Filters








3,496 Hits in 5.5 sec

Human Fall Detection Using Machine Learning Methods: A Survey

Komal Singh, Akshay Rajput, Sachin Sharma
2019 International journal of mathematical, engineering and management sciences  
In this paper, we discuss different machine learning models designed to detect human fall using these techniques.  ...  A human fall detection system can be designed using one of these technologies: wearable based device, context-aware based and vision based methods.  ...  Acknowledgement The authors express their gratitude to the reviewers for their valuable suggestions towards the improvement in the quality of the paper.  ... 
doi:10.33889/ijmems.2020.5.1.014 fatcat:aj6vu47yvnbcxo7aem524e5kia

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild [article]

Jason Y. Zhang and Sam Pepose and Hanbyul Joo and Deva Ramanan and Jitendra Malik and Angjoo Kanazawa
2020 arXiv   pre-print
In particular, we introduce a scale loss that learns the distribution of object size from data; an occlusion-aware silhouette re-projection loss to optimize object pose; and a human-object interaction  ...  We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment.  ...  This work was funded in part by the CMU Argo AI Center for Autonomous Vehicle Research.  ... 
arXiv:2007.15649v2 fatcat:yccc5eaccncava3knmyw5dyzbe

Silhouettes from Real Objects Enable Realistic Interactions with a Virtual Human in Mobile Augmented Reality

Hanseob Kim, Ghazanfar Ali, Andréas Pastor, Myungho Lee, Gerard J. Kim, Jae-In Hwang
2021 Applied Sciences  
We also conducted a pilot study using our approach and reported significant improvements in user perception of spatial awareness and presence for realistic interactions with a virtual human.  ...  Our proposed method uses the dynamic silhouette of a real object to enable realistic interactions.  ...  Acknowledgments: We express sincere gratitude to the participants in the experiments. We also thank the reviewers for their valuable contributions.  ... 
doi:10.3390/app11062763 fatcat:lj3c6jtnx5fdzox6nlpovhzjai

EagleSense

Chi-Jui Wu, Steven Houben, Nicolai Marquardt
2017 Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems - CHI '17  
To facilitate the prototyping of ubiquitous computing applications for interactive spaces, we developed EagleSense, a real-time human posture and activity recognition system with a single top-view depthsensing  ...  novel algorithm and processing pipeline, including details for calculating silhouetteextremities features and applying gradient tree boosting classifiers for activity recognition optimized for top-view depth  ...  Human detection and tracking HCI researchers used real-time human pose estimation (localization of skeleton joints) from single depth images [45] via commodity depth sensors such as the Microsoft Kinect  ... 
doi:10.1145/3025453.3025562 dblp:conf/chi/WuHM17 fatcat:dydjs5d6g5cvdc4clugbib34ou

A survey on vision-based fall detection

Zhong Zhang, Christopher Conly, Vassilis Athitsos
2015 Proceedings of the 8th ACM International Conference on PErvasive Technologies Related to Assistive Environments - PETRA '15  
This article is a survey of systems and algorithms which aim at automatically detecting cases where a human falls and may have been injured.  ...  To improve the quality of living for seniors, a wide range of monitoring systems with fall detection functionality have been proposed over recent years.  ...  [22] use human motion analysis and human silhouette shape variations to detect slip-only and fall events.  ... 
doi:10.1145/2769493.2769540 dblp:conf/petra/ZhangCA15 fatcat:f3gjqvybojalla7igfa2tvz4yy

Mobile human-robot teaming with environmental tolerance

Matthew M. Loper, Nathan P. Koenig, Sonia H. Chernova, Chris V. Jones, Odest C. Jenkins
2009 Proceedings of the 4th ACM/IEEE international conference on Human robot interaction - HRI '09  
We posit that the use of recent emerging devices for depth-based imaging can enable robot perception of non-verbal cues in human movement in the face of lighting and minor terrain variations.  ...  We demonstrate that structured light-based depth sensing with standard perception algorithms can enable mobile peerto-peer interaction between humans and robots.  ...  Human Detection and Following In order to detect humans in varying environments, we require algorithms to interpret the depth data obtained by our active lighting system.  ... 
doi:10.1145/1514095.1514124 dblp:conf/hri/LoperKCJJ09 fatcat:2ncqjous2rgpln7ym52rw4vnta

Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models

Luke K. Topham, Wasiq Khan, Dhiya Al-Jumeily, Abir Hussain
2022 ACM Computing Surveys  
There are several review studies addressing person identification such as the utilization of facial images, silhouette images, and wearable sensor.  ...  possible contributions in the future.  ...  The authors are not aware of any current attempts towards implementing gait identification using 3D HPE.  ... 
doi:10.1145/3533384 fatcat:j6g7wayx4fhkvck3nlsxz5xudi

Body Size Judgments at 17 ms: Evidence From Perceptual and Attitudinal Body Image Indexes

Ana Clara de Paula Nazareth, Vinícius Spencer Escobar, Thiago Gomes DeCastro
2020 Frontiers in Psychology  
Such evidence signals that conscious body image can be associated to implicit detection of visual human body stimuli.  ...  In the second experiment participants had to respond in a seven-point Likert scale if the presented image of body silhouettes were bigger, equal or thinner than their own bodies.  ...  Such evidence signals that conscious body image can be associated to implicit detection of visual human body stimuli.  ... 
doi:10.3389/fpsyg.2019.03018 pmid:32010033 pmcid:PMC6978682 fatcat:7ftgnmywqzcljn2ovrwfw52g2m

