• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.719-725
• /
• 2007

In this paper, we present an audio-visual speech recognition system for noise-robust human-computer interaction. Unlike usual speech recognition systems, our system utilizes the visual signal containing speakers' lip movements along with the acoustic signal to obtain robust speech recognition performance against environmental noise. The procedures of acoustic speech processing, visual speech processing, and audio-visual integration are described in detail. Experimental results demonstrate the constructed system significantly enhances the recognition performance in noisy circumstances compared to acoustic-only recognition by using the complementary nature of the two signals.

• 로봇학회논문지
• /
• 제1권1호
• /
• pp.36-45
• /
• 2006

In this paper, we introduce visual contexts in terms of types and utilization methods for robust object recognition with intelligent mobile robots. One of the core technologies for intelligent robots is visual object recognition. Robust techniques are strongly required since there are many sources of visual variations such as geometric, photometric, and noise. For such requirements, we define spatial context, hierarchical context, and temporal context. According to object recognition domain, we can select such visual contexts. We also propose a unified framework which can utilize the whole contexts and validates it in real working environment. Finally, we also discuss the future research directions of object recognition technologies for intelligent robots.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.334-338
• /
• 2022

In visual simultaneous localization and mapping (vSLAM), the correct recognition of a place benefits in relocalization and improved map accuracy. However, its performance is significantly affected by the environmental conditions such as variation in light, viewpoints, seasons, and presence of dynamic objects. This research addresses the problem of feature occlusion caused by interference of dynamic objects leading to the poor performance of visual place recognition algorithm. To overcome the aforementioned problem, this research analyzes the role of scene semantics in correct detection of a place in challenging environments and presents a semantics aided visual place recognition method. Semantics being invariant to viewpoint changes and dynamic environment can improve the overall performance of the place matching method. The proposed method is evaluated on the two benchmark datasets with dynamic environment and seasonal changes. Experimental results show the improved performance of the visual place recognition method for vSLAM.

• 반도체디스플레이기술학회지
• /
• 제18권4호
• /
• pp.57-61
• /
• 2019

Nowadays, portable digital cameras such as smart phone cameras are being popularly used for entertainment and visual information recording. Given a database of geo-tagged images, a visual location recognition system can determine the place depicted in a query photo. One of the most common visual location recognition approaches is the bag-of-words method where local image features are clustered into visual words. In this paper, we propose a new bag-of-words-based visual location recognition algorithm using time-series streetview database. The proposed algorithm selects only a small subset of image features which will be used in image retrieval process. By reducing the number of features to be used, the proposed algorithm can reduce the memory requirement of the image database and accelerate the retrieval process.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권8호
• /
• pp.299-308
• /
• 2014

신체 동작, 얼굴 표정과 같이 아주 복잡한 생체 패턴을 인식하고 분류하는 인간의 능력을 모방한 정보처리 컴퓨팅 관련 연구가 최근 다수 등장하고 있다. 특히 컴퓨터비전 분야에서는 인간의 뛰어난 인지 능력 중 상황정보 없이 시각시퀀스에서 동작을 분류하는 기능을 통해 시공간적 패턴 코딩과 빠른 인식 방법을 이해하고자 한다. 본 연구는 비디오 시퀀스상의 동작인식에 생물학적 시각인지과정의 영향을 받은 생체 기반 컴퓨터비전 모델을 제시하였다. 제안 모델은 이미지 시퀀스에서 동작을 검출하고 시각 패턴을 판별하는 데 생체 시각처리과정의 신경망 구조 단계를 반영하였다. 실험을 통해 생체 기반 동작인식 모델이 인간 시각인지 처리의 여러 가지 속성을 고려했을 뿐 아니라 기존 동작인식시스템에 비해 시간 정합성이 뛰어나며 시간 변화에 강건한 분류 능력을 보임을 알 수 있다. 제안 모델은 지능형 로봇 에이전트와 같은 생체 기반 시각정보처리 시스템 구축에 기여할 수 있다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.19-21
• /
• 2004

In many cases, human's visual recognition depends on contextual information. We need to use effective feature information for performing vigorous place recognition to illumination, noise, etc. In the existing cases that use edge and color, etc., visual recognition doesn't cope effectively with real environment. To solve this problem, using natural marker, we improve the efficiency of place recognition.

