Filters








132 Hits in 7.5 sec

Evaluation of a monitoring system for event recognition of older people

Carlos Fernando Crispim-, Vasanth Bathrinarayanan, Baptiste Fosty, Alexandra Konig, Rim Romdhane, Monique Thonnat, Francois Bremond
2013 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance  
The prototype uses as input a 2D RGB camera, and its performance is compared to the use of a RGB-D camera.  ...  The experimentation results show the proposed approach has a competitive performance to the use of a RGB-D camera, even outperforming it on event recognition precision.  ...  A 2D-RGB camera is used to track the people over the environment and estimate their posture.  ... 
doi:10.1109/avss.2013.6636634 dblp:conf/avss/CrispimBFKRTB13 fatcat:weawmlj4mbaodpgsosfxvoxdei

A Hierarchical Description-based Video Monitoring System for Elderly

Mochamad Irwan Nari, Agung Wahyu Setiawan, Widyawardana Adiprawita
2017 Proceeding of the Electrical Engineering Computer Science and Informatics  
In this research, prototype of an inexpensive video monitoring system for the elderly using a single RGB camera proposed.  ...  For event recognition, we use a hierarchical description-based approach with three attributes, namely posture (e.g., stand, sit and lie), location (e.g., walking zone, relaxing zone and toilet zone) and  ...  [6] use four cameras to capture the scene from different angles. They extract the location of the subject to activities recognized. Dubois et al. [7] using the RGB-D camera to capture objects.  ... 
doi:10.11591/eecsi.v4.1044 fatcat:4cejxgl25nbjxlabw6app6bcoa

Combining multiple sensors for event recognition of older people

Carlos Fernando Crispim-Junior, Baptiste Fosty, Rim Romdhane, Qiao Ma, Francois Bremond, Monique Thonnat
2013 Proceedings of the 1st ACM international workshop on Multimedia indexing and information retrieval for healthcare - MIIRH '13  
conflicting events from video cameras with a partially overlapped field of view (a RGB-and a RGB-D-camera).  ...  Event models combine a priori knowledge of the scene (3D geometric and semantic information, such as contextual zones and equipments) with moving objects (e.g., a Person) detected by a monitoring system  ...  It models the context of a human (e.g., body posture) using data from a set of cameras, and of the environment (semantic information about the scene) using data of accelerometer devices attached to objects  ... 
doi:10.1145/2505323.2505329 dblp:conf/mm/JuniorFRMBT13 fatcat:dc54m4otejeddhawpo6h7ag7cq

Fall detection and activity recognition using human skeleton features

Heilym Ramirez, Sergio A. Velastin, Ignacio Meza, Ernesto Fabregas, Dimitrios Makris, Gonzalo Farias
2021 IEEE Access  
It carries out the detection using human skeleton estimation for features extraction.  ...  The use of human skeleton detection opens the possibility for detecting not only falls but also different kind of activities for several subjects in the same scene.  ...  It is the first RGB-D dataset that provides ground truth data for different body parts of a person moving in a scene with occlusions.  ... 
doi:10.1109/access.2021.3061626 fatcat:nk5btenvnjdcvougdk4e3nphqy

Improving posture classification accuracy for depth sensor-based human activity monitoring in smart environments

Edmond S.L. Ho, Jacky C.P. Chan, Donald C.K. Chan, Hubert P.H. Shum, Yiu-ming Cheung, Pong C. Yuen
2016 Computer Vision and Image Understanding  
in the same context.  ...  Alternatively, identifying human posture with traditional 2D video cameras can be performed using computer vision techniques [3] .  ...  Sitting on a chair and working on a work bench Here, we perform evaluation on the sitting to work posture database, which includes healthy, B-1 and B-2 postures as explained in Section 6.2 .  ... 
doi:10.1016/j.cviu.2015.12.011 fatcat:bq3wk3m34jbfbhqhe7i4z2n5ma

An Unobtrusive and Non-Contact Method for Respiratory Measurement With Respiratory Region Detecting Algorithm Based on Depth Images

Chenglu Sun, Wei Li, Chen Chen, Zeyu Wang, Wei Chen
2019 IEEE Access  
The proposed algorithm contains four steps: body edge extraction, noise reduction, "image skeleton" extraction, and respiratory region estimation.  ...  As a result, the respiratory waveform can be derived from the depth data in the ROI.  ...  (a) and (d) show that the subject is in the stand posture, (b) and (e) show the subject is in the sit posture, and (c) and (f) show the subject is in the supine posture.  ... 
doi:10.1109/access.2018.2890082 fatcat:gvg3ancw6fhaln6omyd7oq6q5u

Uncertainty Modeling Framework for Constraint-Based Elementary Scenario Detection in Vision Systems [chapter]

Carlos Fernando Crispim-Junior, Francois Bremond
2015 Lecture Notes in Computer Science  
The uncertainty modeling framework is demonstrated on the detection of activities of daily living of participants of an Alzheimer's disease study, monitored by a vision system using a RGB-D sensor (Kinect  ...  Although effective those representations have difficulty on incorporating scene semantics.  ...  (person changes from sitting to standing posture before person in corridor zone).  ... 
doi:10.1007/978-3-319-16181-5_19 fatcat:bmxdkzmvu5cflfekyy73au3rou

