• Title/Summary/Keyword: Face it

Search Result 5,048, Processing Time 0.03 seconds

Vision-based Low-cost Walking Spatial Recognition Algorithm for the Safety of Blind People (시각장애인 안전을 위한 영상 기반 저비용 보행 공간 인지 알고리즘)

  • Sunghyun Kang;Sehun Lee;Junho Ahn
    • Journal of Internet Computing and Services
    • /
    • v.24 no.6
    • /
    • pp.81-89
    • /
    • 2023
  • In modern society, blind people face difficulties in navigating common environments such as sidewalks, elevators, and crosswalks. Research has been conducted to alleviate these inconveniences for the visually impaired through the use of visual and audio aids. However, such research often encounters limitations when it comes to practical implementation due to the high cost of wearable devices, high-performance CCTV systems, and voice sensors. In this paper, we propose an artificial intelligence fusion algorithm that utilizes low-cost video sensors integrated into smartphones to help blind people safely navigate their surroundings during walking. The proposed algorithm combines motion capture and object detection algorithms to detect moving people and various obstacles encountered during walking. We employed the MediaPipe library for motion capture to model and detect surrounding pedestrians during motion. Additionally, we used object detection algorithms to model and detect various obstacles that can occur during walking on sidewalks. Through experimentation, we validated the performance of the artificial intelligence fusion algorithm, achieving accuracy of 0.92, precision of 0.91, recall of 0.99, and an F1 score of 0.95. This research can assist blind people in navigating through obstacles such as bollards, shared scooters, and vehicles encountered during walking, thereby enhancing their mobility and safety.

A Research on Adversarial Example-based Passive Air Defense Method against Object Detectable AI Drone (객체인식 AI적용 드론에 대응할 수 있는 적대적 예제 기반 소극방공 기법 연구)

  • Simun Yuk;Hweerang Park;Taisuk Suh;Youngho Cho
    • Journal of Internet Computing and Services
    • /
    • v.24 no.6
    • /
    • pp.119-125
    • /
    • 2023
  • Through the Ukraine-Russia war, the military importance of drones is being reassessed, and North Korea has completed actual verification through a drone provocation towards South Korea at 2022. Furthermore, North Korea is actively integrating artificial intelligence (AI) technology into drones, highlighting the increasing threat posed by drones. In response, the Republic of Korea military has established Drone Operations Command(DOC) and implemented various drone defense systems. However, there is a concern that the efforts to enhance capabilities are disproportionately focused on striking systems, making it challenging to effectively counter swarm drone attacks. Particularly, Air Force bases located adjacent to urban areas face significant limitations in the use of traditional air defense weapons due to concerns about civilian casualties. Therefore, this study proposes a new passive air defense method that aims at disrupting the object detection capabilities of AI models to enhance the survivability of friendly aircraft against the threat posed by AI based swarm drones. Using laser-based adversarial examples, the study seeks to degrade the recognition accuracy of object recognition AI installed on enemy drones. Experimental results using synthetic images and precision-reduced models confirmed that the proposed method decreased the recognition accuracy of object recognition AI, which was initially approximately 95%, to around 0-15% after the application of the proposed method, thereby validating the effectiveness of the proposed method.

Study of Non Pressure and Pressure Foam of Bio-based Polymer Containing Blend (바이오 기반 폴리머가 포함된 블렌드의 상압 및 가압 발포 연구)

  • Dong-Hun Han;Young-Min Kim;Danbi Lee;Seongho Son;Geon-hee Seo;Hanseong Kim
    • Composites Research
    • /
    • v.36 no.5
    • /
    • pp.297-302
    • /
    • 2023
  • There are several methods for shaping foams, but the most commonly used methods involve the use of resin mixed with a foaming agent, which is then foamed under high temperature and pressure in the case of compression foaming, or foamed under high temperature without applying pressure in the case of atmospheric foaming. The polymers used for foaming require design and analysis of optimal foaming conditions in order to achieve foaming under ambient pressure. Environmentally friendly bio-based polymers face challenges when it comes to foaming on their own, which has led to ongoing research in blending them with resins capable of traditional foam production. This study investigates changes in the characteristics of bio-based polymer-EVA blend foams based on variations in the content of bio-based polymers and explores the optimal foaming conditions according to crosslinking. The correlation between foaming characteristics and mechanical properties of the foams was examined. Through this research, we gained insights into how the content of bio-based polymers affects the properties of foams containing bio-based polymers and identified differences between ambient pressure and high-pressure foaming processes. Additionally, the feasibility of commercializing bio-based polymer-EVA composite foams was confirmed.

