Robust Recognition and Segmentation of Human Actions Using HMMs with Missing Observations

被引:0
|
作者
Patrick Peursum
Hung H. Bui
Svetha Venkatesh
Geoff West
机构
[1] Curtin University of Technology,Department of Computing
[2] SRI International,Artificial Intelligence Center
来源
EURASIP Journal on Advances in Signal Processing | / 2005卷
关键词
human motion analysis; action segmentation; HMMs;
D O I
暂无
中图分类号
学科分类号
摘要
This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation. Based on this framework, a model is trained to automatically segment and classify an activity sequence into its constituent subactions during inferencing. This is achieved by introducing action labels into the observation vector and setting these labels as missing data during inferencing, thus forcing the system to infer the probability of each action label. Additionally, missing data provides recognition-level support for occlusions and imperfect silhouette segmentation, permitting the use of a fast (real-time) pose estimation that delegates the burden of handling undetected limbs onto the action recognition system. Findings show that the use of missing data to segment activities is an accurate and elegant approach. Furthermore, action recognition can be accurate even when almost half of the pose feature data is missing due to occlusions, since not all of the pose data is important all of the time.
引用
收藏
相关论文
共 50 条
  • [21] Simultaneous gesture segmentation and recognition based on forward spotting accumulative HMMs
    Song, Jinyoung
    Kim, Daijin
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 1231 - +
  • [22] Depth Silhouettes Context: A New Robust Feature for Human Tracking and Activity Recognition based on Embedded HMMs
    Jalal, Ahmad
    Kamal, Shaharyar
    Kim, Daijin
    2015 12TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS AND AMBIENT INTELLIGENCE (URAI), 2015, : 294 - 299
  • [23] Recognition of human actions using texture descriptors
    Vili Kellokumpu
    Guoying Zhao
    Matti Pietikäinen
    Machine Vision and Applications, 2011, 22 : 767 - 780
  • [24] Recognition of human actions using texture descriptors
    Kellokumpu, Vili
    Zhao, Guoying
    Pietikainen, Matti
    MACHINE VISION AND APPLICATIONS, 2011, 22 (05) : 767 - 780
  • [25] Soccer highlights detection and recognition using HMMs
    Assfalg, J
    Bertini, M
    Del Bimbo, A
    Nunziati, W
    Pala, P
    IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL I AND II, PROCEEDINGS, 2002, : 825 - 828
  • [26] Handwritten Digit Recognition using DCT and HMMs
    Ali, Syed Salman
    Ghani, Muhammad Usman
    PROCEEDINGS OF 2014 12TH INTERNATIONAL CONFERENCE ON FRONTIERS OF INFORMATION TECHNOLOGY, 2014, : 303 - 306
  • [27] Recognition of Human Actions By using Depth Information
    Keceli, Ali Seydi
    Can, Ahmet Burak
    2013 21ST SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2013,
  • [28] Feature Space Generalized Variable Parameter HMMs for Noise Robust Recognition
    Li, Yang
    Liu, Xunying
    Wang, Lan
    14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 2967 - 2971
  • [29] Sports event recognition using layered HMMs
    Barnard, M
    Odobez, JM
    2005 IEEE International Conference on Multimedia and Expo (ICME), Vols 1 and 2, 2005, : 1151 - 1154
  • [30] Noise Robust Speech Recognition Based on Noise-Adapted HMMs Using Speech Feature Compensation
    Chung, Yong-Joo
    2013 INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE APPLICATIONS AND TECHNOLOGIES (ACSAT), 2014, : 132 - 135