Learning hierarchical models of activity

Osentoski, Sarah; Manfredi, Victoria; Mahadevan, Sridhar

doi:10.1109/iros.2004.1389465

Cited by 20 publications

(20 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it extends the HHMM by allowing the refinement of an abstract state into lower-level states to be dependent on the current context, modeled by the current state at the bottom level. The AHMM was first applied to activity tracking and recognition [26], and used to model movements in an indoor environment [31].…”

Section: The Hierarchical Hmm (Hhmm)mentioning

confidence: 99%

Efficient duration and hierarchical modeling for human activity recognition

Duong

Phung

Bui

et al. 2009

Artificial Intelligence

View full text Add to dashboard Cite

A challenge in building pervasive and smart spaces is to learn and recognize human activities of daily living (ADLs). In this paper, we address this problem and argue that in dealing with ADLs, it is beneficial to exploit both their typical duration patterns and inherent hierarchical structures. We exploit efficient duration modeling using the novel Coxian distribution to form the Coxian hidden semi-Markov model (CxHSMM) and apply it to the problem of learning and recognizing ADLs with complex temporal dependencies. The Coxian duration model has several advantages over existing duration parameterization using multinomial or exponential family distributions, including its denseness in the space of nonnegative distributions, low number of parameters, computational efficiency and the existence of closed-form estimation solutions. Further we combine both hierarchical and duration extensions of the hidden Markov model (HMM) to form the novel switching hidden semi-Markov model (SHSMM), and empirically compare its performance with existing models. The model can learn what an occupant normally does during the day from unsegmented training data and then perform online activity classification, segmentation and abnormality detection. Experimental results show that Coxian modeling outperforms a range of baseline models for the task of activity segmentation. We also achieve a recognition accuracy competitive to the current state-of-the-art multinomial duration model, while gaining a significant reduction in computation. Furthermore, cross-validation model selection on the number of phases K in the Coxian indicates that only a small K is required to achieve the optimal performance. Finally, our models are further tested in a more challenging setting in which the tracking is often lost and the activities considerably overlap. With a small amount of labels supplied during training in a partially supervised learning mode, our models are again able to deliver reliable performance, again with a small number of phases, making our proposed framework an attractive choice for activity modeling.

show abstract

Section: The Hierarchical Hmm (Hhmm)mentioning

confidence: 99%

Efficient duration and hierarchical modeling for human activity recognition

Duong

Phung

Bui

et al. 2009

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Bui et al [2002] have proposed Abstract Hidden Markov Models (AHMM), which are a hierarchical extension of HMMs that allow to represent motion at different levels of detail (eg metric, room, building, etc.) and integrate the concept of policy (ie plan), which may be regarded as the equivalent of a motion pattern; a two-level AHMM has been applied to intentional motion by Osentoski et al [2004], using EM to learn the model's parameters. One of the advantages of AHMMs over HMMs is that they are able to provide good mid-term predictions even if they are wrong at the long-term, for example, they may accurately predict that a person is going towards the room's door even if they wrongly predict that the final destination is the kitchen.…”

Section: Other State-space Modelsmentioning

confidence: 99%

Incremental Learning for Motion Prediction of Pedestrians and Vehicles

Govea

2010

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

The main subject of this thesis is motion prediction. The problem is approached from the hypothesis that the dynamic and kinematic properties of objects such as pedestrian and vehicles do not suffice to predict their motion in the long term. Instead, the work presented here, inscribes itself in a new family of approaches which assume that, in a given environment, objects do not move at random, but engage in "typical motion patterns", which may be learned and then used to predict motion on the basis of sensor data. In this context, this thesis focuses in three fundamental questions: modeling, learning and prediction.Modeling. This thesis is based on Hidden Markov Models, a probabilistic framework, which is used as a discrete approximation to represent the continuous state-space in which motion takes place. The main originality of the approach lies in modeling explicitly the intentions which are at the origin of "typical motion patterns". This is achieved through the using of an extended space, which adds the state that the object intends to reach to the other "classic" state variables, such as position or velocity.Learning. The main problem of existing approaches lies in the separation of model learning and utilization in two distinct stages: in a first phase, the model is learned from data; then, it is used to predict. This principle is difficult to apply to real situations, because it requires at least one example of every possible typical pattern to be available during the learning phase.To address this problem, this thesis proposes a novel extension to Hidden Markov Models which allows simultaneous learning and utilization of the model. This extension incrementally builds a topological map -representing the model's structure -and reestimates the model's parameters. The approach is intended to be general, and it could be used in other application domains such as gesture recognition or automatic landmark extraction.Prediction. In this context, prediction is carried on by using exact Bayesian inference algorithms, which are able to work in real time thanks to the properties of the structure which has been learned. In particular, the time complexity of inference is reduced from O(N 2 ) to O(N) with respect to the number of discrete states in the system.All of the results obtained on this thesis have been implemented and validated with experiments, using both real and simulated data. Real data has been obtained on two different visual tracking systems: one installed over a parking lot, and the other installed at INRIA's entry hall. For synthetic data, a simulator has been developed in order to facilitate the conduction of controlled tests and the study of larger environments than for real data.

show abstract

“…Nevertheless, uncertainties are pervasive in the velocity and heading direction of people's movement. Several studies have exploited the spatial-temporal nature of human motion using a chain of Gaussian distributions [13] , clustering the trajectories with Kmeans [14] , and learning human motion patterns from tracking data using an EM algorithm [6] . However, most past research ignores the combination of human motion uncertainty prediction with motion pattern prediction.…”

Section: Introductionmentioning

confidence: 99%

Decision-Theoretical Navigation of Service Robots Using POMDPs with Human-Robot Co-Occurrence Prediction

Qian

Duan

et al. 2013

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

To improve the natural human-avoidance skills of service robots, a human motion predictive navigation method is proposed, namely PN-POMDP. A humanrobot motion co-occurrence estimation algorithm is proposed which incorporates long-term and short-term human motion prediction. To improve the reliability of probabilistic and predictive navigation, the POMDP model is utilized to generate navigation control policies through theoretically optimal decisions. A layered motion control structure is proposed that combines global path planning and reactive avoidance. Multiple comity policies are integrated with a decision-making module that generates efficient and human-compliant navigational behaviours for robots. Experimental results illustrate the effectiveness and reliability of the predictive navigation method.

show abstract

Learning hierarchical models of activity

Cited by 20 publications

References 8 publications

Efficient duration and hierarchical modeling for human activity recognition

Efficient duration and hierarchical modeling for human activity recognition

Incremental Learning for Motion Prediction of Pedestrians and Vehicles

Decision-Theoretical Navigation of Service Robots Using POMDPs with Human-Robot Co-Occurrence Prediction

Contact Info

Product

Resources

About