 모델의 경우 입력된 두 단락을 비교하는 duoBERT를 이용했을 때 KorQuAD 2.0의 개발셋에서 F1 83.0%의 성능을 보였다.

• Proceedings of the KIEE Conference
• /
• 2004.04a
• /
• pp.46-48
• /
• 2004

본 논문에서는 유한 요소법과 등가회로법을 이용하여 윤곽 진동형 압전 변압기의 특성을 해석하였으며 이를 통해 얻어진 결과를 기반으로 매칭 임피던스와 전기 및 기계적 결합 계수를 계산하였다. 전력 소자로서 사용되는 압전 변압기는 부하 등 특정 목적에 부합하는 정확한 설계가 필요하기 때문에 다중 목적 함수를 갖는 진화 전략을 이용하여 형상 최적화를 수행하였다.