A survey of imagery techniques for semantic labeling of human-vehicle interactions in persistent surveillance systems

Vinayak Elangovan, Amir Shirkhodaie, Ivan Kadar
2011 Signal Processing, Sensor Fusion, and Target Recognition XX  
processing techniques for spatiotemporal characterization and tracking of human target in urban environments.  ...  Various Persistent Surveillance System (PSS) imagery techniques have been proposed in the past for identifying human interactions with various objects in the environment.  ...  In contrary, outdoor scene images often have wide range of depth, and size of human blob and his/her interacting objects can be very small.  ... 
doi:10.1117/12.887019 fatcat:nsxr5vr76jbjbppmctkxs6x2pq

Robust Model-Based 3D Torso Pose Estimation in RGB-D Sequences

Markos Sigalas, Maria Pateraki, Iason Oikonomidis, Panos Trahanias
2013 2013 IEEE International Conference on Computer Vision Workshops  
The detected face of the user steers the initiation of shoulder areas hypotheses, based on illumination, scale and pose invariant features on the RGB silhouette.  ...  In this context, the extraction of human-body pose information is of utmost importance.  ...  Based on face detection and tracking, the human body silhouette is extracted for the detected users in the scene. • Shoulder joint approximation.  ... 
doi:10.1109/iccvw.2013.49 dblp:conf/iccvw/SigalasPOT13 fatcat:k5kfd2746ff77pidka36ens76i

Efficient multi-view ray tracing using edge detection and shader reuse

Magnus Andersson, Björn Johnsson, Jacob Munkberg, Petrik Clarberg, Jon Hasselgren, Tomas Akenine-Möller
2011 The Visual Computer  
We introduce multiview silhouette edges to detect sharp geometrical discontinuities in the radiance function. These are used to significantly improve the quality of the reconstruction.  ...  We present a specialized algorithm for efficient multi-view image generation from a camera line using ray tracing, which builds on previous methods for multi-dimensional adaptive sampling and reconstruction  ...  In combination with sampling of L using adaptive forward rays, as described in MDAS, we also analytically detect geometric silhouette edges by tracing a triangle backwards from an intersection point towards  ... 
doi:10.1007/s00371-011-0560-4 fatcat:j33bs4ihevhdtib6oklj2s2twm

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction [article]

Zerong Zheng and Tao Yu and Yebin Liu and Qionghai Dai
2020 arXiv   pre-print
Experimental results demonstrate that our method achieves state-of-the-art performance for image-based 3D human reconstruction in the cases of challenging poses and clothing types.  ...  Moreover, a novel depth-ambiguity-aware training loss is further integrated to resolve depth ambiguities and enable successful surface detail reconstruction with imperfect body reference.  ...  As shown in DeepHuman, a SMPL model fitted to the input image can serve as a strong geometry prior, and guarantee pose and shape aware human model reconstructions.  ... 
arXiv:2007.03858v2 fatcat:evtj2ijtfrasfosn4q5hzcitnu

MoSculp: Interactive Visualization of Shape and Time [article]

Xiuming Zhang, Tali Dekel, Tianfan Xue, Andrew Owens, Qiurui He, Jiajun Wu, Stefanie Mueller, William T. Freeman
2018 arXiv   pre-print
To provide this end-to-end workflow, we introduce an algorithm that estimates that human's 3D geometry over time from a set of 2D images and develop a 3D-aware image-based rendering approach that embeds  ...  video, render it in a synthetic scene or physically print it.  ...  We are grateful to Angjoo Kanazawa for her help in running [51] on the Horse sequence. We thank Kevin Burg for allowing us to use the ballet clips from [10] .  ... 
arXiv:1809.05491v1 fatcat:2fkf32opvvfgngxe3vm5jqs3v4

A survey of advances in vision-based human motion capture and analysis

Thomas B. Moeslund, Adrian Hilton, Volker Krüger
2006 Computer Vision and Image Understanding  
Recent research has addressed reliable tracking and pose estimation in natural scenes. Progress has also been made towards automatic understanding of human actions and behavior.  ...  This survey reviews advances in human motion capture and analysis from 2000 to 2006, following a previous survey of papers up to 2000 [206].  ...  Temporal context-free Zhao and Thorpe [338] use depth data to extract the silhouettes of individuals in the image.  ... 
doi:10.1016/j.cviu.2006.08.002 fatcat:7vsbfnczrzgsbdbbmlzvfprh54

Frontal View Gait Recognition with Fusion of Depth Features from a Time of Flight Camera

Tengku Mohd Afendi, Fatih Kurugollu, Danny Crookes, Ahmed Bouridane, Mohsen Farid
2018 IEEE Transactions on Information Forensics and Security  
The four-part method includes: a new human silhouette extraction algorithm that reduces the multiple reflection problem experienced by ToF cameras; a frame selection method based on a new gait cycle detection  ...  algorithm; four new gait image representations; and a novel fusion classifier.  ...  Human Silhouette Extraction The first stage is the extraction of the human silhouette from the depth image (Z-image).  ... 
doi:10.1109/tifs.2018.2870594 fatcat:cjx4vefikfafnaeca744ksyawi
« Previous Showing results 1 — 15 out of 3,496 results