Combined Shape Analysis of Human Poses and Motion Units for Action Segmentation and Recognition

Size: px
Start display at page:

Download "Combined Shape Analysis of Human Poses and Motion Units for Action Segmentation and Recognition"

Transcription

1 Combined Shape Analysis of Human Poses and Motion Units for Action Segmentation and Recognition Maxime Devanne 1,2, Hazem Wannous 1, Stefano Berretti 2, Pietro Pala 2, Mohamed Daoudi 1, and Alberto Del Bimbo 2 1 University Lille 1 /Télécom Lille / CRIStAL, FRANCE 2 University of Florence MICC, ITALY UHA3DS 15, May , Ljubljana, Slovenia

2 Motivation Human behavior analysis challenging task Complexity of human motions Variability of gesture combinations Local "temporal" analysis of a sequence More accurate understanding of what the human is doing Instead of analyzing the whole sequence 2

3 Goal Action segmentation Segmentation of a long sequence into different actions Sequence Walk Jump Run Action recognition Recognize the action performed by a subject in a sequence Especially deal with the failure case of gesture s repetition Action Hand waving 3

4 Cost effective depth sensor Release of cost effective depth cameras Microsoft Kinect, Asus Xtion Pro Live, Depth image in addition to the color image Skeleton estimated from depth image* Depth image Skeleton * Shotton et al. (CVPR 2011) 4

5 Skeletal representation How to represent a 3D human skeleton for action segmentation and recognition? 5

6 Skeletal representation Characterization of a human pose? Location of different body parts relative to each other (shape of pose) Human skeleton representation? Local evolution describing the relative position between various body parts. Representing a 3D human skeleton for action segmentation? Using geometric shape of a set of 3D points A set of 3D points as a curve Analyzing the shape of a curve 6

7 Shape Analysis of curves in R n Curve Representation: Square-Root Velocity Function (SRVF) * SRV Curve in R 3 F Such function q captures the shape of a curve Each function q is an element of the Riemannian manifold called Shape Space Shape comparison between curves q 1, q 2 Geodesic distance between q 1 and q 1 on the shape space S * Joshi et al. (CVPR 2007) 7

8 Pose-based Approach Human pose as a 3D curve instead of a 3D skeleton A set of 3D points (joints) connected by rods (bones) Spatial configuration Joints of each limb are connected together Representing the shape of the body Shape analysis of poses Human pose Geodesic distance between two poses represented on the Shape space 3D Curve Shape space ds q1 q2* Curve 1 Curve 2 Shape space 8

9 Pose-based Approach Motion Segmentation Sliding window technique Within each temporal window Mean pose computation: Riemannian Center of Mass Standard deviation of all poses Karcher mean computing Window p m 9

10 Pose-based Approach Motion Segmentation 10

11 From pose to segment (trajectory) Each skeletal human sequence is segmented into Motion Units What interest? How to represent and exploit MUs? 11

12 Motion Unit representation What characterizes a human motion? Pose changes in the time (segment-based) Motion representation? Temporal evolution describing the relative change between poses. Represent a motion for human action recognition? Using geometric shape of a set of skeletal postures Trajectory : set of skeletal poses Analyzing the shape of a trajectory 12

13 Action recognition by shape analysis on R n * * Devanne et al. (Trans. On Cyb. 2014)

14 Action recognition by shape analysis on Rn Limitations 14

15 Segment-based Approach Detection of periodic Motion Units Sequence : successive MUs Shape Analysis of trajectories representing MUs Distance between trajectories Periodic action segmentation Walking is a succession of «left step» and «right step» Grouping periodic MUs in same action cluster Different lengths 15

16 Experimental Results Action Segmentation 14 sequences from the CMU dataset Mocap Data Long sequences where the subject performs successively different actions Provided ground truth 16

17 Experimental Results Action Segmentation 14 sequences performed by the subject #86 Comparison with the state-of-the-art s method Hierarchical Aligned Cluster Analysis (HACA) [Zhou et al. Trans. On PAMI 14] Ground truth HACA Our Segmentation Result (4th sequence) Segmentation accuracies for 14 sequences (subject #86 ) 17

18 Segment-based Approach Action Recognition Repetition of gestures affect the recognition task Action «hammer» with? hammer strokes Removing the repeated MUs Evaluate how the repetition s removal affect the recognition accuracy Comparing with our previous work * Comparing with a method from the sate of the art * Devanne et al. (Trans. On Cyb. 2014) 18

19 Experimental Results MSR Action 3D dataset [Li et al. HCBA 2010] 20 actions performed by 10 subjects 2-3 times Gaming action without any object Cross-Subject protocol high arm wave side kick jogging Method Accuracy (%) Actionlet [Wang et al. CVPR 12] 88,2 Moving Pose [Zanfir et al. ICCV 13] 91,7 ScTPM [4] [Luo et al. ICCV 13] 93,8 Our previous [Devanne et al. Trans. On Cyb. 2014] 92,1 Our 94,3 19

20 Experimental Results MSRC-12 dataset * 12 iconic and metaphoric gestures 594 sequences of 12 gestures 30 different persons / perform each action several times Each gesture is repeated several times (from 2 to 15) Image from: * Fothergill et al. ACM CHI 2012] 20

21 Experimental Results Results: MSRC-12 dataset Only 296 sequences of 6 gestures classes Comparison with state-of-the-art s method * 5-fold leave-person-out-cross-validation (24 training & 6 test) Class DFM [*] Our previous [**] Our Duck 96, Goggles 88,0 82,0 90,0 Shoot 85,7 73,5 81,6 Throw 90,0 88,0 90,0 Change weapon 87,5 89,6 89,6 Kick 98,0 98,0 98,0 Mean 90,9 88,5 91,5 ** Devanne et al. Trans. On Cyb. 2014] *Lehrmann et al. (CVPR 2014) 21