The Use of Generative AI Technologies in Electronic Records Management and Archival Information Service (전자기록관리 업무 및 기록정보서비스에서의 생성형 AI 기술 활용)

  • Yoona Kang;Hyo-Jung Oh
    • Journal of Korean Society of Archives and Records Management
    • /
    • v.23 no.4
    • /
    • pp.179-200
    • /
    • 2023
  • Records management institutions in Korea generally face a situation where they lack the workforce to manage the vast amount of electronic records. If electronic records management tasks and archival information services can be automated and intelligentized, the workload can be reduced and the service satisfaction of users can be improved. Therefore, this study proposes to utilize "generative AI" technology in records management practice. To achieve this, the study first examined previous research that aimed to intelligently automate various tasks in the field of records management. The fundamental concepts of generative AI were subsequently outlined, and domestic cases of generative AI applications were investigated. Next, the scope of applying generative AI to the field of records management was defined, and specific utilization strategies were proposed based on this. Regarding the strategies, the effectiveness was verified by presenting results from applying commercial generative AI services or citing examples from other fields. Lastly, the benefits and implications of using generative AI technology in the field of records management, as well as limitations that must be addressed in advance, were presented. This study holds significance in that it identified tasks within the field of records management where generative AI technology can be integrated and proposed effective utilization strategies tailored to those tasks.

Research and improvement of image analysis and bar code and QR recognition technology for the development of visually impaired applications (시각장애인 애플리케이션 개발을 위한 이미지 분석과 바코드, QR 인식 기술의 연구 및 개선)

  • MinSeok Cho;MinKi Yoon;MinSu Seo;YoungHoon Hwang;Hyun Woo;WonWhoi Huh
    • The Journal of the Convergence on Culture Technology
    • /
    • v.9 no.6
    • /
    • pp.861-866
    • /
    • 2023
  • Individuals with visual impairments face difficulties in accessing accurate information about medical services and medications, making it challenging for them to ensure proper medication intake. While there are healthcare laws addressing this issue, there is a lack of standardized solutions, and not all over-the-counter medications are covered. Therefore, we have undertaken the design of a mobile application that utilizes image recognition technology, barcode scanning, and QR code recognition to provide guidance on how to take over-the-counter medications, filling the existing gaps in the knowledge of visually impaired individuals. Currently available applications for individuals with visual impairments allow them to access information about medications. However, they still require the user to remember which specific medication they are taking, posing a significant challenge. In this research, we are optimizing the camera capture environment, user interface (UI), and user experience (UX) screens for image recognition, ensuring greater accessibility and convenience for visually impaired individuals. By implementing the findings from our research into the application, we aim to assist visually impaired individuals in acquiring the correct methods for taking over-the-counter medications.

A Study on the Concept Definition and Institutional Foundations of Local Forestry Using the Delphi Technique (델파이 기법을 적용한 지역임업 개념의 정의와 제도 기반에 관한 연구)

  • Ju Yeon Kim;Jae Hyun Kim
    • Journal of Korean Society of Forest Science
    • /
    • v.113 no.2
    • /
    • pp.239-258
    • /
    • 2024
  • In the face of complex crises such as a shrinking society, regional imbalance, and climate change, there is a need to seek sustainable development in local communities. In the forest sector, attempts are being made to link forest resources with local industries. However, the current support system, which is centered on the central government, has limitations in achieving sustainable forest management. On the other hand, the international community is actively promoting a shift in systems by introducing the concept of local forestry, which emphasizes local initiatives to achieve sustainable forest management. However, in the Republic of Korea, the concept of local forestry is still unclear, which hinders the promotion of a paradigm shift. In this paper, we applied the Delphi technique to conduct three surveys of 29 academics, administrators, and field experts in the Republic of Korea. The aim was to define the concept of local forestry that is suitable for domestic conditions and identify institutional measures to establish and revitalize it. The results showed that local forestry can be defined as a broad concept that is both consultative and systemic in nature and that an institutional approach that supports actors and their activities is necessary to revitalize local forestry.

A study of measures to improve the system for the construction of deep tunnels in urban area (도심지 대심도 터널 건설을 위한 제도개선 방안 연구)

  • Hoonki Moon;Joon-Shik Moon;Jongho Shin
    • Journal of Korean Tunnelling and Underground Space Association
    • /
    • v.25 no.6
    • /
    • pp.469-478
    • /
    • 2023
  • The deep tunnel in urban area is a future-oriented construction plan that allows the above-ground space to be used as an eco-friendly park and transportation infrastructure to be constructed in the underground space. However, tunnel construction is often depicted as to cause ground collapse in some media and movies. In fact, while the construction of a deep tunnel in the urban area is underway, the project face with difficulties due to opposition complaints from residents near the route. In this study, we sought to identify perceptions on deep space development and citizen concerns through a public opinion survey regarding deep tunnels. By analyzing laws relevant with the promotion of deep tunnel construction, we reviewed the possibility of public engagement at each stage of the construction and investigated separated surface rights related to compensation for underground space. Through the results of the public opinion survey, it was identified that the concerns of citizens were problems that current technology could solve. Citizen's concerns were improved into a system that confirmed the stability of tunnel construction through public participation, and improvement measures were presented to encourage cooperation from those concerned regarding the establishment of divided superficies.

