583 Hits in 3.4 sec

Human action recognition using Lagrangian descriptors

Esra Acar, Tobias Senst, Alexander Kuhn, Ivo Keller, Holger Theisel, Sahin Albayrak, Thomas Sikora
2012 2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP)  
The results demonstrate that our approach is promising and that human action recognition performance is improved by fusing Lagrangian measures.  ...  Human action recognition requires the description of complex motion patterns in image sequences. In general, these patterns span varying temporal scales.  ...  CONCLUSIONS AND FUTURE WORK We presented a framework based on Lagrangian methods which makes use of FTLE and time-normalized arc length measures for human action recognition.  ... 
doi:10.1109/mmsp.2012.6343469 dblp:conf/mmsp/AcarSKKTAS12 fatcat:fleel55fh5gvhiyrjogxjcdphy

The Human Action Image

Ricky J. Sethi, Amit K. Roy-Chowdhury
2010 2010 20th International Conference on Pattern Recognition  
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  ...  Action. 1 We embed the HAI as the Motion Energy Pathway of the latest Neurobiological model of motion recognition.  ...  The HAI can be used to recognize individuals on the basis of their gait as well as human actions, in general; therefore, it is a descriptor for human motion as well as gait.  ... 
doi:10.1109/icpr.2010.896 dblp:conf/icpr/SethiC10a fatcat:nzmddzva55ctfcj3wr5puogaqm

Clustered Multi-task Linear Discriminant Analysis for View Invariant Color-Depth Action Recognition

Yan Yan, Elisa Ricci, Gaowen Liu, Ramanathan Subramanian, Nicu Sebe
2014 2014 22nd International Conference on Pattern Recognition  
In this paper we focus on the specific problem of action recognition under view point changes and propose a novel approach for view-invariant action recognition operating jointly on visual data of color  ...  The widespread adoption of low-cost depth cameras has opened new opportunities to improve traditional action recognition systems.  ...  In this paper we propose a novel approach for multi-view action recognition where SSM descriptors are used within a multi-task learning framework.  ... 
doi:10.1109/icpr.2014.601 dblp:conf/icpr/YanRLSS14 fatcat:y4l67fn6lrfb7dsdadkukglsw4

Action Recognition Using Low-Rank Sparse Representation

Shilei CHENG, Song GU, Maoquan YE, Mei XIE
2018 IEICE transactions on information and systems  
Human action recognition in videos draws huge research interests in computer vision.  ...  key words: human action recognition, low-rank sparse representation, bag of word model, sparse coding representation, low-rank representation  ...  Introduction Human action recognition has been an important topic in the field of computer vision.  ... 
doi:10.1587/transinf.2017edl8176 fatcat:yrxrifkubfhy3hhfr2udxupa6y

A Local Feature based on Lagrangian Measures for Violent Video Classification

T. Senst, V. Eiselein, T. Sikora
2015 6th International Conference on Imaging for Crime Prevention and Detection (ICDP-15)  
We will show that the temporal interval of the used motion information is a crucial aspect and study its influence on the classification performance.  ...  Lagrangian theory provides a diverse set of tools for continuous motion analysis. Existing work shows the applicability of Lagrangian method for video analysis in several aspects.  ...  In our previous work we have extended this field of applications and shown that Lagrangian methods are also an valuable tool on a microscopic level e.g for human action recognition [2] and people carrying  ... 
doi:10.1049/ic.2015.0104 dblp:conf/icdp/SenstES15 fatcat:4ovmgt2a3ngvbkt4d6b2cqz75m

The human action image and its application to motion recognition

Ricky J. Sethi, Amit K. Roy-Chowdhury
2010 Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing - ICVGIP '10  
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 Hamilton's Action. 1 We prove the additivity  ...  The Form Pathway is modelled using existing low-level feature descriptors based on shape and appearance.  ...  Our HAI can be used to recognize individuals on the basis of their gait as well as human actions, in general; therefore, it is a descriptor for human motion as well as gait.  ... 
doi:10.1145/1924559.1924560 dblp:conf/icvgip/SethiC10 fatcat:fduyxt6sinh4pikka7j2x5bfku

Efficient Sparse Representation based Action Recognition in video

2019 International Journal of Engineering and Advanced Technology  
Human Action Recognition (HAR) is an interesting and helpful topic in various real-life applications such as surveillance based security system, computer vision and robotics.  ...  To refine the sparse representation the max pooling method is used and the action recognition is performed using SVM classifier. The proposed approach outperforms on the benchmark datasets.  ...  The ability of the computer system in identifying the human actions performed in a video is known as human action recognition.  ... 
doi:10.35940/ijeat.b2950.129219 fatcat:q3zx53su7naaplxdl2zvfz4r7u