22 Summary Segmentation of skeletal sequence into Motion Units (MUs) Shape analysis on a Riemannian manifold 3D human pose ND trajectory MUs Competitive results for the task of gesture segmentation Improvement of our previous approach for the task of action recognition Motion segmentation for: Simultaneous segmentation and action recognition (online recognition) Activity recognition Complexity of human motion is increase 22

23 Thank You Questions 23

24 References [1] A. Fod, M. J. Mataric, and O. C. Jenkins. Automated derivation of primitives for movement classification. Autonomous Robots, 2(1):39 54, Jan [2] F. Zhou, F. De la Torre, and J. K. Hodgins. Hierarchical aligned cluster analysis for temporal clustering of human motion. IEEE Trans. on Pattern Analysis and Machine Intelligence, 35(3): , Mar [3] M. Zanfir, M. Leordeanu, and C. Sminchisescu. The moving pose: An efficient 3d kinematics descriptor for low-latency action recognition and detection. In Proc. IEEE Int. Conf. on Computer Vision (ICCV), pages IEEE, [4] J. Luo, W. Wang, and H. Qi. Group sparsity and geometry constrained dictionary learning for action recognition from depth maps. In IEEE Int. Conf. on Computer Vision (ICCV), pages , [5] J. Wang, Z. Liu, Y. Wu, and J. Yuan, Mining actionlet ensemble for action recognition with depth cameras, CVPR [6] M. Devanne, H. Wannous, S. Berretti, P. Pala, M. Daoudi, and A. Del Bimbo. 3D human action recognition by shape analysis of motion trajectories on riemannian manifold. IEEE Trans. On Cybernetics, [7] A. Lehrmann, P. Gehler, and S. Nowozin. Efficient nonlinear markov models for human motion. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages , Columbus, OH, USA, June [8] S. H. Joshi, E. Klassen, A. Srivastava, and I. Jermyn, A novel representation for riemannian analysis of elastic curves in Rn, CVPR

25 Square Root Velocity Function Distance = Great cercle arc Preshape space Shape space 06/10/

26 Pose-based Approach Motion Segmentation 26

27 Proposed Approach Shape analysis of human pose in R 3 Local changes detection Sequence decomposition into motion units Shape Analysis of spatio-temporal motion units (Mus) in R 60 Detection of similar cycles of MUs Grouped for action segmentation Removed for action recognition 27

28 Skeletal representation Characterization of a human pose? how different body parts are located relative to each other (pose-based) Representation of It should be such that its local evolution directly describes the relative position between various body parts. How to represent a 3D human skeleton for action segmentation? Represent a skeleton using geometric shape of a set of 3D points A set of 3D points can be viewed as a curve Analyzing the shape of a curve 28

29 Segment-based Approach Action Recognition Repetition of gestures affect the recognition task Action «hammer» with? hammer strokes Removing the repeated MUs Keep continuity between the two extreme poses Geodesic path Shape Space 29

30 HACA Our 30

Combined Shape Analysis of Human Poses and Motion Units for Action Segmentation and Recognition

Combined Shape Analysis of Human Poses and Motion Units for Action Segmentation and Recognition Combined Shape Analysis of Human Poses and Motion Units for Action Segmentation and Recognition Maxime Devanne, Hazem Wannous, Stefano Berretti, Pietro Pala, Mohamed Daoudi, Alberto Del Bimbo To cite this

More information

3D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold

3D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold 3D Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold Maxime Devanne, Hazem Wannous, Stefano Berretti, Pietro Pala, Mohamed Daoudi, Alberto Del Bimbo To cite this

More information

Human-Object Interaction Recognition by Learning the distances between the Object and the Skeleton Joints

Human-Object Interaction Recognition by Learning the distances between the Object and the Skeleton Joints Human-Object Interaction Recognition by Learning the distances between the Object and the Skeleton Joints Meng Meng, Hassen Drira, Mohamed Daoudi, Jacques Boonaert To cite this version: Meng Meng, Hassen

More information

Skeleton-based Action Recognition Based on Deep Learning and Grassmannian Pyramids

Skeleton-based Action Recognition Based on Deep Learning and Grassmannian Pyramids Skeleton-based Action Recognition Based on Deep Learning and Grassmannian Pyramids Dimitrios Konstantinidis, Kosmas Dimitropoulos and Petros Daras ITI-CERTH, 6th km Harilaou-Thermi, 57001, Thessaloniki,

More information

Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets

Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets arxiv:1502.01228v6 [cs.cv] 28 Dec 2015 Linear-time Online Action Detection From 3D Skeletal Data Using Bags of Gesturelets Moustafa Meshry, Mohamed E. Hussein and Marwan Torki This paper is accepted for

More information

arxiv: v3 [cs.cv] 31 Mar 2017

arxiv: v3 [cs.cv] 31 Mar 2017 Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection arxiv:1607.02737v3 [cs.cv] 31 Mar 2017 Guillermo Garcia-Hernando Imperial College London ggarciah@imperial.ac.uk

More information

Scale Invariant Human Action Detection from Depth Cameras using Class Templates

Scale Invariant Human Action Detection from Depth Cameras using Class Templates Scale Invariant Human Action Detection from Depth Cameras using Class Templates Kartik Gupta and Arnav Bhavsar School of Computing and Electrical Engineering Indian Institute of Technology Mandi, India

More information

arxiv: v4 [cs.cv] 16 Oct 2015

arxiv: v4 [cs.cv] 16 Oct 2015 Alexandria, Egypt, Africa Page 1 Stats-Calculus Pose Descriptor Feeding A Discrete HMM Low-latency Detection And Recognition System For 3D Skeletal Actions arxiv:1509.09014v4 [cs.cv] 16 Oct 2015 Rofael

More information

Accurate 3D Action Recognition using Learning on the Grassmann Manifold

Accurate 3D Action Recognition using Learning on the Grassmann Manifold Accurate 3D Action Recognition using Learning on the Grassmann Manifold Rim Slama, Hazem Wannous, Mohamed Daoudi, Anuj Srivastava To cite this version: Rim Slama, Hazem Wannous, Mohamed Daoudi, Anuj Srivastava.

