• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권3호
• /
• pp.163-169
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. To achieve this goal, we propose a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers have been also presented. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.67-90
• /
• 2019

Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.

• Journal of information and communication convergence engineering
• /
• 제20권1호
• /
• pp.65-72
• /
• 2022

With the mark of the fourth industrial revolution, the smart factory is evolving into a new future manufacturing plant. As a human-machine-interactive tool, augmented reality (AR) helps workers acquire the proficiency needed in smart factories. The valuable data displayed on the AR device must be delivered intuitively to users. Current AR applications used in smart factories lack user movement calibration, and visual fiducial markers for position correction are detected only nearby. This paper demonstrates a marker-based object detection using perspective projection to adjust augmented content while maintaining the user's original perspective with displacement. A new angle, location, and scaling values for the AR content can be calculated by comparing equivalent marker positions in two images. Two experiments were conducted to verify the implementation of the algorithm and its practicality in the smart factory. The markers were well-detected in both experiments, and the applicability in smart factories was verified by presenting appropriate displacement values for AR contents according to various movements.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.425-426
• /
• 2022

범죄예방 목적으로 주변에 많은 CCTV가 설치되어 있는데 범죄의 상황에 따라 사후조사보다 사전에 대응해야하는 경우가 많다. 이런 경우 사람이 많은 CCTV를 보고 있을 수 없기 때문에 특정 상황 발생시 알람을 울려줄 필요가 있다. 따라것 영상데이터를 분석하여 어떠한 행위인지를 파악해야 하는데 본 연구에서는 급격한 움직임에 따른 히스토그램의 변화에 착안하여 히스토그램 연산을 통한 장면전환검축 기법을 제안한다.

• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.329-336
• /
• 2023

This paper introduces an edge AI-based scene-specific object detection system for long-term traffic management, focusing on analyzing congestion and movement via cameras. It aims to balance fast processing and accuracy in traffic flow data analysis using edge computing. We adapt the YOLOv5 model, with four heads, to a scene-specific model that utilizes the fixed camera's scene-specific properties. This model selectively detects objects based on scale by blocking nodes, ensuring only objects of certain sizes are identified. A decision module then selects the most suitable object detector for each scene, enhancing inference speed without significant accuracy loss, as demonstrated in our experiments.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권3호
• /
• pp.178-184
• /
• 2016

This paper proposes a new path-finding scheme using viewpoint-invariant landmarks. The scheme introduces the concept of landmark detection in images captured with a vision sensor attached to a mobile robot, and provides landmark clues to determine a path. Experiment results show that the scheme efficiently detects landmarks with changes in scenes due to the robot's movement. The scheme accurately detects landmarks and reduces the overall landmark computation cost. The robot moves in the room to capture different images. It can efficiently detect landmarks in the room from different viewpoints of each scene. The outcome of the proposed scheme results in accurate and obstacle-free path estimation.

• Journal of information and communication convergence engineering
• /
• 제10권3호
• /
• pp.307-314
• /
• 2012

This paper reports on the design of an object tracker that utilizes a family of unscented Kalman filters, one for each tracked object. This is a more efficient design than having one unscented Kalman filter for the family of all moving objects. The performance of the designed and implemented filter is demonstrated by using simulated movements, and also for object movements in 2D and 3D space.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권8호
• /
• pp.577-581
• /
• 2009

최근 유비쿼터스 컴퓨팅과 유비쿼터스 네트워크를 활용하여 새로운 서비스들을 개발하려는 노력이 활발히 진행 중이며, 이에 관련된 기술의 중요성도 급증하고 있다. 특히 감시정찰 센서네트워크의 핵심 구성요소인 저가의 경량 센서노드에서 측정한 미가공 데이터(raw data)를 사용하여 침입 물체의 실시간 탐지, 식별, 추적 및 예측하기 위한 디지털 신호처리 기술은 주요 기술 중 하나이다. 본 논문에서는 감시정찰 센서네트워크의 핵심 구성요소인 센서노드의 적외선 센서에서 측정한 척외선 미가공 데이터를 사용하여 사람과 차량을 탐지할 수 있는 디지털 신호처리 알고리즘을 설계 및 구현한다. 알고리즘의 주 목표는 감사정찰용 센서노드의 탐지 신뢰성을 높이기 위하여 높은 침입물체 탐지 성공률(success rate)과 낮은 허위신고(false alarm) 횟수를 갖도록 하는 것이다. 성능평가 결과에 의하면 제안한 APIDA 알고리즘은 평지일 경우 90% 이상의 탐지 성공률과 2회 이하의 허위신고 횟수를 가지는 것을 확인할 수 있었다.

• 대한인간공학회지
• /
• 제34권5호
• /
• pp.377-399
• /
• 2015

Objective: The aim of this study is to understand and identify the critical issues in vision research area using content analysis and network analysis. Background: Vision, the most influential factor in information processing, has been studied in a wide range of area. As studies on vision are dispersed across a broad area of research and the number of published researches is ever increasing, a bibliometric analysis towards literature would assist researchers in understanding and identifying critical issues in their research. Method: In this study, content and network analysis were applied on the meta-data of literatures collected using three search keywords: 'visual search', 'eye movement', and 'eye tracking'. Results: Content analysis focuses on extracting meaningful information from the text, deducting seven categories of research area; 'stimuli and task', 'condition', 'measures', 'participants', 'eye movement behavior', 'biological system', and 'cognitive process'. Network analysis extracts relational aspect of research areas, presenting characteristics of sub-groups identified by community detection algorithm. Conclusion: Using these methods, studies on vision were quantitatively analyzed and the results helped understand the overall relation between concepts and keywords. Application: The results of this study suggests that the use of content and network analysis helps identifying not only trends of specific research areas but also the relational aspects of each research issue while minimizing researchers' bias. Moreover, the investigated structural relationship would help identify the interrelated subjects from a macroscopic view.