Laplacian one class extreme learning machines for human action recognition

Vasileios Mygdalis, Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas
2016 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)  
ACKNOWLEDGEMENT The research leading to these results has been supported by COST, Action IC1206 and the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement number 316564 (IMPART  ...  INTRODUCTION Human action recognition is a widely studied classification problem, due to its importance in media industry applications, such as semantic video annotation, human-computer interaction, movie  ...  In this paper, a novel OCC method for human action recognition namely the Laplacian One Class Extreme Learning Machines is presented.  ... 
doi:10.1109/mmsp.2016.7813387 dblp:conf/mmsp/MygdalisITP16 fatcat:rqzkfushjrdllpoweqc2ipo4kq

Shift Invariant Dictionary Learning for Human Action Recognition

To solve this issue, the shift-invariant dictionary is used for action recognition in this work.  ...  The advantage of the proposed SID based action recognition method is that it requires minimum training time and achieves highest accuracy.  ...  The sparse coding problem is solved efficiently using generalized lagrangian multiplier method.  ... 
doi:10.35940/ijitee.b7005.129219 fatcat:6kq7ivnwzfdxdfu2mvzz2uanoy

Camera Motion and Surrounding Scene Appearance as Context for Action Recognition [chapter]

Fabian Caba Heilbron, Ali Thabet, Juan Carlos Niebles, Bernard Ghanem
2015 Lecture Notes in Computer Science  
This paper describes a framework for recognizing human actions in videos by incorporating a new set of visual cues that represent the context of the action.  ...  motion that interestingly is shown to be discriminative for certain action classes.  ...  [32] propose the use of Lagrangian point trajectories for action description in videos captured by moving cameras.  ... 
doi:10.1007/978-3-319-16817-3_38 fatcat:b4ll7boarfgohcyrza3lfh4obm

A Novel Spatio-Temporal Violence Classification Framework Based on Material Derivative and LSTM Neural Network

Wafa Lejmi, Anouar Ben Khalifa, Mohamed Ali Mahjoub
2020 Traitement du signal  
In the current era, the implementation of automated security video surveillance systems is particularly needy in terms of human violence recognition.  ...  The obtained results are promising and show that the proposed model can be potentially useful for detecting human violence.  ...  [48] used various Trace transform functionals to compute robust features for human action recognition that are efficient and invariant to scaling.  ... 
doi:10.18280/ts.370501 fatcat:wtqbfu3jcvawjlnjvebpol6piq

Machine Learning Model for Group Activity Recognition Based on Discriminative Interaction Contextual Relationship

Smita S. Kulkarni, Sangeeta Jadhav, Essam Houssein
2021 Mathematical Problems in Engineering  
The descriptor was developed by integrating the focal person action descriptor and interaction joint context descriptor of nearby people in the video frame.  ...  This paper proposed a model that formulates a group action context (GAC) descriptor.  ...  activity recognition method. us, the group action context (GAC) descriptor is formulated from the people interaction in a scene and then this descriptor is classified into group activity category by using  ... 
doi:10.1155/2021/5596312 fatcat:6ybibswtsjbilj5on2ayzctacy

3D Human Action Recognition using Hu Moment Invariants and Euclidean Distance Classifier

Fadwa Al-Azzo, Arwa Mohammed, Mariofanna Milanova
2017 International Journal of Advanced Computer Science and Applications  
This paper presents a new model of scale, rotation, and translations invariant interest point descriptor for human actions recognition.  ...  The proposed approach deals with raw input human action video sequences.  ...  Many specialized algorithms have been advanced for human action recognition.  ... 
doi:10.14569/ijacsa.2017.080403 fatcat:2paoecaajzbjjelbrlokzypv5i

Human action recognition based on deep network and feature fusion

Dongli Wang, Jun Yang, Yan Zhou, Zhen Zhou
2020 Filomat  
Feature representation is of vital importance for human action recognition. In recent few years, the application of deep learning in action recognition has become popular.  ...  However, for action recognition in videos, the advantage of single convolution feature over traditional methods is not so evident.  ...  Conclusion In this paper, a new representative descriptor has proposed for human action recognition on realistic datasets.  ... 
doi:10.2298/fil2015967w fatcat:pzrts6vdc5eq7ku5tgfhsu623m

Combining Per-frame and Per-track Cues for Multi-person Action Recognition [chapter]

Sameh Khamis, Vlad I. Morariu, Larry S. Davis
2012 Lecture Notes in Computer Science  
We propose a model to combine per-frame and per-track cues for action recognition.  ...  Finally, we improve on the stateof-the-art action recognition results for two publicly available datasets.  ...  Introduction We introduce a novel framework for human action recognition from videos.  ... 
doi:10.1007/978-3-642-33718-5_9 fatcat:hji47lhygfbgvdymul2pv4fuui
« Previous Showing results 1 — 15 out of 583 results