Recognition of human body motion using phase space constraints

By Lee W. Campbell, Aaron F. Bobick. 1995

Subfields: Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Campbell and Bobick [160] introduced a mapping from the Cartesian space to the “phase space”.”
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition (2014, background): “Multicamera motion capture (MoCap) systems [3] have been used for human action recognition, but such special equipment is marker-based and expensive.”
Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice (2014, neutral): “…developed in other areas and their influence on action recognition Xiaojiang Peng School of Information Sciences and Technology, Southwest Jiaotong University, Chengdu, China E-mail: xiaojiangp@gmail.com Limin Wang Department of Information Engineering, The Chinese University of Hong Kong, Hong…”
Fuzzy human motion analysis: A review (2014, methodology): “HMM have been widely employed in the human action recognition [154, 155, 156, 157, 158].”
Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost (2006, background): “In the above 3-D approaches, [1] decomposes the original 3-D joint trajectories into a collection of 2-D projected curves.”
Towards Understanding Action Recognition (2013, methodology): “Pose has been used in early work on action recognition [3, 32].”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “[26] Skel+Seq 3d joint trajectories Projection in phase spaces Similar to NN yes yes no”
A survey of vision-based methods for action representation, segmentation and recognition (2011, background): “1995 Campbell and Bobick [16] bm gr sw – – – – – –”
Recent developments in human motion analysis (2003, methodology): “State-space approaches The approach based on the state-space models [136–139,52,149] deAnes each static posture as a state, and uses certain probabilities to generate mutual connections between these states.”
Action Recognition from Arbitrary Views using 3 D Exemplars (2007, background): “[6, 20] assume a known parametric model, typically a kinematic model, and represent actions in a joint or parameter space.”
Learning Variable-Length Markov Models of Behavior (2001, background): “Of particular interest is the modelling and recognition of human activities involving highly structured and semantically rich behaviour such as dance, aerobics, and sign language [6, 20, 21].”
Inferring 3D body pose from silhouettes using activity manifold learning (2004, background): “Partial recovery of body configuration can also be achieved through intermediate view-based representations (models) that may or may not be tied to specific body parts [6, 5, 31, 13, 27].”
Does Human Action Recognition Benefit from Pose Estimation? (2011, methodology): “The sequences themselves were then classified through exemplar matching [12, 23, 32] or with state-space models such as HMMs [5].”