More information

Dynamic Human Shape Description and Characterization

Dynamic Human Shape Description and Characterization Dynamic Human Shape Description and Characterization Z. Cheng*, S. Mosher, Jeanne Smith H. Cheng, and K. Robinette Infoscitex Corporation, Dayton, Ohio, USA 711 th Human Performance Wing, Air Force Research

More information

CovP3DJ: Skeleton-parts-based-covariance Descriptor for Human Action Recognition

CovP3DJ: Skeleton-parts-based-covariance Descriptor for Human Action Recognition CovP3DJ: Skeleton-parts-based-covariance Descriptor for Human Action Recognition Hany A. El-Ghaish 1, Amin Shoukry 1,3 and Mohamed E. Hussein 2,3 1 CSE Department, Egypt-Japan University of Science and

More information

Skeleton based Human Action Recognition using Kinect

Skeleton based Human Action Recognition using Kinect Skeleton based Human Action Recognition using Kinect Ayushi Gahlot Purvi Agarwal Akshya Agarwal Vijai Singh IMS Engineering college, Amit Kumar Gautam ABSTRACT This paper covers the aspects of action recognition

More information

Person Identity Recognition on Motion Capture Data Using Label Propagation

Person Identity Recognition on Motion Capture Data Using Label Propagation Person Identity Recognition on Motion Capture Data Using Label Propagation Nikos Nikolaidis Charalambos Symeonidis AIIA Lab, Department of Informatics Aristotle University of Thessaloniki Greece email:

More information

3D Human Motion Analysis and Manifolds

3D Human Motion Analysis and Manifolds D E P A R T M E N T O F C O M P U T E R S C I E N C E U N I V E R S I T Y O F C O P E N H A G E N 3D Human Motion Analysis and Manifolds Kim Steenstrup Pedersen DIKU Image group and E-Science center Motivation

More information

Motion Analysis: Action Detection, Recognition and Evaluation based on motion capture data

Motion Analysis: Action Detection, Recognition and Evaluation based on motion capture data Motion Analysis: Action Detection, Recognition and Evaluation based on motion capture data Fotini Patrona, Anargyros Chatzitofis, Dimitrios Zarpalas, Petros Daras Information Technologies Institute, Centre

More information

TOOLS FOR ANALYZING SHAPES OF CURVES AND SURFACES. ANUJ SRIVASTAVA Department of Statistics Florida State University

TOOLS FOR ANALYZING SHAPES OF CURVES AND SURFACES. ANUJ SRIVASTAVA Department of Statistics Florida State University TOOLS FOR ANALYZING SHAPES OF CURVES AND SURFACES ANUJ SRIVASTAVA Department of Statistics Florida State University 1 MURI: INTGERATED FUSION AND SENSOR MANAGEMENT FOR ATE Innovative Front-End Processing

More information

Object Recognition 1

Object Recognition 1 Object Recognition 1 The Margaret Thatcher Illusion by Peter Thompson Lighting affects appearance The Margaret Thatcher Illusion by Peter Thompson 2 Recognition Problems Face Detection What is it? Object

More information

Object Recognition 1

Object Recognition 1 Object Recognition 1 2 Lighting affects appearance The Margaret Thatcher Illusion by Peter Thompson 3 The Margaret Thatcher Illusion by Peter Thompson 4 Recognition Problems What is it? Object detection

More information

Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations

Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations Mohamed E.

More information

Video based Animation Synthesis with the Essential Graph. Adnane Boukhayma, Edmond Boyer MORPHEO INRIA Grenoble Rhône-Alpes

Video based Animation Synthesis with the Essential Graph. Adnane Boukhayma, Edmond Boyer MORPHEO INRIA Grenoble Rhône-Alpes Video based Animation Synthesis with the Essential Graph Adnane Boukhayma, Edmond Boyer MORPHEO INRIA Grenoble Rhône-Alpes Goal Given a set of 4D models, how to generate realistic motion from user specified

More information

3D Human Motion Analysis Framework for Shape Similarity and Retrieval

3D Human Motion Analysis Framework for Shape Similarity and Retrieval 3D Human Motion Analysis Framework for Shape Similarity and Retrieval Rim Slama, Hazem Wannous, Mohamed Daoudi To cite this version: Rim Slama, Hazem Wannous, Mohamed Daoudi. 3D Human Motion Analysis Framework

More information

Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data

Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data Raviteja Vemulapalli, Rama Chellappa Center for Automation Research UMIACS, University of Maryland, College Park. Abstract Recently,

More information

EigenJoints-based Action Recognition Using Naïve-Bayes-Nearest-Neighbor

EigenJoints-based Action Recognition Using Naïve-Bayes-Nearest-Neighbor EigenJoints-based Action Recognition Using Naïve-Bayes-Nearest-Neighbor Xiaodong Yang and YingLi Tian Department of Electrical Engineering The City College of New York, CUNY {xyang02, ytian}@ccny.cuny.edu

More information

EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION. Ing. Lorenzo Seidenari

EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION. Ing. Lorenzo Seidenari EVENT DETECTION AND HUMAN BEHAVIOR RECOGNITION Ing. Lorenzo Seidenari e-mail: seidenari@dsi.unifi.it What is an Event? Dictionary.com definition: something that occurs in a certain place during a particular