Radar and RGB-Depth Sensors for Fall Detection: A Review

Enea Cippitelli, Francesco Fioranelli, Ennio Gambi, Susanna Spinsante
2017 IEEE Sensors Journal  
This paper reviews recent works in the literature on the use of systems based on Radar and RGB-Depth sensors for fall detection, and discusses outstanding research challenges and trends related to this  ...  Researchers from different fields can benefit from multidisciplinary knowledge and awareness of the latest developments in radar and RGB-D sensors that this paper is discussing.  ...  Finally, the review of the state-of-the-art for radar and RGB-D sensors in the context of fall detection and human activity recognition is important to identify gaps and future research directions, in  ... 
doi:10.1109/jsen.2017.2697077 fatcat:4pu3dtph2fcu7ictfcf6z3wu6y

Neural Networks for Automatic Posture Recognition in Ambient-Assisted Living

Bruna Maria Vittoria Guerra, Micaela Schmid, Giorgio Beltrami, Stefano Ramat
2022 Sensors  
of the subject in an ecological context within each recorded frame.  ...  To this goal, we propose a monitoring system detecting dangerous situations by classifying human postures through Artificial Intelligence (AI) solutions.  ...  the NTU RGB + D one [23, 24] .  ... 
doi:10.3390/s22072609 pmid:35408224 pmcid:PMC9003043 fatcat:yfqn5cslffeurpd2bnzrispuia

Predicting bedside falls using current context

Asbjorn Danielsen, Bernt A. Bremdal
2017 2017 IEEE Symposium Series on Computational Intelligence (SSCI)  
Such tools would need to use the current context as input to predict an imminent fall.  ...  These features are used by a classification algorithm to create a probability matrix representing the conditional probability of an individual in the current frame being recognized in a specific location  ...  I EXPERIMENT SCENES AND INSTRUCTIONS Scene 1 Scene 2 Scene 3 Scene 4 Enter room Sit down (in bed) Enter room Fall down (beside bed) Enter room Lay down (in bed) Enter room Lay down  ... 
doi:10.1109/ssci.2017.8280988 dblp:conf/ssci/DanielsenB17 fatcat:bxqvze4ytbglfj7efumtsjqsqq

A Vision-Based System for Monitoring Elderly People at Home

Marco Buzzelli, Alessio Albé, Gianluigi Ciocca
2020 Applied Sciences  
In this work, we propose a monitoring system designed to be as unobtrusive as possible, by exploiting computer vision techniques and visual sensors such as RGB cameras.  ...  We subsequently curate a taxonomy of human actions, derived from different sources in the literature, and provide the scientific community with considerations about the mutual exclusivity and commonalities  ...  Acknowledgments: We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Jetson TX1 Kit and the Titan Xp GPU used for this research.  ... 
doi:10.3390/app10010374 fatcat:d7mkeskoufdn3phtozckn4kafe

Human activity recognition from skeleton poses [article]

Frederico Belmonte Klein, Angelo Cangelosi
2019 arXiv   pre-print
A promising approach is using trained classifiers to recognise human actions through sequences of skeleton poses extracted from images or RGB-D data from a sensor.  ...  Human Action Recognition is an important task of Human Robot Interaction as cooperation between robots and humans requires that artificial agents recognise complex cues from the environment.  ...  For the present work the RGB-D will be disregarded and only the skeleton joint positions will be used.  ... 
arXiv:1908.08928v1 fatcat:cawqgl7psvfo7awuc6vk6i4ptq

An Online One Class Support Vector Machine-Based Person-Specific Fall Detection System for Monitoring an Elderly Individual in a Room Environment

Miao Yu, Yuanzhang Yu, Adel Rhuma, Syed Mohsen Raza Naqvi, Liang Wang, Jonathon A. Chambers
2013 IEEE journal of biomedical and health informatics  
ACKNOWLEDGEMENT The authors wish to acknowledge the valuable help of the Associate Editor and anonymous reviewers in improving the quality of our paper.  ...  in the scene during the initial training period.  ...  Figure 6 (d) shows the corresponding histograms for four postures of standing, sitting, bending and lying.  ... 
doi:10.1109/jbhi.2013.2274479 pmid:24240718 fatcat:w74djo7hxjczlbgt5n5af73yiu

Kinect Sensor Based Gesture Recognition for Surveillance Application [article]

Biswarup Ganguly, Amit Konar
2018 arXiv   pre-print
Human body movements have been viewed using these depth sensors which can provide sufficient accuracy while tracking full body in real time mode with low cost.  ...  Human body tracking is a well studied topic in todays era of Human Computer Interaction and it can be formed by the virtue of human skeleton structures.  ...  Step V : Estimating observation symbols.  ... 
arXiv:1812.09595v1 fatcat:hkayujn4gbavzbviwlbjvliyce

Towards a Live Feedback Training System: Interchangeability of Orbbec Persee and Microsoft Kinect for Exercise Monitoring

Verena Venek, Wolfgang Kremser, Thomas Stöggl
2021 Designs  
Furthermore, we used both skeleton datasets as input for the ILSE exercise monitoring including posture recognition and repetition-counting.  ...  Nine functional training exercises were performed by six healthy subjects in front of both systems simultaneously.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.  ... 
doi:10.3390/designs5020030 fatcat:z7xhcu6xzng4pkenwebm5nmyru
« Previous Showing results 1 — 15 out of 132 results