Learning and Detecting Activities from Movement Trajectories Using the Hierarchical Hidden Markov Models

Nguyễn, Nam Thành; Phung, Dinh; Venkatesh, Svetha; Bui, Hung

doi:10.1109/cvpr.2005.203

Cited by 221 publications

(158 citation statements)

References 16 publications

Supporting

Mentioning

157

Contrasting

Unclassified

Order By: Relevance

“…These models facilitate machine learning, by reusing the lowlevel actions [11]. Further, multi-level approaches decrease the semantic gap between low-level features and complex behaviours [8].…”

Section: Related Workmentioning

confidence: 99%

“…When longerterm behaviours are composed of several short-term actions in a particular sequence, the temporal structure can be exploited in sequential models such as hand-crafted grammars [10], or statistical, graphical models [11]. The merit of temporal structure has been demonstrated for behaviours such as 'two people meet, then depart' [10] and 'having a snack' inside a small living room [11]. These behaviours have a small spatial extent.…”

Section: Related Workmentioning

confidence: 99%

“…Hierarchical models [11,13] and models with an intermediate level [8,15] have gained interest for automated recognition of complex behaviours. These models facilitate machine learning, by reusing the lowlevel actions [11].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

Burghouts¹,

Schutte²,

Hove³

et al. 2014

SIViP

View full text Add to dashboard Cite

Threat detection is a challenging problem, because threats appear in many variations and differences to normal behaviour can be very subtle. In this paper, we consider threats on a parking lot, where theft of a truck's cargo occurs. The theft takes place in very different forms, in the midst of many people who pose no threat. The threats range from explicit, e.g., a person attacking the truck driver, to implicit, e.g., somebody loitering and then fiddling with the exterior of the truck in order to open it. Our goal is a system that is able to recognize a threat instantaneously as they develop. Typical observables of the threats are a person's activity, presence in a particular zone, and the trajectory. The novelty of this paper is an encoding of these threat observables in a semantic, intermediate-level representation, based on low-level visual features that have no intrinsic semantic meaning themselves. The semantic representation encodes the notions of trajectories, zones and activities. The aim of this representation is to bridge the semantic gap between the low-level tracks and motion and the higher-level notion of threats. In our experiments, we demonstrate that our semantic representation is more descriptive for threat detection than directly using low-level features. We find that a person's activities are the most important elements of this semantic representation, followed by the person's trajectory. The proposed threat detection system is very accurate: 96.6% of the tracks are correctly interpreted, when considering the temporal context.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

Burghouts¹,

Schutte²,

Hove³

et al. 2014

SIViP

View full text Add to dashboard Cite

show abstract

“…al. [19] used an HHMM framework to model and recognise three human activities (e.g. having a meal) in a confined space, while tracking the user with two static cameras.…”

Section: Related Workmentioning

confidence: 99%

“…Researchers have therefore resorted to explore different stochastic/probabilistic modelling techniques capable of representing the possible uncertainties involved in ADLs. Probabilistic models such as Bayesian Network (BN) [13], Dynamic Bayesian Network (DBN) [14],Partially Observable Markov Decision Process(POMDPs) [15], [16], [17], Hidden Markov Models (HMM) [18] and Hierarchical Hidden Markov Models (HHMM) [19] have been proposed in the literature.…”

Section: Related Workmentioning

confidence: 99%

A probabilistic approach to learn activities of daily living of a mobility aid device user

Patel

Miró

Dissanayake

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-The problem of inferring human behaviour is naturally complex: people interact with the environment and each other in many different ways, and dealing with the often incomplete and uncertain sensed data by which the actions are perceived only compounds the difficulty of the problem. In this paper, we propose a framework whereby these elaborate behaviours can be naturally simplified by decomposing them into smaller activities, whose temporal dependencies can be more efficiently represented via probabilistic hierarchical learning models. In this regard, patterns of a number of activities typically carried out by users of an ambulatory aid device have been identified with the aid of a Hierarchical Hidden Markov Model (HHMM) framework. By decomposing the complex behaviours into multiple layers of abstraction the approach is shown capable of modelling and learning these tightly coupled humanmachine interactions. The inference accuracy of the proposed model is proven to compare favourably against more traditional discriminative models, as well as other compatible generative strategies to provide a complete picture that highlights the benefits of the proposed approach, and opens the door to more intelligent assistance with a robotic mobility aid.

show abstract

Intuitive network applications: Learning user context and behavior

Bila¹,

Cao²,

Dinoff³

et al. 2008

Bell Labs Tech. J.

View full text Add to dashboard Cite

There are various dimensions involved in this approach: 1) machine learning techniques to gather user habits and preferences in an automated fashion; 2) human factors-directed approaches to explicitly gather additional information from the user, while minimizing the (perceived) inconvenience to him; 3) providing the user with an easy mechanism to view and control the acquired information (whether learned or explicitly gathered); and 4) ensuring that the overall information monitoring and analysis are done in a robust, scalable fashion, and the acquired information can be used at run time in a near-real time fashion. In this paper, we focus primarily on an overview of the INA architecture and present some details on machine learning directed at an advertising

show abstract

Learning and Detecting Activities from Movement Trajectories Using the Hierarchical Hidden Markov Models

Abstract: Abstract

Cited by 221 publications

References 16 publications

Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

A probabilistic approach to learn activities of daily living of a mobility aid device user

Intuitive network applications: Learning user context and behavior

Contact Info

Product

Resources

About