More information

Analyzing and Segmenting Finger Gestures in Meaningful Phases

Analyzing and Segmenting Finger Gestures in Meaningful Phases 2014 11th International Conference on Computer Graphics, Imaging and Visualization Analyzing and Segmenting Finger Gestures in Meaningful Phases Christos Mousas Paul Newbury Dept. of Informatics University

More information

Editors. Mohamed Daoudi Anuj Srivastava Remco Veltkamp. 3D Face Modeling, Analysis and Recognition

Editors. Mohamed Daoudi Anuj Srivastava Remco Veltkamp. 3D Face Modeling, Analysis and Recognition Editors Mohamed Daoudi Anuj Srivastava Remco Veltkamp 3D Face Modeling, Analysis and Recognition 3D FACE MODELING, ANALYSIS AND RECOGNITION 3D FACE MODELING, ANALYSIS AND RECOGNITION Editors Mohamed

More information

Part I: HumanEva-I dataset and evaluation metrics

Part I: HumanEva-I dataset and evaluation metrics Part I: HumanEva-I dataset and evaluation metrics Leonid Sigal Michael J. Black Department of Computer Science Brown University http://www.cs.brown.edu/people/ls/ http://vision.cs.brown.edu/humaneva/ Motivation

More information

Recognizing Actions from Depth Cameras as Weakly Aligned Multi-Part Bag-of-Poses

Recognizing Actions from Depth Cameras as Weakly Aligned Multi-Part Bag-of-Poses 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Recognizing Actions from Depth Cameras as Weakly Aligned Multi-Part Bag-of-Poses Lorenzo Seidenari,Vincenzo Varano, Stefano Berretti,

More information

Computer Animation and Visualisation. Lecture 3. Motion capture and physically-based animation of characters

Computer Animation and Visualisation. Lecture 3. Motion capture and physically-based animation of characters Computer Animation and Visualisation Lecture 3. Motion capture and physically-based animation of characters Character Animation There are three methods Create them manually Use real human / animal motions

More information

Skeleton Based Action Recognition with Convolutional Neural Network

Skeleton Based Action Recognition with Convolutional Neural Network B G R Spatial Structure Skeleton Based Action Recognition with Convolutional Neural Network Yong Du,, Yun Fu,,, Liang Wang Center for Research on Intelligent Perception and Computing, CRIPAC Center for

More information

Human Action Recognition Using Dynamic Time Warping and Voting Algorithm (1)

Human Action Recognition Using Dynamic Time Warping and Voting Algorithm (1) VNU Journal of Science: Comp. Science & Com. Eng., Vol. 30, No. 3 (2014) 22-30 Human Action Recognition Using Dynamic Time Warping and Voting Algorithm (1) Pham Chinh Huu *, Le Quoc Khanh, Le Thanh Ha

More information

Human Body Recognition and Tracking: How the Kinect Works. Kinect RGB-D Camera. What the Kinect Does. How Kinect Works: Overview

Human Body Recognition and Tracking: How the Kinect Works. Kinect RGB-D Camera. What the Kinect Does. How Kinect Works: Overview Human Body Recognition and Tracking: How the Kinect Works Kinect RGB-D Camera Microsoft Kinect (Nov. 2010) Color video camera + laser-projected IR dot pattern + IR camera $120 (April 2012) Kinect 1.5 due

More information

3D-based Deep Convolutional Neural Network for Action Recognition with Depth Sequences

3D-based Deep Convolutional Neural Network for Action Recognition with Depth Sequences 3D-based Deep Convolutional Neural Network for Action Recognition with Depth Sequences Zhi Liu a, Chenyang Zhang b, Yingli Tian b a College of Computer Science and Engineering, Chongqing University of

More information

The Kinect Sensor. Luís Carriço FCUL 2014/15

The Kinect Sensor. Luís Carriço FCUL 2014/15 Advanced Interaction Techniques The Kinect Sensor Luís Carriço FCUL 2014/15 Sources: MS Kinect for Xbox 360 John C. Tang. Using Kinect to explore NUI, Ms Research, From Stanford CS247 Shotton et al. Real-Time

More information

Real-Time Continuous Action Detection and Recognition Using Depth Images and Inertial Signals

Real-Time Continuous Action Detection and Recognition Using Depth Images and Inertial Signals Real-Time Continuous Action Detection and Recognition Using Depth Images and Inertial Signals Neha Dawar 1, Chen Chen 2, Roozbeh Jafari 3, Nasser Kehtarnavaz 1 1 Department of Electrical and Computer Engineering,

More information

Expanding gait identification methods from straight to curved trajectories

Expanding gait identification methods from straight to curved trajectories Expanding gait identification methods from straight to curved trajectories Yumi Iwashita, Ryo Kurazume Kyushu University 744 Motooka Nishi-ku Fukuoka, Japan yumi@ieee.org Abstract Conventional methods

More information

GRAPH-BASED APPROACH FOR MOTION CAPTURE DATA REPRESENTATION AND ANALYSIS. Jiun-Yu Kao, Antonio Ortega, Shrikanth S. Narayanan

GRAPH-BASED APPROACH FOR MOTION CAPTURE DATA REPRESENTATION AND ANALYSIS. Jiun-Yu Kao, Antonio Ortega, Shrikanth S. Narayanan GRAPH-BASED APPROACH FOR MOTION CAPTURE DATA REPRESENTATION AND ANALYSIS Jiun-Yu Kao, Antonio Ortega, Shrikanth S. Narayanan University of Southern California Department of Electrical Engineering ABSTRACT

More information

Terry Taewoong Um. Terry T. Um and Dana Kulić. University of Waterloo. Department of Electrical & Computer Engineering

