• ETRI Journal
• /
• v.45 no.5
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• Journal of Korea Multimedia Society
• /
• v.23 no.6
• /
• pp.792-801
• /
• 2020

Today, the media environment has changed dramatically with the development of Internet transmission technology, computer performance, and various media production technologies. In particular, video content is widely used every day through mobile device or computer connected to the Internet. In addition, the ability to produce video content today is more important than ever, as the use of video content is also increasing in the area of information delivery and communication over the Internet. In this study, it was developed a liberal education curriculum in universities for the production of video content. The developed curriculum was composed of a combination of an online curriculum for theory and an offline curriculum for practicum. In the online curriculum, a 54 DOOR contents were developed to allow students to learn the theoretical knowledge and basic making techniques related to the production of video content. In an offline 15-week practicum curriculum, it covered the practical training contents of video content production that should be acquired every week. This developed liberal education curriculum aims to give non-major students in universities the opportunity to learn the technology of producing video content and to foster the ability to communicate in the media environment by using the video content produced.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.783-792
• /
• 2022

Versatile Video Coding (VVC) is the latest video coding standard, which had been developed by the Joint Video Experts Team (JVET) of ITU-T Video Coding Experts Group (VCEG) and ISO/IEC Moving Picture Experts Group (MPEG) in 2020. Although VVC can provide powerful coding performance, it requires tremendous computational complexity to determine the optimal block structures during the encoding process. In this paper, we propose a fast ternary tree decision method using two neural networks with 7 nodes as input vector based on the multi-layer perceptron structure, names STH-NN and STV-NN. As a training result of neural network, the STH-NN and STV-NN achieved accuracies of 85% and 91%, respectively. Experimental results show that the proposed method reduces the encoding complexity up to 25% with unnoticeable coding loss compared to the VVC test model (VTM).

• Journal of Korean Academy of Nursing
• /
• v.46 no.1
• /
• pp.128-139
• /
• 2016

Purpose: This study was designed to evaluate the effects of an individual breast-feeding promotion program to address breast-feeding knowledge, attitude, method and rate of practice for married immigrant women. Methods: A non-equivalent control group quasi-experimental design was used (experimental group=16, control group=17). The intervention consisted of 3 phases: (1) Within 2 hours of delivery - individual breast-feeding training through video/verbal/practical training education and demonstration (2) After 1~2 days - group training using video, model doll, and breast models (3) After 7 days - family visit, counseling, retraining and reinforcement training. The data were analyzed using non-parametric tests with the SPSS program. Results: Married immigrant women who participated in the individual breast-feeding program scored high in knowledge, attitude, method and rate of practice compared to the control group. Conclusion: The results indicate that the individual breast-feeding program is very effective in increasing breast-feeding knowledge, attitude, method and rate of practicing breast feeding for married immigrant women. So, nurses are encouraged to aggressively utilize individual breast-feeding programs to help married immigrant women, who are exposed to vulnerability due to various situations.

• Journal of the Korean Society of Physical Medicine
• /
• v.14 no.1
• /
• pp.7-14
• /
• 2019

PURPOSE: This study examined the effects of observing a self-video or a video of another person performing balance and gait training, followed by actual performance of the observed movements on the balance and walking ability of chronic stroke patients. METHODS: Thirty patients, who had experienced a stroke and were admitted to S rehabilitation hospital for treatment, were selected randomly and divided into three groups with 10 patients each: self-action observation (SAO) group, other-action observation (OAO) group, and treadmill walking training (TWT) group. The training program was conducted five times per week for four weeks. The GAITRite system, 10 m walking test, and timed up and go test were performed to measure the subjects' gait and balance ability. RESULTS: The velocity, cadence, double support, and stride length were increased significantly in the SAO and OAO groups (p<.05) but the T group showed no significant changes; no significant difference was observed among the groups (p >.05). The 10MWT decreased significantly in the OAO group (p<.05), but there were no significant changes in the SAO and T groups, and no significant difference was observed among the groups (p>.05). The TUG decreased significantly in the SAO and OAO groups (p<.05), but there were no significant changes in the T group, and no significant difference was observed among the groups (p>.05). CONCLUSION: The self or other action observation training helps improve the balance and gait ability.

• Journal of the Korean Society of Physical Medicine
• /
• v.11 no.1
• /
• pp.133-140
• /
• 2016

PURPOSE: This study's aim was to investigate the effects of an action observational training in subactue stroke patients with moderate impairment. METHODS: 22 participants (men=13, women=9) with hemiparesis were randomly assigned to action observation training group or task-oriented training group. Patients in both group underwent a patient-specific multidisciplinary rehabilitation program. Participants in the action observation group (mean age, $62.78{\pm}9.85$) were asked to watch the video scene, in the knowledge that they would then attempt to perform the same movement task after watching. The control group (mean age, $61.49{\pm}8.64$) practiced the same tasks, without watching the video. To evaluate upper limb function, the upper extremity part of the Fugl-Meyer Assessment upper extremity and the Box and Block Test were used. The modified Barthel index was used to assess ADLs, and the modified Ashworth scale were used to assess spasticity in the upper extremity. RESULTS: The action observational training group exhibited greater changes in the Fugl-Meyer assessment upper extremity (P<0.05; 95% CI, 0.929 - 6.403), the Box and Block test (P<0.05; 95% CI, 0.086 - 5.913), and the modified Barthel index (P<0.01; 95% CI, 2.483 - 12.627) between groups. And the modified Ashworth scale (P>0.05; 95% CI, -0.402 to 0.624) did not show significantly different between groups. CONCLUSION: These findings suggest that action observational training may be more helpful to improve upper-extremity function than physical training only in subactue patients with moderate impairment after stroke.

