• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.

• 한국전문물리치료학회지
• /
• 제22권4호
• /
• pp.27-33
• /
• 2015

The purpose of this study was to find which spatiotemporal gait parameters gained from stroke patients could be predictive factors for the gait part of Tinetti Performance-Oriented Mobility Assessment (POMA-G). Two hundred forty-six stroke patients were recruited for this study. They participated in two assessments, the POMA-G and computerized spatiotemporal gait analysis. To analyze the relationship between the POMA-G and spatiotemporal parameters, we used Pearson's correlation coefficients. In addition, multiple linear regression analyses (stepwise method) were used to predict the spatiotemporal gait parameters that correlated most with the POMA-G. The results show that the gait velocity (r=.67, p<.01), cadence (r=.66, p<.01), step length of the affected side (r=.49, p<.01), step length of the non-affected side (r=.53, p<.01), swing percentage of the non-affected side (r=.47, p<.01), and single support percentage of the affected side (r=.53, p<.01) as well as the double support percentage of the non-affected side (r=-.42, p<.01) and the step-length asymmetry (r=-.64, p<.01) correlated with POMA-G. The gait velocity, step-length asymmetry, cadence, and single support percentage of the affected side explained 67%, 2%, 2%, and 1% of the variance in the POMA-G, respectively. In conclusion, gait velocity would be the most predictive factor for the POMA-G.

• 국제물리치료학회지
• /
• 제10권4호
• /
• pp.1873-1878
• /
• 2019

Background: Walking is a complex activity. The main components of walking include balance, coordination, and symmetrical posture. The characteristics of walking patterns of stroke patients include slow walking, measured by gait cycle and walking speed. This is an important factor that reflects post-stroke quality of life and walking ability. Objective: This study aimed to examine the effect of deep lumbar muscle stabilization exercise on the spatiotemporal walking ability of stroke patients. Design: Quasi-experial study Methods: The experiment was conducted 5 times per week for 4 weeks, with 30 minutes per session, on 10 subjects in the experimental group who performed the deep lumbar muscle stabilization exercise and 10 subjects in the control group who performed a regular exercise. Variables that represent the spatiotemporal walking ability (step length, stride length, step rate, and walking speed) were measured using GAITRrite before and after the experiment and were analyzed. Results: There was a significant difference in the pre- and post-exercise spatiotemporal walking ability between the two groups (p<.05). Furthermore, there was a significant difference in the step rate and walking speed between the two groups (p<.05). Conclusions: Deep lumbar muscle stabilization exercise is effective in improving the walking ability of stroke patients. Therefore, its application will help improve the spatiotemporal walking ability of stroke patients.

• 한국컴퓨터산업교육학회:학술대회논문집
• /
• 한국컴퓨터산업교육학회 2003년도 제4회 종합학술대회 논문집
• /
• pp.127-133
• /
• 2003

The data models which express all types of video information physically and logically. and the definition of spatiotemporal relationship of video data objects In This paper, we classifies meta-model for efficient management on spatiotemporal relationship between two objects in video image data, suggests meta-models based on Rambaugh's OMT technique, and expanded user model to apply the adaptive model, established from hyper-media or web agent to VOD. The proposed meta-model uses data's special physical feature: the effects of camera's and editing effects of shot, and 17 spatial relations on Allen's 13 temporal relations, topology and direction to include logical presentation of spatiotemporal relation for possible spatiotemporal reference and having unspecified applied mediocrity.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 KOBA 방송기술 워크샵 KOBA Broadcasting Technology Workshop
• /
• pp.29-34
• /
• 1999

We present a practical method for removing biotches and restoring their mission data. To detect blotches, we employ a robust approach of local analysis of spatiotemporal anisotropic brightness continuity Our approach uses first-order spatiotemporal directional derivatives to select the smoothest direction for each examined pixel, and puts out the incorruption probability that he examined pixel may not be corrupted by blotches. As the restoration filter, were employ a spatiotemporal fuzzy filter whose response is adaptively controlled according to a fuzzy rule defined by the incorruption probability. The fuzzy filter is composed of the two different filter of the identity filter and the spatiotemporal directional-weighted-mean filter, and will put out an intermediate value between the original input brightness and the directional-weighted-mean brightness. We design the fuzzy rule in advance by a standard supervised learning fuzzy rule in advance by a standard supervised learning method. The computer simulations are presented.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.294-298
• /
• 2015

In the United States, the completion of Construction Work Zone (CWZ) impact assessments for all federally-funded highway infrastructure improvement projects is mandated, yet it is regarded as a daunting task for state transportation agencies, due to a lack of standardized analytical methods for developing sounder Transportation Management Plans (TMPs). To circumvent these issues, this study aims to create a spatiotemporal modeling framework, dubbed "SWAT" (Spatiotemporal Work zone Assessment for TMPs). This study drew a total of 43,795 traffic sensor reading data collected from heavily trafficked highways in U.S. metropolitan areas. A multilevel-cluster-driven analysis characterized traffic patterns, while being verified using a measurement system analysis. An artificial neural networks model was created to predict potential 24/7 traffic demand automatically, and its predictive power was statistically validated. It is proposed that the predicted traffic patterns will be then incorporated into a what-if scenario analysis that evaluates the impact of numerous alternative construction plans. This study will yield a breakthrough in automating CWZ impact assessments with the first view of a systematic estimation method.

