• 문화기술의 융합
• /
• 제10권1호
• /
• pp.517-524
• /
• 2024

ChatGPT와 같은 생성형 AI는 21세기의 인간과 기계 간 상호작용에 새로운 패러다임을 제시했다. 이러한 기술의 발전이 다양한 분야에 빠르게 퍼져나가면서, AI와 꽤 멀리 떨어져 있다고 생각되었던 예술 분야에서도 AI가 어떤 역할을 할 수 있는지에 대한 연구가 활발히 진행되고 있다. 이에 본 연구는 제 4차 산업혁명의 시대에 시각예술 교육에서 생성형 AI의 활용 가능성을 탐구하고자 한다. 경북에 위치한 4년제 대학에서 진행된 실증연구는 창의적 융합모듈 수업에 참여한 70명의 학생들을 중심으로, AI와 시각예술 분야에서 협업의 영향, 그 중에서도 전공, 학년, 성별에 따른 차이점을 분석했다. 결과적으로, AI와 함께하는 시각예술 창작 활동이 학생들의 창의성과 디지털 미디어 리터러시에 긍정적인 영향을 미치는 것을 확인하며, 이를 기반으로 더욱 효과적인 교육 전략과 방향 모색에 관해 제언한다.

• 정보과학회 논문지
• /
• 제45권1호
• /
• pp.30-35
• /
• 2018

GuessWhat?!은 질문자와 답변자로 구성된 두 플레이어가 이미지를 보고 질문자에게 비밀로 감추어진 정답 물체에 대해 예/아니오/잘 모르겠음 셋 중 하나로 묻고 답하며, 정답 물체를 추려 나가는 문제이다. GuessWhat?!은 최근 컴퓨터 비전과 인공지능 대화 시스템의 테스트베드로서 컴퓨터 비전과 인공지능 학계의 많은 관심을 받았다. 본 논문에서, 우리는 GuessWhat?! 게임 프레임워크가 가지는 특성에 대해 논의한다. 더 나아가, 우리는 제안된 틀을 기반으로 GuessWhat?!의 간단한 solution을 제안한다. 사람이 평균 4~5개 정도의 질문을 통하여 맞추는 이 문제에 대하여, 우리가 제안한 방법은 2개의 질문만으로 기존 딥러닝 기반 기술의 성능을 상회하는 성능을 보이며, 5개의 질문이 허용되면 인간 수준의 성능을 능가한다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권11호
• /
• pp.1126-1130
• /
• 2010

차세대 IT유망 교육 분야로 지능로봇 관련 연구가 활발하게 진행되고 있다. 지능로봇은 실세계의 인간 세계와 가장 근접한 환경을 많이 고려하고 있기 때문에 인간의 행위 혹은 판단 능력을 기능으로 제공할 수 있어야 한다. 이와 같은 이유로 최근 로봇 교육은 다양한 하드웨어 형태의 로봇뿐만 아니라, 많은 기능을 포함한 서비스 컴포넌트 아키텍처 형태의 소프트웨어 로봇 개발 연구가 진행되고 있다. 따라서 본 논문에서는 RDS를 이용한 창의적 문제해결 학습방법에 관하여 제안한다. RDS는 소프트웨어 모듈로서 지능로봇을 제어하거나 프로그램하기 위한 소프트웨어 도구이다. 지능로봇 통합 개발 표준화를 고려한 컴포넌트 프레임워크를 활용하여 다양한 지능로봇의 형태와 여러 환경을 3차원 공간의 시각적 시뮬레이션 환경으로 제공하고 교육시간과 적은 비용으로 지능로봇 실험 환경을 제공할 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 춘계학술대회 및 임시총회
• /
• pp.187-190
• /
• 2002

인간의 두뇌에서는 갖가지 다양한 형태의 입력들을 이용하여 동시에 여러 가지의 판단, 추론 및 기억 등의 기능을 수행한다 이러한 이유로 인간 두뇌는 거대한 지능형 정보처리기라고 할 수 있다 현재 정보처리 메커니즘은 다양한 형태로 발달되고 있지만 그 중에서도 지능형 정보처리 메커니즘으로는 소프트 컴퓨팅 기법을 응용한 것이 대부분이다. 본 논문에서는 소프트 컴퓨팅 기법을 이용하여 두뇌에서의 시각, 청각의 정보처리 과정을 하나의 구조로 모델링하고자 한다. 시각에서의 정보와 청각에서의 정보는 각기 다른 모듈에서 처리되는 방식을 취하고 있으며, 최종적으로 두 감각 정보를 이용한 처리가 가능하도록 모듈형태의 전체적인 구조를 지니고 있다. 상이한 두 가지의 정보를 동시에 처리하는 과정을 모델링함으로써 복잡한 문제의 해결 및 다양한 경우에 대한 고려를 수행하여 인간 두뇌 모델링의 기초를 마련하고자 한다.