Terry Taewoong Um. Terry T. Um and Dana Kulić. University of Waterloo. Department of Electrical & Computer Engineering AN UNSUPERVISED APPROACH TO DETECTING AND ISOLATING ATHLETIC MOVEMENTS Terry T. Um and Dana Kulić University of Waterloo Department of Electrical & Computer Engineering Terry Taewoong Um Terry Taewoong

More information

3D Pose Estimation using Synthetic Data over Monocular Depth Images

3D Pose Estimation using Synthetic Data over Monocular Depth Images 3D Pose Estimation using Synthetic Data over Monocular Depth Images Wei Chen cwind@stanford.edu Xiaoshi Wang xiaoshiw@stanford.edu Abstract We proposed an approach for human pose estimation over monocular

More information

Learning features combination for human action recognition from skeleton sequences

Learning features combination for human action recognition from skeleton sequences Learning features combination for human action recognition from skeleton sequences Diogo Carbonera Luvizon, Hedi Tabia, David Picard To cite this version: Diogo Carbonera Luvizon, Hedi Tabia, David Picard.

More information

HUMAN action recognition is an important problem in

HUMAN action recognition is an important problem in SUBMITTED TO IEEE TRANSACTIONS ON CYBERNETICS, VOL. X, NO. X, X 2016 (WILL BE INSERTED BY THE EDITOR) 1 Action Recognition Based on Joint Trajectory Maps with Convolutional Neural Networks Pichao Wang,

More information

STOP: Space-Time Occupancy Patterns for 3D Action Recognition from Depth Map Sequences

STOP: Space-Time Occupancy Patterns for 3D Action Recognition from Depth Map Sequences STOP: Space-Time Occupancy Patterns for 3D Action Recognition from Depth Map Sequences Antonio W. Vieira 1,2,EricksonR.Nascimento 1, Gabriel L. Oliveira 1, Zicheng Liu 3,andMarioF.M.Campos 1, 1 DCC - Universidade

More information

3D Human Video Retrieval: from Pose to Motion Matching

3D Human Video Retrieval: from Pose to Motion Matching Author manuscript, published in "Eurographics Workshop on 3D Object Retrieval, Girona : Spain (2013)" 3D Human Video Retrieval: from Pose to Motion Matching R. Slama 1,2, H. Wannous 1,2 and M. Daoudi 2,3

More information

arxiv: v2 [cs.cv] 13 Nov 2016

arxiv: v2 [cs.cv] 13 Nov 2016 Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks Pichao Wang 1, Zhaoyang Li 2, Yonghong Hou 2 and Wanqing Li 1 1 Advanced Multimedia Research Lab, University of Wollongong,

More information

Classification of RGB-D and Motion Capture Sequences Using Extreme Learning Machine

Classification of RGB-D and Motion Capture Sequences Using Extreme Learning Machine Classification of RGB-D and Motion Capture Sequences Using Extreme Learning Machine Xi Chen and Markus Koskela Department of Information and Computer Science Aalto University School of Science P.O. Box

More information

Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting

Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting R. Maier 1,2, K. Kim 1, D. Cremers 2, J. Kautz 1, M. Nießner 2,3 Fusion Ours 1

More information

AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering

AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering AUTOMATIC 3D HUMAN ACTION RECOGNITION Ajmal Mian Associate Professor Computer Science & Software Engineering www.csse.uwa.edu.au/~ajmal/ Overview Aim of automatic human action recognition Applications

More information

Edge Enhanced Depth Motion Map for Dynamic Hand Gesture Recognition

Edge Enhanced Depth Motion Map for Dynamic Hand Gesture Recognition 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Edge Enhanced Depth Motion Map for Dynamic Hand Gesture Recognition Chenyang Zhang and Yingli Tian Department of Electrical Engineering

More information

Adaptive Action Detection

Adaptive Action Detection Adaptive Action Detection Illinois Vision Workshop Dec. 1, 2009 Liangliang Cao Dept. ECE, UIUC Zicheng Liu Microsoft Research Thomas Huang Dept. ECE, UIUC Motivation Action recognition is important in

More information

Understanding Sport Activities from Correspondences of Clustered Trajectories

Understanding Sport Activities from Correspondences of Clustered Trajectories Understanding Sport Activities from Correspondences of Clustered Trajectories Francesco Turchini, Lorenzo Seidenari, Alberto Del Bimbo http://www.micc.unifi.it/vim Introduction The availability of multimedia

More information

Extremal Human Curves: a New Human Body Shape and Pose Descriptor

Extremal Human Curves: a New Human Body Shape and Pose Descriptor Extremal Human Curves: a New Human Body Shape and Pose Descriptor Rim Slama, Hazem Wannous and Mohamed Daoudi Abstract Automatic estimation of 3D shape similarity from video is a very important factor

More information

Sign Language Recognition using Dynamic Time Warping and Hand Shape Distance Based on Histogram of Oriented Gradient Features

Sign Language Recognition using Dynamic Time Warping and Hand Shape Distance Based on Histogram of Oriented Gradient Features Sign Language Recognition using Dynamic Time Warping and Hand Shape Distance Based on Histogram of Oriented Gradient Features Pat Jangyodsuk Department of Computer Science and Engineering The University

More information

Human Activities Recognition Based on Skeleton Information via Sparse Representation

Human Activities Recognition Based on Skeleton Information via Sparse Representation Regular Paper Journal of Computing Science and Engineering, Vol. 12, No. 1, March 2018, pp. 1-11 Human Activities Recognition Based on Skeleton Information via Sparse Representation Suolan Liu School of

More information

A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models

A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models Emanuele Ruffaldi Lorenzo Peppoloni Alessandro Filippeschi Carlo Alberto Avizzano 2014 IEEE International

