• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.69-75
• /
• 2014

Existing People Counting System using a single overhead mounted camera has limitation in object recognition and counting in various environments. Those limitations are attributable to overlapping, occlusion and external factors, such as over-sized belongings and dramatic light change. Thus, this paper proposes the new concept of People Counting System by Facial Age Group using two depth cameras, at overhead and frontal viewpoints, in order to improve object recognition accuracy and robust people counting to external factors. The proposed system is counting the pedestrians by five process such as overhead image processing, frontal image processing, identical object recognition, facial age group classification and in-coming/out-going counting. The proposed system developed by C++, OpenCV and Kinect SDK, and it target group of 40 people(10 people by each age group) was setup for People Counting and Facial Age Group classification performance evaluation. The experimental results indicated approximately 98% accuracy in People Counting and 74.23% accuracy in the Facial Age Group classification.

• Journal of the Korea Safety Management & Science
• /
• v.6 no.2
• /
• pp.79-89
• /
• 2004

It is known that most people have a dominant eye, even though each of their two eyes in isolation may provide equal vision. In this study, 600 Korean male and female subjects aging from 11 to 78 were selected to investigate the various statistics about eye dominance( whether the left or right eye is dominant} in Korean and their employment characteristics of preferred eye in sighting diverse things. A simple sighting test was applied such that subjects are requested to aim a distance target through small hole in B4 sized paper with both eyes open. The dominant eye was determined by alternate occlusion: when viewing with the dominant eye into the hole is aligned with the target, whereas when viewing with the other eye into the hole appears offset to one side. The descriptive statistics showed that 83.7% and 16.3% were right and left eye dominant respectively. Moreover, various statistical analysis revealed that general tendency of eye dominance was varied by age, gender, hand dominance and visual acuity. It was thus found from these results that people sighting their eyes differently depending on the eye dominance when they sight things.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.298-306
• /
• 2013

Recent years have witnessed a growing interest in the fields of video surveillance and mobile object tracking. This paper proposes a mobile object tracking algorithm. First, several parameters such as object window, object area, and expansion-contraction (E-C) parameter are defined. Then, a modified E-C algorithm for multiple-object tracking is presented. The proposed algorithm tracks moving objects by expansion and contraction of the object window. In addition, it includes methods for updating the background image and avoiding occlusion of the target image. The validity of the proposed algorithm is verified experimentally. For example, the first scenario traces the path of two people walking in opposite directions in a hallway, whereas the second one is conducted to track three people in a group of four walkers.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.645-646
• /
• 2006

Pressure-induced decubitus is a serious disease among the elderly people. Interface pressure occluding vascular perfusion is known to be a cause of decubitus. Therefore, it is essential to quantify the relationship between vascular perfusion and interface pressure among the elderly people. Nine elderly normal people ($57.8{\pm}5.6\;years,\;63.3{\pm}7.0kg,\;1.68{\pm}0.05m$) were participated. Pressure was applied on the ischial tuberosity in the sitting posture from 0mmHg to 135mmHg as capillary vascular perfusion was recorded. The average interface pressure to occlude vascular perfusion under the ischial tuberosity is 120mmHg. Vascular perfusion values at the capillary occlusion is often lower than 60% of the vascular perfusion at 15mmHg. Higher sampling number is required to have more accurate results.

• Journal of Ginseng Research
• /
• v.47 no.2
• /
• pp.274-282
• /
• 2023

Background: Ginsenoside compound K (CK) stimulated activation of the PI3K-Akt signaling is one of the major mechanisms in promoting cell survival after stroke. However, the underlying mediators remain poorly understood. This study aimed to explore the docking protein of ginsenoside CK mediating the neuroprotective effects. Materials and methods: Molecular docking, surface plasmon resonance, and cellular thermal shift assay were performed to explore ginsenoside CK interacting proteins. Neuroscreen-1 cells and middle cerebral artery occlusion (MCAO) model in rats were utilized as in-vitro and in-vivo models. Results: Ginsenoside CK interacted with recombinant human PTP1B protein and impaired its tyrosine phosphatase activity. Pathway and process enrichment analysis confirmed the involvement of PTP1B and its interacting proteins in PI3K-Akt signaling pathway. PTP1B overexpression reduced the tyrosine phosphorylation of insulin receptor substrate 1 (IRS1) after oxygen-glucose deprivation/reoxygenation (OGD/R) in neuroscreen-1 cells. These regulations were confirmed in the ipsilateral ischemic hemisphere of the rat brains after MCAO/R. Ginsenoside CK treatment reversed these alterations and attenuated neuronal apoptosis. Conclusion: Ginsenoside CK binds to PTP1B with a high affinity and inhibits PTP1B-mediated IRS1 tyrosine dephosphorylation. This novel mechanism helps explain the role of ginsenoside CK in activating the neuronal protective PI3K-Akt signaling pathway after ischemia-reperfusion injury.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.449-452
• /
• 2000

