Learning and detecting activities from movement trajectories using the hierarchical hidden Markov model

By Nam Thanh Nguyen, Dinh Q. Phung, Svetha Venkatesh, Hung Hai Bui. Computer Vision and Pattern Recognition, 2005

374 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/78c6b9df5f943c5ad775dde9b02668c039c13548

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Discriminative subvolume search for efficient action detection (2009, background): “One type of approaches uses motion trajectories to represent actions and it requires target tracking [16] [1].”
Autonomously constructing hierarchical task networks for planning and human-robot collaboration (2016, background): “As (hierarchical) HMMs have been shown to be a popular and effective approach for action and goal recognition [4], [30], we test the effectiveness of our hierarchies at segmenting tasks within this domain.”
Human activity analysis (2011, background): “Nguyen et al. [2005] also constructed hierarchical HMMs of two layers to recognize complex sequential activities.”
A survey on activity recognition and behavior understanding in video surveillance (2013, methodology): “[119] used hierarchical HMMs (HHMMs) to recognize behavior correctly but not suited well for complex behaviors.”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, methodology): “Modeling complex interactions and simultaneous activities pose a challenge for researchers due to the rigid flat structure [68].”
Tracking and Modeling of Human Activity Using Laser Rangefinders (2010, background): “In order to recognize longer movement sequences, the tracks of foreground objects in an image are first classified into activity primitives such as hand gestures, walking, and paths between known landmarks [5, 16, 30].”
Recognition of Composite Human Activities through Context-Free Grammar Based Representation (2006, background): “Similarly, Nguyen et al. [4] used hierarchical HMMs in order to recognize two levels of actions.”
Peek-a-boo: i see your smart home activities, even encrypted! (2018, background): “. ... ... ... ... ... P m1 P m2 P m3 ... ... P mm (4) If the smart home environment has X t number of states where t=0,1,...,T, the elements of the transition matrix can be shown as follows [27]: P ij = N ij N i , (5) where N ij denotes the number of transition from X t to X t+1, where X t is t”
Conditional random fields for activity recognition (2007, background): “[27,80], although it results in models where exact inference is intractable.”
Simultaneous Plan Recognition and Monitoring (SPRAM) for Robot Assistants (2013, background): “the inclusion of durations [6] or hierarchies [11, 4].”
Expandable Data-Driven Graphical Modeling of Human Actions Based on Salient Postures (2008, background): “Researchers have so far explored various types of visual information to describe human motion, including motion trajectories [2]–[4], sequences of silhouettes or contours of the human body [5], [6], spatio–temporal salient points [7], hierarchical configuration of body parts [8], [9], such as torso,”
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living (2012, methodology): “[76] present an application of the hierarchical HMM which detects three different activities, namely have a snack, short meal or normal meal, depending on the visited spots in each action sequence.”
Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video (2009, background): “In hierarchical Markov models (HHMMs) [83], [84], each possible state is represented by a lower level HMM.”