Filters








7,471 Hits in 6.5 sec

Multi-Type Activity Recognition from a Robot's Viewpoint

Ilaria Gori, J. K. Aggarwal, Larry Matthies, Michael. S. Ryoo
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
We first design a new unified descriptor, called Relation History Image (RHI), which can be extracted from all the activity types we are interested in.  ...  However, traditional methods treat such types of activities separately, while in real settings detecting and recognizing different types of activities simultaneously is necessary.  ...  The only descriptors that may be suitable for our multi-type activity recognition setting are appearance-based descriptors such as HON4D, STIP and DSTIP.  ... 
doi:10.24963/ijcai.2017/680 dblp:conf/ijcai/GoriAMR17 fatcat:je6sozfyjrdzrmghotgcg2nkau

Multi-Type Activity Recognition in Robot-Centric Scenarios [article]

Ilaria Gori, J. K. Aggarwal, Larry Matthies, Michael S. Ryoo
2016 arXiv   pre-print
Activity recognition is very useful in scenarios where robots interact with, monitor or assist humans.  ...  We present a new unified descriptor, called Relation History Image (RHI), which can be extracted from all the activity types we are interested in.  ...  Our descriptor is unified as it is able to describe different types of human activities while maintaining the same format and dimension.  ... 
arXiv:1507.02558v2 fatcat:rjdjgnohxbabhldd5dhycvurdm

A Comprehensive Review of Group Activity Recognition in Videos

Li-Fang Wu, Qi Wang, Meng Jian, Yu Qiao, Bo-Xuan Zhao
2021 International Journal of Automation and Computing  
From this comprehensive literature review, readers can obtain an overview of progress in group activity recognition for future studies.  ...  In this paper, we give a comprehensive overview of the advances in group activity recognition in videos during the past 20 years.  ...  Unified modeling framework Group activity recognition for video usually involves multi-person detection, multi-person tracking and activity recognition.  ... 
doi:10.1007/s11633-020-1258-8 fatcat:ycka4thcy5a6vghpenpthtrndi

A Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos

Jun Zhu, Quan Zhou, Weijia Zou, Rui Zhang, Wenjun Zhang
2013 Sensors  
build a valid similarity metric between two video clips for kernel-based classification.  ...  In this paper, we propose a generalized pyramid matching kernel (GPMK) for recognizing human actions in realistic videos, based on a multi-channel "bag of words" representation constructed from local spatial-temporal  ...  for recognizing human daily activities in RGB-D videos.  ... 
doi:10.3390/s131114398 pmid:24284771 pmcid:PMC3871056 fatcat:czvyitfno5csfiqcszbhulmrui

A Comprehensive Study of Group Activity Recognition Methods in Video

S. A. Vahora, N. C. Chauhan
2017 Indian Journal of Science and Technology  
Applications/Improvements: This reviews help in different applications of human activity analysis, mainly in group activity recognition and the models described here can be used in different applications  ...  Methods/Statistical Analysis: Different methods of group activity recognition categorized and analyzed according to hand-crafted and learned feature descriptors.  ...  For each class a multi-model density function on the DTIM leaned and MAP classifier is designed on DTIM for group activity recognition.  ... 
doi:10.17485/ijst/2017/v10i23/113996 fatcat:5ltu45vqmvdgxgeasifu3fipry

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

Allah Sargano, Plamen Angelov, Zulfiqar Habib
2017 Applied Sciences  
Human activity recognition (HAR) is an important research area in the fields of human perception and computer vision due to its wide range of applications.  ...  However, handcrafted representation-based approaches are still widely used due to some bottlenecks such as computational complexity of deep learning techniques for activity recognition.  ...  human activity recognition.  ... 
doi:10.3390/app7010110 fatcat:4hbcvrnvhfam5kbf44oqdgz2pm

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
with Rotation-Invariant Fast Features Demo: Unified Tracking and Recognition with Rotation-Invariant Fast Features Workshop: Quantization Schemes for Low Bitrate Compressed Histogram of Gradient Descriptors  ...  for Object Detection Part and Appearance Sharing: Recursive Compositional Models for Multi-View Multi-Object Detection Freifeld, Oren Contour People: A Parameterized Model of 2D Articulated Human  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Pedestrian Classification Based on Full-SVM Decision Tree

Hongmin Xue, Zhijing Liu, Jing Xiong
2015 International Journal of Multimedia and Ubiquitous Engineering  
Visual analysis has potential to be used for recognition, and it is one of the hottest but most difficult subjects in computer vision.  ...  The Support Vector Machine technology and the decision tree have combined into one multi-class classifier so as to solve multi-class classification problems.  ...  It also includes efforts to classify different types of human activities, such as Walking, jogging, running, boxing, hand waving, bending, jumping and skipping action.  ... 
doi:10.14257/ijmue.2015.10.5.14 fatcat:xqnj3ogzkra5lamceyt7njabcu