More information

Magnifying subtle facial motions for 4D Expression Recognition

Magnifying subtle facial motions for 4D Expression Recognition Magnifying subtle facial motions for 4D Expression Recognition Qingkai Zhen, Di Huang, Yunhong Wang, Hassen Drira, Ben Boulbaba, Mohamed Daoudi To cite this version: Qingkai Zhen, Di Huang, Yunhong Wang,

More information

Mining 3D Key-Pose-Motifs for Action Recognition

Mining 3D Key-Pose-Motifs for Action Recognition Mining 3D Key-Pose-Motifs for Action Recognition Chunyu Wang, Yizhou Wang, and Alan L. Yuille 2 Nat l Eng. Lab. for Video Technology, Cooperative Medianet Innovation Center Key Lab. of Machine Perception

More information

Arm-hand Action Recognition Based on 3D Skeleton Joints Ling RUI 1, Shi-wei MA 1,a, *, Jia-rui WEN 1 and Li-na LIU 1,2

Arm-hand Action Recognition Based on 3D Skeleton Joints Ling RUI 1, Shi-wei MA 1,a, *, Jia-rui WEN 1 and Li-na LIU 1,2 1 International Conference on Control and Automation (ICCA 1) ISBN: 97-1-9-39- Arm-hand Action Recognition Based on 3D Skeleton Joints Ling RUI 1, Shi-wei MA 1,a, *, Jia-rui WEN 1 and Li-na LIU 1, 1 School

More information

Thiruvarangan Ramaraj CS525 Graphics & Scientific Visualization Spring 2007, Presentation I, February 28 th 2007, 14:10 15:00. Topic (Research Paper):

Thiruvarangan Ramaraj CS525 Graphics & Scientific Visualization Spring 2007, Presentation I, February 28 th 2007, 14:10 15:00. Topic (Research Paper): Thiruvarangan Ramaraj CS525 Graphics & Scientific Visualization Spring 2007, Presentation I, February 28 th 2007, 14:10 15:00 Topic (Research Paper): Jinxian Chai and Jessica K. Hodgins, Performance Animation

More information

Dynamic hand gesture recognition based on 3D pattern assembled trajectories

Dynamic hand gesture recognition based on 3D pattern assembled trajectories Dynamic hand gesture recognition based on 3D pattern assembled trajectories Said Yacine Boulahia, Eric Anquetil, Franck Multon, Richard Kulpa To cite this version: Said Yacine Boulahia, Eric Anquetil,

More information

Applications. Systems. Motion capture pipeline. Biomechanical analysis. Graphics research

Applications. Systems. Motion capture pipeline. Biomechanical analysis. Graphics research Motion capture Applications Systems Motion capture pipeline Biomechanical analysis Graphics research Applications Computer animation Biomechanics Robotics Cinema Video games Anthropology What is captured?

More information

TOWARDS SIGN LANGUAGE RECOGNITION BASED ON BODY PARTS RELATIONS

TOWARDS SIGN LANGUAGE RECOGNITION BASED ON BODY PARTS RELATIONS TOWARDS SIGN LANGUAGE RECOGNITION BASED ON BODY PARTS RELATIONS M. Martinez-Camarena Universidad Politecnica de Valencia J. Oramas M., T. Tuytelaars KU Leuven, ESAT-PSI, iminds ABSTRACT Over the years,

More information

Dense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm

Dense Tracking and Mapping for Autonomous Quadrocopters. Jürgen Sturm Computer Vision Group Prof. Daniel Cremers Dense Tracking and Mapping for Autonomous Quadrocopters Jürgen Sturm Joint work with Frank Steinbrücker, Jakob Engel, Christian Kerl, Erik Bylow, and Daniel Cremers

More information

Dynamic Time Warping for Binocular Hand Tracking and Reconstruction

Dynamic Time Warping for Binocular Hand Tracking and Reconstruction Dynamic Time Warping for Binocular Hand Tracking and Reconstruction Javier Romero, Danica Kragic Ville Kyrki Antonis Argyros CAS-CVAP-CSC Dept. of Information Technology Institute of Computer Science KTH,

More information

REJECTION-BASED CLASSIFICATION FOR ACTION RECOGNITION USING A SPATIO-TEMPORAL DICTIONARY. Stefen Chan Wai Tim, Michele Rombaut, Denis Pellerin

REJECTION-BASED CLASSIFICATION FOR ACTION RECOGNITION USING A SPATIO-TEMPORAL DICTIONARY. Stefen Chan Wai Tim, Michele Rombaut, Denis Pellerin REJECTION-BASED CLASSIFICATION FOR ACTION RECOGNITION USING A SPATIO-TEMPORAL DICTIONARY Stefen Chan Wai Tim, Michele Rombaut, Denis Pellerin Univ. Grenoble Alpes, GIPSA-Lab, F-38000 Grenoble, France ABSTRACT

More information

Graph-Based Action Models for Human Motion Classification

Graph-Based Action Models for Human Motion Classification Graph-Based Action Models for Human Motion Classification Felix Endres Jürgen Hess Wolfram Burgard University of Freiburg, Dept. of Computer Science, Freiburg, Germany Abstract Recognizing human actions

More information

Generating Different Realistic Humanoid Motion

Generating Different Realistic Humanoid Motion Generating Different Realistic Humanoid Motion Zhenbo Li,2,3, Yu Deng,2,3, and Hua Li,2,3 Key Lab. of Computer System and Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing

More information

Improving Surface Normals Based Action Recognition in Depth Images

Improving Surface Normals Based Action Recognition in Depth Images Improving Surface Normals Based Action Recognition in Depth Images Xuan Nguyen, Thanh Nguyen, François Charpillet To cite this version: Xuan Nguyen, Thanh Nguyen, François Charpillet. Improving Surface