Development and Research of MMA Waterproof Coating and Waterproof System for Concrete Civil Structures (콘크리트 토목구조물 교면용 MMA 도막방수재 및 교면방수 시스템의 개발 연구)

  • Chul-Woo Lim;Sang-Ho Ji;Ki-Won An
    • Journal of the Korean Recycled Construction Resources Institute
    • /
    • v.12 no.2
    • /
    • pp.128-134
    • /
    • 2024
  • Asphalt-based waterproofing materials for bridge decks face issues such as softening or liquefaction of the material during the process of pouring hot asphalt concrete on top of the waterproofing layer. This leads to instability and reduced thickness of the waterproofing layer. To address these problems, new solutions beyond the existing materials, including the development and adoption of new materials, are required. Therefore, this study investigates the properties of MMA(Methyl Methacrylate) coating waterproofing material, which meets the basic physical properties for bridge deck waterproofing. We examined the overall quality standards in a system where the substrate concrete, waterproofing material, and paving layer are integrated. The study confirmed the applicability of MMA coating waterproofing material on bridge decks. The results indicate that a stable application of MMA coating waterproofing material for civil engineering structures' bridge decks can be achieved with a mix ratio of hard MMA resin : soft MMA resin : powder = 6 : 34 : 60. Additionally, when using emulsified asphalt with hardening characteristics for the adhesion between the dissimilar materials of MMA waterproofing and asphalt concrete, it is expected to meet the minimum quality standards of the Ministry of Land, Infrastructure, and Transport's 'Guidelines for Asphalt Concrete Pavement Construction (2021.07)'.

The Impact of Nomad Physical Activity Through Online Videos of Active Seniors on Physical Self-Perception and Successful Aging (엑티브시니어의 온라인 동영상을 통한 노마드 체육활동이 신체적자기지각과 성공적 노화에 미치는 영향)

  • Hye-young Hwang;Soo-Jin Seo;Hyun-Kyoung Kim;Hey-Jin Kim;Heung-Tae Kim
    • Journal of Industrial Convergence
    • /
    • v.22 no.6
    • /
    • pp.81-88
    • /
    • 2024
  • The purpose of this study is to provide academic basic data by identifying the effects of active seniors' online video physical activity on physical self-perception and successful aging. In order to achieve the purpose of this study, 10 active seniors in D city were selected, and after receiving consent to participate in online video physical activity, it was divided into pre and post, and from March 14 to April 22, 2022, Kakao Talk group chat was opened to watch online physical activity videos during the 12th session, download 2 videos a week, and exercise from Monday to Friday. To solve the research problem, frequency analysis and paired t-test were conducted using the SPSS Ver20.0 statistical program. As a result, first, as a result of analyzing the pre- and post-tests of physical self-perception through physical activity of active seniors, all of face satisfaction, body satisfaction, change in physical strength, and change in disease increased on average. Second, as a result of pre- and post-analysis of active seniors' successful aging through physical activity, acceptance of others, orientation toward self-fulfillment, self-acceptance, and satisfaction with children increased, but autonomous life and active participation in life decreased. Through these results, in the COVID-19 period, when activities were restricted due to social distancing, active seniors' online video physical activity has a positive effect on physical self-perception and successful aging, and various programs that can be active on their own should be developed in the future.

A Study on Water Demand Forecasting Methods Applicable to Developing Country (개발도상국에 적용 가능한 물수요 예측 방법 연구)

  • Sung-Uk Kim;Kye-Won Jun;Wan-Seop Pi;Jong-Ho Choi
    • Journal of Korean Society of Disaster and Security
    • /
    • v.16 no.4
    • /
    • pp.75-84
    • /
    • 2023
  • Many developing countries face challenges in estimating long-term discharge due to the lack of hydrological data for water supply planning, making it difficult to establish a rational water supply plan for decision-making on water distribution. The study area, the Bandung region in Indonesia, is experiencing rapid urbanization and population concentration, leading to a severe shortage of freshwater. The absence of water reservoir prediction methods has resulted in a water supply rate of approximately 20%. In this study, we aimed to propose an approach for predicting water reservoirs in developing countries by analyzing water safety and potential water supply using the MODSIM (Modified SIMYLD) network model. To assess the suitability of the MODSIM model, we applied the unit hydrograph method to calculate long-term discharge based on 19 years of discharge data (2002-2020) from the Pataruman observation station. The analysis confirmed alignment with the existing monthly optimal operation curve. The analysis of power plant capacity revealed a difference of approximately 0.30% to 0.50%, and the water intake safety at the Pataruman point showed 1.64% for Q95% flow and 0.47% for Q355 flow higher. Operational efficiency, compared to the existing reservoir optimal operation curve, was measured at around 1%, confirming the potential of using the MODSIM network model for water supply evaluation and the need for water supply facilities.