• 정보처리학회논문지D
• /
• 제10D권7호
• /
• pp.1103-1114
• /
• 2003

현재의 이동객체를 기반으로 하는 다양한 시공간 응용환경에서의 서비스 지원 시스템 개발을 위하여 중요한 문제 중의 하나는 방대한 이동객체의 위치 이동 데이터로부터의 의미 있는 지식인 시공간 이동 패턴을 탐사하는 것이다. 이를 위하여 시간적 위상관계, 공간적 위상관계 그리고 시공간적 위상관계에 대한 접근이 지식 탐사를 위하여 고려되어야 한다. 이 논문에서는 효율적인 시공간 이동 패턴 탐사 기법인 MPMine 알고리즘을 제안하였다. 제안한 기법은 시간 제약조건과 공간 제약조건 등을 함께 괴려하며 또한 공간 위상 연산인 contain()을 이용한 공간 개념화를 수행할 수 있다. 제안한 기법은 기존의 일반적인 시간 패턴 탐사 기법과 달리 이동객체 데이터 집합으로부터 위치 및 일반화를 통하여 탐색 공간을 줄일 수 있어 효율적으로 유용한 이동 패턴을 탐사할 수 있다.

• 대한중풍순환신경학회지
• /
• 제14권1호
• /
• pp.1-7
• /
• 2013

The following study reviewed the walking patterns of stroke patients with hemiplegia, which is called hemiplegic gait of stroke patients. Focusing is given to the changes in the distance and temporal factors of walking, which is called spatiotemporal characteristics, throughout the walking cycle. First, we introduced the definitions of essential terms related to gait and its measure. Second, we reviewed the spatiotemporal characteristics of hemiplegic gait. A main issue was that hemiplegic gait showed significant deviations from normal healthy gait. Although hemiplegia is primarily associated with unilateral motor disorder, changes in almost all spatiotemporal parameters used to assess walking were evident on both the involved and uninvolved sides of the body. Last, we reviewed the changes of spatiotemporal parameters of hemiplegic gait according to the prognosis or status of stroke patients, which may help to give a specific intervention for rehabilitation of stroke.

• 한국전문물리치료학회지
• /
• 제21권1호
• /
• pp.29-36
• /
• 2014

The purpose of this study was to investigate the immediate effect of fabric ankle-foot orthosis on spatiotemporal gait parameters, compared to a barefoot condition in children with spastic cerebral palsy. Eleven children with spastic cerebral palsy participated in this study. Spatiotemporal gait parameters were measured with the GAITRite system. Fabric ankle-foot orthosis significantly improved Timed Up and Go test time and gait velocity. There was no significant difference in cadence. The step time significantly improved in both the more and less affected foot compared to the barefoot condition. The step length of the affected foot also significantly improved, but there was no significant difference in the step length of the less affected foot. There was significant improvement in the stride length of both the affected and less affected foot, but no significant difference in single stance or double stance. The fabric ankle-foot orthosis could improve stability, and selective control of the joint and promote better walking in children with cerebral palsy. Consequently, the fabric ankle-foot orthosis might be an alternative assistive device for neurological populations as a primary role instead of the typical ankle-foot orthosis.

• 한국측량학회지
• /
• 제37권6호
• /
• pp.517-523
• /
• 2019

PM₁₀ 농도는 시간 및 공간 의존성을 동시에 가지는 시공간 데이터이지만 현실적으로 연속적인 시공간 데이터를 획득하는 것은 쉬운 일이 아니다. 본 연구에서는 위성영상과 대기질 및 기상 관측 센서 데이터를 복합적인 딥러닝 모델에 적용하여 시공간 해상도를 향상시키는 모델을 설계하였다. 설계된 딥러닝 모델은 기상, 토지 이용 등 PM₁₀ 농도에 영향을 줄 수 있는 인자를 이용하여 학습하였으며, 대기질 및 기상 관측 데이터만을 이용하여 15분 단위의 30m×30m의 공간해상도를 PM₁₀ 영상을 생성하였다.