More information

Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization

Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization Journal of Computer Science 6 (9): 1008-1013, 2010 ISSN 1549-3636 2010 Science Publications Support Vector Machine-Based Human Behavior Classification in Crowd through Projection and Star Skeletonization

More information

Action Recognition in Video by Sparse Representation on Covariance Manifolds of Silhouette Tunnels

Action Recognition in Video by Sparse Representation on Covariance Manifolds of Silhouette Tunnels Action Recognition in Video by Sparse Representation on Covariance Manifolds of Silhouette Tunnels Kai Guo, Prakash Ishwar, and Janusz Konrad Department of Electrical & Computer Engineering Motivation

More information

Action Recognition & Categories via Spatial-Temporal Features

Action Recognition & Categories via Spatial-Temporal Features Action Recognition & Categories via Spatial-Temporal Features 华俊豪, 11331007 huajh7@gmail.com 2014/4/9 Talk at Image & Video Analysis taught by Huimin Yu. Outline Introduction Frameworks Feature extraction

More information

Fast and precise kinematic skeleton extraction of 3D dynamic meshes

Fast and precise kinematic skeleton extraction of 3D dynamic meshes Fast and precise kinematic skeleton extraction of 3D dynamic meshes Julien Tierny, Jean-Philippe Vandeborre, Mohamed Daoudi To cite this version: Julien Tierny, Jean-Philippe Vandeborre, Mohamed Daoudi.

More information

Human Activity Recognition Process Using 3-D Posture Data

Human Activity Recognition Process Using 3-D Posture Data Human Activity Recognition Process Using 3-D Posture Data G.Nandini PG Scholar, Dept of ECE, PVKK Institute of Technology, Anantapur, AP, India. K.Naveen Kumar Associate Professor, Dept of ECE, PVKK Institute

More information

J. Vis. Commun. Image R.

J. Vis. Commun. Image R. J. Vis. Commun. Image R. 25 (2014) 2 11 Contents lists available at SciVerse ScienceDirect J. Vis. Commun. Image R. journal homepage: www.elsevier.com/locate/jvci Effective 3D action recognition using

More information

Markerless human motion capture through visual hull and articulated ICP

Markerless human motion capture through visual hull and articulated ICP Markerless human motion capture through visual hull and articulated ICP Lars Mündermann lmuender@stanford.edu Stefano Corazza Stanford, CA 93405 stefanoc@stanford.edu Thomas. P. Andriacchi Bone and Joint

More information

HUMAN action recognition has received increasing attention

HUMAN action recognition has received increasing attention SUBMITTED TO IEEE SIGNAL PROCESSING LETTERS, 2016 1 SkeletonNet: Mining Deep Part Features for 3D Action Recognition Qiuhong Ke, Senjian An, Mohammed Bennamoun, Ferdous Sohel, and Farid Boussaid Abstract

More information

HUMAN action recognition [1] [3] is a long standing. Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition

HUMAN action recognition [1] [3] is a long standing. Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition JOURNAL OF L A TEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition Jian Liu, Naveed Akhtar, and Ajmal Mian arxiv:1711.05941v4

More information

Human Upper Body Pose Estimation in Static Images

Human Upper Body Pose Estimation in Static Images 1. Research Team Human Upper Body Pose Estimation in Static Images Project Leader: Graduate Students: Prof. Isaac Cohen, Computer Science Mun Wai Lee 2. Statement of Project Goals This goal of this project

More information

Mining Actionlet Ensemble for Action Recognition with Depth Cameras

Mining Actionlet Ensemble for Action Recognition with Depth Cameras Mining Actionlet Ensemble for Action Recognition with Depth Cameras Jiang Wang 1 Zicheng Liu 2 Ying Wu 1 Junsong Yuan 3 jwa368@eecs.northwestern.edu zliu@microsoft.com yingwu@northwestern.edu jsyuan@ntu.edu.sg

More information

Pose Estimation on Depth Images with Convolutional Neural Network

Pose Estimation on Depth Images with Convolutional Neural Network Pose Estimation on Depth Images with Convolutional Neural Network Jingwei Huang Stanford University jingweih@stanford.edu David Altamar Stanford University daltamar@stanford.edu Abstract In this paper

More information

Curve Matching from the View of Manifold for Sign Language Recognition

Curve Matching from the View of Manifold for Sign Language Recognition Curve Matching from the View of Manifold for Sign Language Recognition Yushun Lin 1,2, Xiujuan Chai 1, Yu Zhou 3, and Xilin Chen 1 1 Key Lab of Intelligent Information Processing of Chinese Academy of

More information

A Survey of Human Action Recognition Approaches that use an RGB-D Sensor

A Survey of Human Action Recognition Approaches that use an RGB-D Sensor IEIE Transactions on Smart Processing and Computing, vol. 4, no. 4, August 2015 http://dx.doi.org/10.5573/ieiespc.2015.4.4.281 281 EIE Transactions on Smart Processing and Computing A Survey of Human Action

More information

Learning Semantic Environment Perception for Cognitive Robots

Learning Semantic Environment Perception for Cognitive Robots Learning Semantic Environment Perception for Cognitive Robots Sven Behnke University of Bonn, Germany Computer Science Institute VI Autonomous Intelligent Systems Some of Our Cognitive Robots Equipped

More information

Human Action Recognition via Fused Kinematic Structure and Surface Representation

Human Action Recognition via Fused Kinematic Structure and Surface Representation University of Denver Digital Commons @ DU Electronic Theses and Dissertations Graduate Studies 8-1-2013 Human Action Recognition via Fused Kinematic Structure and Surface Representation Salah R. Althloothi

More information

Gesture Recognition: Hand Pose Estimation. Adrian Spurr Ubiquitous Computing Seminar FS

