• 센서학회지
• /
• 제23권1호
• /
• pp.46-50
• /
• 2014

In this paper, we report a novel algorithm based on phase displacement, which supplements conventional TOF methods for distance measurement using an ultrasonic wave. The proposed algorithm roughly measures the distance between the transmission part and the receiving part by using the initial TOF. Thereafter, the precise distance is determined by measuring the phase displacement value between the synchronizing transmission signal and the signal obtained at the receiving end. A distance measurement experiment using a micrometer was performed to verify the accuracy of the ultrasonic wave sensor system. We found that the mean errors from the one adopting the distance measurement algorithm based on phase displacement varied from a minimum of 0.03 mm to a maximum of 0.09 mm. In addition, the standard deviation varied from a minimum of 0.04 mm to a maximum of 0.07 mm, thus giving a precision of ${\pm}0.1$ mm.

• 한국지능시스템학회논문지
• /
• 제20권3호
• /
• pp.343-347
• /
• 2010

본 논문에서는 상관계수와 거리계수의 조합형 유사성 척도에 기반을 둔 효과적인 영상인식 방법을 제안하였다. 여기서 상관계수는 Pearson coefficient에 의한 통계적 유사성을 측정하기 위함이고, 거리계수는 city-block에 의한 공간적인 유사성을 측정하기 위함이다. 또한 영상사이의 전체 유사성은 각 영상이 가지는 특징사이의 유사성으로 계산되며, 영상의 특징은 PCA와 ICA로 각각 추출하였다. 제안된 방법을 40*50 픽셀의 960(30명*4표정*2조명*4포즈)개 다른 표정영상을 대상으로 실험한 결과, ICA 기반 조합형 척도를 이용하는 것이 PCA 기반 조합형 척도보다 우수한 인식률을 가지며, 또한 조명과 같은 주변 환경에도 강건한 인식성능이 있음을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.85-87
• /
• 2000

In pattern classification, the Bhattacharyya distance has been used as a class separability measure and provides useful information for feature selection and extraction. In this paper, we propose a method to predict the classification error for multimodal data based on the Bhattacharyya distance. In our approach, we first approximate the pdf of multimodal distribution with a Gaussian mixture model and find the bhattacharyya distance and classification error. Exprimental results showed that there is a strong relationship between the Bhattacharyya distance and the classification error for multimodal data.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권4호
• /
• pp.223-232
• /
• 2003

This paper presents a new method driving multiple robots to their goal position without collision. Each robot adjusts its motion based on the information on the goal location, velocity, and position of the robot and the velocity and position of the .other robots. To consider the movement of the robots in a work area, we adopt the concept of avoidability measure. The avoidability measure figures the degree of how easily a robot can avoid other robots considering the following factors: the distance from the robot to the other robots, velocity of the robot and the other robots. To implement the concept in moving robot avoidance, relative distance between the robots is derived. Our method combines the relative distance with an artificial potential field method. The proposed method is simulated for several cases. The results show that the proposed method steers robots to open space anticipating the approach of other robots. In contrast, the usual potential field method sometimes fails preventing collision or causes hasty motion, because it initiates avoidance motion later than the proposed method. The proposed method can be used to move robots in a robot soccer team to their appropriate position without collision as fast as possible.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1493-1503
• /
• 2018

We propose an object recognition system and experiential game contents using Kinect to maximize object recognition rate by utilizing underwater robots. we implement an ice hockey game based on object-aware interactive contents to validate the excellence of the proposed system. The object recognition system, which is a preprocessor module, is composed based on Kinect and OpenCV. Network sockets are utilized for object recognition communications between C/S. The problem of existing research, degradation of object recognition at long distance, is solved by combining the system development method suggested in the study. As a result of the performance evaluation, the underwater robot object recognized all target objects (90.49%) with 80% of accuracy from a 2m distance, revealing 42.46% of F-Measure. From a 2.5m distance, it recognized 82.87% of the target objects with 60.5% of accuracy, showing 34.96% of F-Measure. Finally, it recognized 98.50% of target objects with 59.4% of accuracy from a 3m distance, showing 37.04% of F-measure.

• 한국지능시스템학회논문지
• /
• 제15권7호
• /
• pp.789-793
• /
• 2005

구간치 퍼지집합은 Gorzalczan응(1983)과 Turken(1986)에 의해 처음 제의되었다. 이를 토대로 Wang과 Li는 구간치 퍼지수에 관한 연산으로 일반화하여 연구하였다. 최근에 홍(2002)는 왕과 리의 이론을 기만적분에 의해 구간치 퍼지집합상의 거리측도에 관한 연구를 하였다. 본 논문에서 우리는 일반측도와 관련된 리만적분 대신에 퍼지측도와 관련된 쇼케이적분을 이용한 구간치 퍼지수 상의 쇼케이 거리측도를 정의하고 이와 관련된 성질들을 조사하였다.

• 한국경영과학회지
• /
• 제32권1호
• /
• pp.125-136
• /
• 2007

The study on query relaxation which provides approximate answers has received attention. In recent years, some arguments have been made that semantic relationships are useful to present the relationships among data values and calculating the semantic distance between two data values can be used as a quantitative measure to express relative distance. The aim of this article is a hierarchical metricized knowledge abstraction (HiMKA) with an emphasis on combining data abstraction hierarchy and distance measure among data values. We propose the operations and the query relaxation algorithm appropriate to the HiMKA. With various experiments and comparison with other method, we show that the HiMKA is very useful for the quantified approximate query answering and our result is to offer a new methodological framework for query relaxation.

• International Journal of Contents
• /
• 제5권4호
• /
• pp.51-54
• /
• 2009

In huge video databases, the effective video content indexing method is required. While manual indexing is the most effective approach to this goal, it is slow and expensive. Thus automatic indexing is desirable and recently various indexing tools for video databases have been developed. For efficient video content indexing, the similarity measure is an important factor. This paper presents new similarity measures between frames and proposes a new algorithm to index video content using Kullback-Leibler distance defined between two histograms. Experimental results show that the proposed algorithm using Kullback-Leibler distance gives remarkable high accuracy ratios compared with several conventional algorithms to index video content.

• Journal of information and communication convergence engineering
• /
• 제13권2호
• /
• pp.74-80
• /
• 2015

In cognitive radios, spectrum sensing plays an important role in accurately detecting the presence or absence of a licensed user. However, the intervention of malicious users (MUs) degrades the performance of spectrum sensing. Such users manipulate the local results and send falsified data to the data fusion center; this process is called spectrum sensing data falsification (SSDF). Thus, MUs degrade the spectrum sensing performance and increase uncertainty issues. In this paper, we propose a method based on the Hausdorff distance and a similarity measure matrix to measure the difference between the normal user evidence and the malicious user evidence. In addition, we use the Dempster-Shafer theory to combine the sets of evidence from each normal user evidence. We compare the proposed method with the k-means and Jaccard distance methods for malicious user detection. Simulation results show that the proposed method is effective against an SSDF attack.

• 한국전자통신학회논문지
• /
• 제14권4호
• /
• pp.679-684
• /
• 2019

CAFFE 모델을 이용하여 클래스의 특정 종의 수량 측정하는 방법과 스테레오 비전을 이용하여 물체의 길이와 너비를 측정하는 방법을 제안한다. 물체의 너비를 구하는 방법은 좌측 센서와 우측 센서의 대상의 좌표 값을 비교하여 센서부터 물체까지의 거리를 계산한다. 그 후 거리와 영상 속의 대상의 길이를 구해 물체의 실제 길이의 근사 값을 계산한다.