• The Journal of the Korea Contents Association
• /
• v.21 no.5
• /
• pp.499-507
• /
• 2021

This study compares the educational effect using real equipment, virtual reality, and video to improve the educational and training effect of the army and verifies which method of education is excellent. The Army has made a lot of efforts to realize the actual training environment, however, it is increasingly difficult to provide the actual training environment because of 1) restrictions on securing training sites and urbanization, 2) deepening conflicts with the people, and 3) difficulties in acquiring defense budget. To resolve these issues, the use of virtual reality(VR) has the advantage to experience actual battlefield indirectly and could save budget by training in a virtual battlefield environment. In particular, in the case of dangerous or expensive weapons systems, is further required. Hence this paper studies how effective virtual reality is compared to the actual weapons system. virtual reality(VR) education is less effective than actual equipment education, but it is higher than video education. Based on this research result, it will be used as a basic data for the analysis of educational effects based in virtual reality(VR).

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.287-293
• /
• 2023

With the rapid development of domestic and international over-the-top markets, a large amount of video content is being created. As the volume of video content increases, consumers tend to increasingly check data concerning the videos before watching them. To address this demand, video summaries in the form of plot descriptions, thumbnails, posters, and other formats are provided to consumers. This study proposes an approach that automatically generates posters to effectively convey video content while reducing the cost of video summarization. In the automatic generation of posters, face recognition and clustering are used to gather and classify character data, and keyframes from the video are extracted to learn the overall atmosphere of the video. This study used the facial data of the characters and keyframes as training data and employed technologies such as DreamBooth, a text-to-image generation model, to automatically generate video posters. This process significantly reduces the time and cost of video-poster production.

• The Korean Journal of Emergency Medical Services
• /
• v.15 no.3
• /
• pp.5-17
• /
• 2011

purpose : The purpose of this study was to analyze the effect of basic life support performance by video simulation training. Methods : The subjects in this study consisted of 24 persons of experimental group and 24 persons of control group in freshmen and sophomore EMT students. The data were collected from September 1 to 30, 2010. Results : 1. Hypothesis one: experimental group is meaningful higher than control group at the operation point (p<0.05) of adult/infant's basic life support for one person. In subcategory that identifying breath, artificial respiration, pulse rate, 30 compressions, Ability to perform all the processes, the experimental group showed statistically higher score (p<0.05) than control group, and sequence from checking reaction to keeping airway management isn't statistically significant difference between experimental group and control. 2. Hypothesis two: In the hypothesis, the experimental group's point of adult basic life support by two persons and use of Automated External Defibrillator is good in experimental group than control group's point(p<0.05). As the result of researching 11 contents of check list about adult basic life support by two persons and Automated External Defibrillator(AED), by dividing into 7 subcategories, every subcategory shows that the experimental group is significant higher than control group(p<0.05). 3. Hypothesis three: In the hypothesis, the experimental group gets higher point of infant basic life support by one or two persons than the control group (p<0.05). As the results of researching 15 contents of check list about infant basic life support by one or two persons, by dividing into 8 subcategories, the experimental group is statistically meaningful higher (p<0.05) than the control group in process of keeping airway, indentifying breathing, identifying pulse, 30 compressions, Ability to perform all the processes. There isn't statistically significant difference between the groups in process of checking reaction, reporting 119, and artificial respiration by giving 2 breaths(p<0.05). Conclusion : As summarizing the results, the group, receiving using video, gets higher points of knowledge of basic life support and operating skill than the general educated group. It is found that the Video simulation training could be effective, because of these positive effects to improve clinical working performance of students, who participate in the department of Emergency Medical Technology.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.391-400
• /
• 2017

The purpose of this study was investigated the effect of orofacial training video program using smart device on oral cavity structure and function, diadochokinetic rate in acute stroke patients with dysarthria. Present study participated in fourteen acute stroke patients with dysarthria. All subjects assigned that randomized each seven patients in experimental and control group. Subjects of two groups received conventional rehabilitation therapy for 4 weeks. Experimental group performed additionally that orofacial training video program using smart device, supervised under caregivers, during 30 min/day. The outcome measures were the oral cavity structure and function of subscale for KOMSE(: Korean Oro-motor Mechanism Screening Examination), AMR(: Alternating Motion Rate), SMR(: Sequential Motion Rate). In results, Both group showed significant improvements after intervention in all assessments(p<.05). In comparison of change between two groups, experimental group showed significant improvements than control group in oral cavity function, /p ə/ and /tə/ of AMR(p<.05). We suggested that orofacial training video program using smart device expected to positive effects the improvements of oral cavity and articulator function in acute stroke patients with dysarthria.