Gesture Recognition: Hand Pose Estimation. Adrian Spurr Ubiquitous Computing Seminar FS Gesture Recognition: Hand Pose Estimation Adrian Spurr Ubiquitous Computing Seminar FS2014 27.05.2014 1 What is hand pose estimation? Input Computer-usable form 2 Augmented Reality Gaming Robot Control

More information

Robust Classification of Human Actions from 3D Data

Robust Classification of Human Actions from 3D Data Robust Classification of Human s from 3D Data Loc Huynh, Thanh Ho, Quang Tran, Thang Ba Dinh, Tien Dinh Faculty of Information Technology University of Science Ho Chi Minh City, Vietnam hvloc@apcs.vn,

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

CS Decision Trees / Random Forests

CS Decision Trees / Random Forests CS548 2015 Decision Trees / Random Forests Showcase by: Lily Amadeo, Bir B Kafle, Suman Kumar Lama, Cody Olivier Showcase work by Jamie Shotton, Andrew Fitzgibbon, Richard Moore, Mat Cook, Alex Kipman,

More information

Action Recognition Using Motion History Image and Static History Image-based Local Binary Patterns

Action Recognition Using Motion History Image and Static History Image-based Local Binary Patterns , pp.20-214 http://dx.doi.org/10.14257/ijmue.2017.12.1.17 Action Recognition Using Motion History Image and Static History Image-based Local Binary Patterns Enqing Chen 1, Shichao Zhang* 1 and Chengwu

More information

HUMAN ACTIVITY RECOGNITION AND GYMNASTICS ANALYSIS THROUGH DEPTH IMAGERY

HUMAN ACTIVITY RECOGNITION AND GYMNASTICS ANALYSIS THROUGH DEPTH IMAGERY HUMAN ACTIVITY RECOGNITION AND GYMNASTICS ANALYSIS THROUGH DEPTH IMAGERY by Brian J. Reily A thesis submitted to the Faculty and the Board of Trustees of the Colorado School of Mines in partial fulfillment

More information

An Approach for Reduction of Rain Streaks from a Single Image

An Approach for Reduction of Rain Streaks from a Single Image An Approach for Reduction of Rain Streaks from a Single Image Vijayakumar Majjagi 1, Netravati U M 2 1 4 th Semester, M. Tech, Digital Electronics, Department of Electronics and Communication G M Institute

More information

Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview

Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview Nonlinear State Estimation for Robotics and Computer Vision Applications: An Overview Arun Das 05/09/2017 Arun Das Waterloo Autonomous Vehicles Lab Introduction What s in a name? Arun Das Waterloo Autonomous

More information

Articulated Pose Estimation with Flexible Mixtures-of-Parts

Articulated Pose Estimation with Flexible Mixtures-of-Parts Articulated Pose Estimation with Flexible Mixtures-of-Parts PRESENTATION: JESSE DAVIS CS 3710 VISUAL RECOGNITION Outline Modeling Special Cases Inferences Learning Experiments Problem and Relevance Problem:

More information

Recognizing Human Activities in Video by Multi-resolutional Optical Flows

Recognizing Human Activities in Video by Multi-resolutional Optical Flows Recognizing Human Activities in Video by Multi-resolutional Optical Flows Toru Nakata Digital Human Research Center, National Institute of Advanced Industrial Science and Technology (AIST). Also Core Research

More information

Class 9 Action Recognition

Class 9 Action Recognition Class 9 Action Recognition Liangliang Cao, April 4, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Visual Recognition

More information

Hand gesture recognition with Leap Motion and Kinect devices

Hand gesture recognition with Leap Motion and Kinect devices Hand gesture recognition with Leap Motion and devices Giulio Marin, Fabio Dominio and Pietro Zanuttigh Department of Information Engineering University of Padova, Italy Abstract The recent introduction

More information

3D Shape Analysis with Multi-view Convolutional Networks. Evangelos Kalogerakis

3D Shape Analysis with Multi-view Convolutional Networks. Evangelos Kalogerakis 3D Shape Analysis with Multi-view Convolutional Networks Evangelos Kalogerakis 3D model repositories [3D Warehouse - video] 3D geometry acquisition [KinectFusion - video] 3D shapes come in various flavors

More information

Feature Weighting in Dynamic Time Warping for Gesture Recognition in Depth Data

Feature Weighting in Dynamic Time Warping for Gesture Recognition in Depth Data Feature Weighting in Dynamic Time Warping for Gesture Recognition in Depth Data Miguel Reyes Dept. Matemàtica Aplicada i Anàlisi, Universitat de Barcelona Gran Via de les Corts Catalanes 585, 08007, Barcelona,

More information

Motion Sensors for Activity Recognition in an Ambient-Intelligence Scenario

Motion Sensors for Activity Recognition in an Ambient-Intelligence Scenario 5th International Workshop on Smart Environments and Ambient Intelligence 2013, San Diego (22 March 2013) Motion Sensors for Activity Recognition in an Ambient-Intelligence Scenario Pietro Cottone, Giuseppe

More information

Construction Progress Management and Interior Work Analysis Using Kinect 3D Image Sensors

Construction Progress Management and Interior Work Analysis Using Kinect 3D Image Sensors 33 rd International Symposium on Automation and Robotics in Construction (ISARC 2016) Construction Progress Management and Interior Work Analysis Using Kinect 3D Image Sensors Kosei Ishida 1 1 School of

More information

Motion Synthesis and Editing. Yisheng Chen

Motion Synthesis and Editing. Yisheng Chen Motion Synthesis and Editing Yisheng Chen Overview Data driven motion synthesis automatically generate motion from a motion capture database, offline or interactive User inputs Large, high-dimensional

More information