• 로봇학회논문지
• /
• 제3권3호
• /
• pp.219-225
• /
• 2008

This study developed a surveillance robot for a ship. The developed robot consists of ultrasonic sensors, an actuator, a lighting fixture and a camera. The ultrasonic sensors are used to avoid collision with obstacles in the environment. The actuator is a servo motor system. The developed robot has four drive wheels for driving. The lighting fixture is used to guide the robot in a dark environment. To transmit an image, a camera with a pan moving and a tilt moving is equipped on the upper part of the robot. AdaBoost algorithm trained with 15 features, is used for face recognition. In order to evaluate the face recognition of the developed robot, experiments were performed.

• ETRI Journal
• /
• 제32권5호
• /
• pp.761-765
• /
• 2010

In this paper, we introduce an improved adaptive boosting (AdaBoost) classifier and its application, a disguised-face discriminator that discriminates between bare and disguised faces. The proposed classifier is based on an AdaBoost learning algorithm and regression technique. In the process, the lookup table of AdaBoost learning is utilized. The proposed method is verified on the captured images under several real environments. Experimental results and analysis show the proposed method has a higher and faster performance than other well-known methods.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.1020-1023
• /
• 2017

Viola와 Jones가 제안한 AdaBoost(Adaptive Boosting) 알고리즘은 기존의 물체 검출기에 비해 속도와 정확도 면에서 우수하여 실시간 물체 검출기로써 좋은 성능을 보인다. 하지만 여전히 많은 계산량 때문에 성능이 낮은 임베디드 환경에서는 실시간 검출에 대한 아쉬움이 있다. 본 논문에서는 계산량을 줄이기 위해 모션 검출을 통해 배경 영역을 제거하고 얼굴 영역을 추정한다. 제거된 배경 영역은 AdaBoost 알고리즘의 검출 과정에서 제외되며 추정된 얼굴 영역에 대해서만 검출을 하게 된다. 모션검출은 ${\Sigma}-{\Delta}$(Sigma-Delta) 배경 추정에 기반한 알고리즘을 사용한다.

• ETRI Journal
• /
• 제31권3호
• /
• pp.282-291
• /
• 2009

An online mean-shift object tracking algorithm, which consists of a learning stage and an estimation stage, is proposed in this work. The learning stage selects the features for tracking, and the estimation stage composes a likelihood image and applies the mean shift algorithm to it to track an object. The tracking performance depends on the quality of the likelihood image. We propose two schemes to generate and integrate likelihood images: one based on the discrete AdaBoost (DAB) and the other based on the real AdaBoost (RAB). The DAB scheme uses tuned feature values, whereas RAB estimates class probabilities, to select the features and generate the likelihood images. Experiment results show that the proposed algorithm provides more accurate and reliable tracking results than the conventional mean shift tracking algorithms.

• 한국통신학회논문지
• /
• 제18권5호
• /
• pp.695-707
• /
• 1993

Marked Petri Net(MPN) 모델은 최대 병행 활성화 랑데부 수에 따른 통신 복잡도를 분석할 수 있게 해준다. 그러나 이 모델은 시간과 확률 속성(Time and Probability characteristics)을 명시할 수 없음으로 통신 복잡도의 새로운 개념인 실행 시간 복잡도를 분석할 수 없다. 본 논문에서는 이러한 실행 시간 복잡도를 효율적으로 분석하기 위해 MPN에 새로운 제약 조건인 net 절감 법칙, 실행 시간, 그리고 확률 조건을 도입한 Ada Tasking Structure Nets(ATSN)을 제안한다. 끝으로 ATSN 모델을 이용하여 통신 복잡도의 분석 효과를 보인다.

• International Journal of Contents
• /
• 제7권3호
• /
• pp.60-64
• /
• 2011

Jane Campion's is a well-known film for a number of reasons, such as for being an Oscar winner, for having been helmed by an emerging director from New Zealand, and for having the reputation of being a feminist film. In this paper, the first scene of was chosen to examine the heroine Ada's language in terms of the gothic genre. Ada is a dumb woman who lives in the era of man's language. She represents the women's social position in the Victorian era but has her own and unique language for communicating with the outside world. The first scene of introduces Ada's own language, using her fingers. Her fingers speak for her all the time instead of her mouth, and there is someone who can understand what she wants to say when all others cannot. How the film depicts Ada's language and how the first scene well summarizes the film's core are examined herein.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2012년도 제45차 동계학술발표논문집 20권1호
• /
• pp.209-211
• /
• 2012

본 논문에서는 AdaBoost 알고리즘에서 약분류기(Weak Classifier)의 성능을 개선하기 위한 임계값 설정 방법을 제안한다. 일반적으로 약분류기에 사용되는 임계값은 특징들의 평균값을 많이 사용하지만 이는 특징들의 분포가 고려되지 않았기 때문에 분별력이 많이 떨어진다. 그러므로 각 특징들의 분포를 고려한 약분류기의 임계값 설정방법을 제안한다. 이는 얼굴에 대한 간단한 학습 및 테스트를 통하여 기존 방법에 비하여 더 나은 성능을 보임을 입증한다.

• 한국지능시스템학회논문지
• /
• 제23권2호
• /
• pp.166-171
• /
• 2013

The method proposed in this paper can improve the performance of the Boosting algorithm in machine learning. The proposed Boundary AdaBoost algorithm can make up for the weak points of Normal binary classifier using threshold boundary concepts. The new proposed boundary can be located near the threshold of the binary classifier. The proposed algorithm improves classification in areas where Normal binary classifier is weak. Thus, the optimal boundary final classifier can decrease error rates classified with more reasonable features. Finally, this paper derives the new algorithm's optimal solution, and it demonstrates how classifier accuracy can be improved using the proposed Boundary AdaBoost in a simulation experiment of pedestrian detection using 10-fold cross validation.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권2호
• /
• pp.143-148
• /
• 2012

This paper proposes a new method to improve performance of AdaBoost by using a distance weight function to increase the accuracy of its machine learning processes. The proposed distance weight algorithm improves classification in areas where the original binary classifier is weak. This paper derives the new algorithm's optimal solution, and it demonstrates how classifier accuracy can be improved using the proposed Distance Sensitive AdaBoost in a simulation experiment of pedestrian detection.

• 전기학회논문지
• /
• 제61권9호
• /
• pp.1336-1339
• /
• 2012

In this paper, we focus on solving the classification problem by using semisupervised learning strategy. Traditional classifiers are constructed based on labeled data in supervised learning. Labeled data, however, are often difficult, expensive or time consuming to obtain, as they require the efforts of experienced human annotators. Unlabeled data are significantly easier to obtain without human efforts. Thus, we use AdaBoost algorithm with SVM-KNN classifier to apply semisupervised learning problem and improve the classifier performance. Experimental results on both artificial and UCI data sets show that the proposed methodology can reduce the error rate.