• 한국지능시스템학회논문지
• /
• 제20권3호
• /
• pp.348-355
• /
• 2010

음성 인식 기술의 발전에도 불구하고 잡음 환경하의 음성 인식은 여전히 어려운 분야이다. 이를 해결하기 위한 방안으로 음성 정보 이외에 시각 정보를 이용한 시각 음성인식에 대한 연구가 진행되고 있다. 하지만 시각 정보 또한 음성과 마찬가지로 주위 조명 환경이나 기타, 다른 요인에 따른 영상잡음이 존재하며, 이런 영상잡음은 시각 음성 인식의 성능 저하를 야기한다. 따라서 인식 성능 향상을 위해 시각 특징 파라미터를 어떻게 추출하느냐는 하나의 관심분야이다. 본 논문에서는 HMM기반 시각 음성인식의 인식 성능 향상을 위한 영상 기반 접근방법에 따른 시각 특징 파라미터의 추출 방법에 대하여 논하고 그에 따른 인식성능을 비교하였다. 실험을 위해 105명에 화자에 대한 62단어의 데이터베이스를 구축하고, 이를 이용하여 히스토그램 매칭, 입술 접기, 프레임 간 필터링 기법, 선형마스크, DCT, PCA 등을 적용하여 시각 특징 파라미터를 추출하였다. 실험결과, 제안된 방법에 의해 추출된 특징 파라미터를 인식기에 적용하였을 때의 인식 성능은 기본 파라미터에 비해 약21%의 성능 향상이 됨을 알 수 있다.

• 전기학회논문지
• /
• 제64권3호
• /
• pp.465-472
• /
• 2015

This paper presents a visual touch recognition for NUI(Natural User Interface) using Voronoi-tessellation algorithm. The proposed algorithms are three parts as follows: hand region extraction, hand feature point extraction, visual-touch recognition. To improve the robustness of hand region extraction, we propose RGB/HSI color model, Canny edge detection algorithm, and use of spatial frequency information. In addition, to improve the accuracy of the recognition of hand feature point extraction, we propose the use of Douglas Peucker algorithm, Also, to recognize the visual touch, we propose the use of the Voronoi-tessellation algorithm. Finally, we demonstrate the feasibility and applicability of the proposed algorithms through some experiments.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.25-32
• /
• 2003

This study deals with the investigation of recognition structure on architectural environment and reconstruction of it by artificial intelligence. To test the possibility of the reconstruction, recognition structure on architectural environment is analysed and each steps of the structure are matched with computational methods. Edge Detection and Neural Network were selected as matching methods to each steps of recognition process. Visual perception system established by selected methods is trained and tested, and the result of the system is compared with that of experiment of human. Assuming that the artificial system resembles the process of human recognition on architectural environment, does the system give similar response of human? The result shows that it is possible to establish artificial visual perception system giving similar response with that of human when it models after the recognition structure and process of human.

• 대한통합의학회지
• /
• 제10권1호
• /
• pp.119-128
• /
• 2022

Purpose : The purpose of this study was to examine the effects of applying occupational therapy that uses motion recognition on the physical self-efficacy, visual-motor integration ability, and play skills of children who have neurodevelopmental disorder before and after treatment. Methods : This The study chose 16 children with neurodevelopmental disorder as research subjects who were randomly and evenly allocated into an experimental group and a control group. The experiment followed a pretest-posttest design. As an intervention, the experimental group received motion recognition-based occupational therapy and a separate sensory integration program. The control group only participated in the separate sensory integration program. The eight-week experiment duration included 24 intervention sessions where the a 50-minute session was implemented three times a week for eight weeks. To compare the physical self-efficacy, visual-motor integration ability, and play skills before and after the intervention, measurement tools including the Physical self efficacy, Beery VMI-6, and Penn interactive peer play scale were used. All measured variables were analyzed and expressed as mean, standard deviation and percentage. Results : The motion recognition-based occupational therapy demonstrated a significant effect on improving the physical self-efficacy, visual-motor integration ability, and play skills of the experimental group. The intervention also caused a significant difference between the experimental group and control group in terms of the physical self-efficacy, visual-motor integration ability, and play skills. Conclusion : We confirmed the possibility motion recognition-based occupational therapy could be effective in improving the physical self-efficacy, visual-motor integration ability, and play skills for patients who have neurodevelopmental disorder. Based on the study result, further future studies are expected based on this study result that prove the application effect of the motion recognition-based occupational therapy using disabled and non- disabled children as subjects are expected in the future.