• 전자통신동향분석
• /
• 제33권4호
• /
• pp.43-53
• /
• 2018

As face recognition (FR) has been well studied over the past decades, FR technology has been applied to many real-world applications such as surveillance and biometric systems. However, in the real-world scenarios, FR performances have been known to be significantly degraded owing to variations in face images, such as the pose, illumination, and low-resolution. Recently, visual intelligence technology has been rapidly growing owing to advances in deep learning, which has also improved the FR performance. Furthermore, the FR performance based on deep learning has been reported to surpass the performance level of human perception. In this article, we discuss deep-learning based high-performance FR technologies in terms of representative deep-learning based FR architectures and recent FR algorithms robust to face image variations (i.e., pose-robust FR, illumination-robust FR, and video FR). In addition, we investigate big face image datasets widely adopted for performance evaluations of the most recent deep-learning based FR algorithms.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• 패션비즈니스
• /
• 제27권4호
• /
• pp.141-162
• /
• 2023

With the prospect that integrating creative AI in the fashion design field will become more visible, this study considered the case of creative fashion design development through Human-AI Co-creation (HAIC). Methodologically, this research encompasses a literature review and empirical investigations. In the literature review, the fashion design and creative HAIC processes, and the possibilities of integrating AI in fashion design were considered. In the empirical study, based on the case analysis of generating fashion design through HAIC, the HAIC type according to the role and interaction method, and characteristics of humans and AI was considered, and the HAIC process for fashion design was derived. The results of this study are summarized as follows. First, HAIC types in fashion design are divided into four types: AI-driven passive HAIC, human-driven passive HAIC, flexible interaction-based HAIC, and integrated interaction-based value creation HAIC. Second, the stages of the HAIC process for creative fashion design can be broadly divided into semantic data integration, visual ideation, design creation and expansion, design presentation, and design/manufacturing solution and UX platform creation. Third, in fashion design, HAIC contributes to human ability, enhancement of creativity, achievement of efficient workflow, and creation of new values. This research suggests that HAIC has the potential to revolutionize the fashion design industry by facilitating collaboration between humans and AI; consequently, enhancing creativity, and improving the efficiency of the design process. It also offers a framework for understanding the different types of HAIC and the stages involved in the creative fashion design process.

• 지능정보연구
• /
• 제6권2호
• /
• pp.29-40
• /
• 2000

Process planning (selection and ordering of processes) and material selection for product manufacturing are two key things determined before taking full-scale manufacturing. Knowledge on product design. material characteristics, processes, time and cost all-together are mutually related and should be considered concurrently. Due to the complexity of problem, human experts have got only one of the feasilbe solutions with their field knowledge and experiences. We propose a hierarchical expert system framework of knowledge representation and reasoning in order to overcome the complexity. Manufacturing processes have inherently hierarchical relationships, from top level processes to bottom level operation processes. Process plan of one level is posted in process blackboard and used for lower level process planning. Process information on blackboard is also used to adjust the process plan in order to resolve the dead-end or inconsistency situation during reasoning. Decision variables for process, material, tool, time and cost are represented as object frames, and their relationships are represented as constraints and rules. Constraints are for relationship among variables such as compatibility, numerical inequality etc. Rules are for causal relationships among variables to reflect human expert\`s knowledge such as process precedence. CRSP(Constraint and Rule Satisfaction Problem) approach is adopted in order to obtain solution to satisfy both constraints and rules. The trade-off procedure gives user chances to see the impact of change of important variables such as material, cost, time and helps to determine the preferred solution. We developed the prototype system using visual C++ MFC, UNIK, and UNlK-CRSP on PC.

• 제어로봇시스템학회논문지
• /
• 제22권11호
• /
• pp.877-882
• /
• 2016

Disaster robots have accepted tele-operation in order to share the intelligence of human operators and robot systems. Virtual wall is one of the tele-operation technology to support recognition of human operator. If the virtual wall can block the robot from dangers, the operator will feel comfortable and can concentrate on fundamental missions. In this paper, we proposes and compares three methods for virtual wall visualization in tele-operation using 3D reconstruction. First is a virtual wall visualized only with edges. A wall filled with transparent color is the second method. Finally, third method is a texture-mapped virtual wall. In the experiments, we discuss their merits and demerits in view of robot tele-operation.

• 국제초고층학회논문집
• /
• 제9권4호
• /
• pp.351-360
• /
• 2020

Monitoring civil structures periodically is necessary for ensuring the fitness of the structures. Cracks on inner and outer surfaces of the building plays a vital role in indicating the health of the building. Conventionally, human visual inspection techniques were carried up to human reachable altitudes. Monitoring of high rise infrastructures cannot be done using this primitive method. Also, there is a necessity for more accurate prediction of cracks on building surfaces for ensuring the health and safety of the building. The proposed research focused on developing an efficient crack classification model using Transfer Learning enabled EfficientNet (TL-EN) architecture. Though many other pre-trained models were available for crack classification, they rely on more number of training parameters for better accuracy. The TL-EN model attained an accuracy of 0.99 with less number of parameters on large dataset. A bench marked METU dataset with 40000 images were used to test and validate the proposed model. The surfaces of high rise buildings were investigated using vision enabled Unmanned Arial Vehicles (UAV). These UAV is fabricated with TL-EN model schema for capturing and analyzing the real time streaming video of building surfaces.