Learning and recognition of objects inspired by early cognition

Maja Rudinac, Gert Kootstra, Danica Kragic, Pieter P. Jonker
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In this paper, we present a unifying approach for learning and recognition of objects in unstructured environments through exploration.  ...  And last, object recognition benefits from a multi-modal representation.  ...  Based on these observations, a multi-view multi-modal representation of the object is build, which is used for learning and recognition.  ... 
doi:10.1109/iros.2012.6385895 dblp:conf/iros/RudinacKKJ12 fatcat:heb2cemfwfcuraxtejb5i35cyu

View and Style-Independent Action Manifolds for Human Activity Recognition [chapter]

Michał Lewandowski, Dimitrios Makris, Jean-Christophe Nebel
2010 Lecture Notes in Computer Science  
We introduce a novel approach to automatically learn intuitive and compact descriptors of human body motions for activity recognition.  ...  Each action descriptor is produced, first, by applying Temporal Laplacian Eigenmaps to view-dependent videos in order to produce a stylistic invariant embedded manifold for each view separately.  ...  The authors would like to thank Lena Gorelick from University of Western Ontario and Richard Souvenir from University of North Carolina at Charlotte for sharing their codes.  ... 
doi:10.1007/978-3-642-15567-3_40 fatcat:xrhzykgjdbhblgj7vfbyqmjvtu

Semantic Labeling of Human Action For Visually Impaired And Blind People Scene Interaction [article]

Leyla Benhamida, Slimane Larabi
2022 arXiv   pre-print
First, based on the state-of-the-art methods of human action recognition from RGB-D sequences, we use the skeleton information provided by Kinect, with the disentangled and unified multi-scale Graph Convolutional  ...  The aim of this work is to contribute to the development of a tactile device for visually impaired and blind persons in order to let them to understand actions of the surrounding people and to interact  ...  The disentangled unified multi-scale GCN for human action recognition This model is based on a powerful disentangled multi-scale aggregation scheme that leads to effectively capture wide joint relationships  ... 
arXiv:2201.04706v1 fatcat:ghdbdynfnnhqha7nuojwr3weay

The Human Action Image

Ricky J. Sethi, Amit K. Roy-Chowdhury
2010 2010 20th International Conference on Pattern Recognition  
Recognizing a person's motion is intuitive for humans but represents a challenging problem in machine vision. In this paper, we present a multi-disciplinary framework for recognizing human actions.  ...  We develop a novel descriptor, the Human Action Image (HAI): a physically-significant, compact representation for the motion of a person, which we derive from first principles in physics using Hamilton's  ...  GEI builds upon the approach of [2] , who proposed MEI and MHI formulations for general human movement recognition.  ... 
doi:10.1109/icpr.2010.896 dblp:conf/icpr/SethiC10a fatcat:nzmddzva55ctfcj3wr5puogaqm

Multi-view Convolutional Neural Networks for 3D Shape Recognition

Hang Su, Subhransu Maji, Evangelos Kalogerakis, Erik Learned-Miller
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
A longstanding question in computer vision concerns the representation of 3D shapes for recognition: should 3D shapes be represented with descriptors operating on their native 3D formats, such as voxel  ...  We conclude that a collection of 2D views can be highly informative for 3D shape recognition and is amenable to emerging CNN architectures and their derivatives.  ...  Acknowledgements We thank Yanjie Li for her help on rendering meshes. We thank NVIDIA for their generous donation of GPUs used in this research. Our work was partially supported by NSF (CHS-1422441).  ... 
doi:10.1109/iccv.2015.114 dblp:conf/iccv/SuMKL15 fatcat:4gyiniflprhj3pxu466yild5ku

Multi-Faceted Hierarchical Image Segmentation Taxonomy ( MFHIST)

Tilottama Goswami, Arun Agarwal, C Raghavendra Rao
2021 IEEE Access  
The paper proposes a unified way of systematic categorization of the research work on image segmentation called Multi-Faceted Hierarchical Image Segmentation Taxonomy (MFHIST), which consist of six facets  ...  Every scope is exemplified with research works from the literature for better understanding.  ...  Few such papers can be cited, such as class based segmentation [38] , defect detection for ceramic tiles industry [39] , object class recognition [40] , building classification in satellite imagery  ... 
doi:10.1109/access.2021.3055678 fatcat:r3aaee4vrbgqhdzlb6qc5vkefy

A 201.4 GOPS 496 mW Real-Time Multi-Object Recognition Processor With Bio-Inspired Neural Perception Engine

Joo-Young Kim, Minsu Kim, Seungjin Lee, Jinwook Oh, Kwanho Kim, Hoi-Jun Yoo
2010 IEEE Journal of Solid-State Circuits  
For human-like multi-object perception, a neural perception engine is proposed with biologically inspired neural networks and fuzzy logic circuits.  ...  It achieves 60 frame/sec multi-object recognition up to 10 different objects for VGA (640 480) video input while dissipating 496 mW at 1.2 V.  ...  For human-like multi-object perception, neural perception engine is proposed with biologically inspired neural networks and fuzzy logic circuits.  ... 
doi:10.1109/jssc.2009.2031768 fatcat:343tnykb7zd5dgpuz5pjdxuboi
« Previous Showing results 1 — 15 out of 7,471 results