본 논문은 다중의 사람을 동시에 검지 및 추적하기 위한 방법을 제안한다 여러 명의 검지된 사람들이 교차해서 움직이거나 폐색(occlusion) 되어 움직이는 경우 이를 검지하고 신뢰적으로 추적하기 위한 방법을 제시한다. 카메라의 시야 범위 안에 나타난 표적은 일정한 크기를 가지는 오브젝트이므로, 배경영상에서 전경 영상만을 분리하는 과정에서 오브젝트의 크기를 고려하여 표적을 검지 한다. 표적의 검지는 환경적인 요인에 의한 부가요소에 적응적으로 대치하기 위해 적응적인 영상처리기법을 사용한다. 최종적으로 검지 된 표적을 동시에 추적하기 위해 본 논문에서는 JPDA(Joint Probability Data Association) 필터를 이용하며 ,표적간의 폐색을 처리하기 위한 방법으로 전이모델을 첨가해서 사용한다. 다중 표적의 추적에 관한 실험의 유효성 및 강인함은 다양한 실제 영상의 실험을 통해 입증한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.445-449
• /
• 2008

개인과 공공의 안전에 대한 요구가 증가함에 따라 카메라를 이용한 영상 감시 시스템이 점차적으로 증가하고 있다. 보안의 필요성에 따라 한 지역에 여러 대의 카메라를 설치하여 FOV(Field Of View)를 겹치는 경우도 있다. 이처럼 FOV의 중첩 영역에서 다중 카메라들로부터 얻은 영상을 처리하여 객체의 위치를 파악하고 추적하는 연구가 활발히 이루어지고 있다. 본 논문에서는 다수의 카메라를 이용해 감시 영역이 중첩되는 지역에서의 겹침이 발생해도 객체를 계속적으로 추적하는 방법을 제안한다. 이 방법으로 단일 카메라 상에서의 외형 식별자를 이용하여 추적하고 다중 카메라 간의 호모그래픽 매트릭스를 이용하여 노이즈에 강건한 시스템을 구현하였다.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.435-437
• /
• 2004

This paper presents a personal identification method using teeth images. The method uses images for teeth expressions of anterior and posterior occlusion state and LDA-based technique. Teeth images give merits for recognition because teeth, rigid objects, cannot be deformed at the moment of image acquisition. In the experiments, personal identification for 12 people was successful. It was shown that our method can contribute to multi-modal authentication systems.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.505-510
• /
• 2009

In recent years the space where a robot works has been expanding to the human space unlike traditional industrial robots that work only at fixed positions apart from humans. A human in the recent situation may be the owner of a robot or the target in a robotic application. This paper deals with the latter case; when a robot vision system is employed to monitor humans for a surveillance application, each person in a scene needs to be identified. Humans, however, often move together, and occlusions between them occur frequently. Although this problem has not been seriously tackled in relevant literature, it brings difficulty into later image analysis steps such as tracking and scene understanding. In this paper, a probabilistic neural network is employed to learn the patterns of the best dividing position along the top pixels of an image region of partly occlude people. As this method uses only shape information from an image, it is simple and can be implemented in real time.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.488-498
• /
• 2007

This paper presents a novel approach for representing the spatio-temporal topology of the camera network with overlapping and non-overlapping fields of view (FOVs) in Ubiquitous Smart Space (USS). The topology is determined by tracking moving objects and establishing object correspondence across multiple cameras. To track people successfully in multiple camera views, we used the Merge-Split (MS) approach for object occlusion in a single camera and the grid-based approach for extracting the accurate object feature. In addition, we considered the appearance of people and the transition time between entry and exit zones for tracking objects across blind regions of multiple cameras with non-overlapping FOVs. The main contribution of this paper is to estimate transition times between various entry and exit zones, and to graphically represent the camera topology as an undirected weighted graph using the transition probabilities.