Human Interaction Representation and Recognition Through Motion Decomposition

Du, Youtian; Chen, Feng; Wang, Xu

doi:10.1109/lsp.2007.908035

Cited by 40 publications

(37 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to evaluate the validity of the proposed model, the trajectories are also classified with a first-order Markov model of interactions as the one described in [10], [11] and [12], using instead of the probabilities of (4) and (5) respectively p( The method is also tested on 24 real-world couple of interacting trajectories (4 for each type of interaction) acquired by a static camera and extracted using a standard blob tracker with a Mean Shift-based occlusion handling and projected onto the ground plane using Tsai's camera calibration. Only one over the 24 interactions is misclassified because of a long track loss due to a camouflage problem affecting the visual tracker.…”

Section: B Interaction Recognition Resultsmentioning

confidence: 99%

“…Bayesian Network (CHDS-DBN), are used respectively in [10] and [11] to recognize interactive motion activities by considering trajectories and motion features. Instead, in [12] tensor space analysis is employed to model and retrieve interdependent trajectories.…”

Section: Related Workmentioning

confidence: 99%

“…Instead, in [12] tensor space analysis is employed to model and retrieve interdependent trajectories. The models presented in [10], [11] and [12] are able to encode only interactions occurring in subsequent time instants, i.e. they are first-order Markov models.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Interaction Analysis with a Bayesian Trajectory Model

Dore

Regazzoni

2010

IEEE Intell. Syst.

View full text Add to dashboard Cite

Human behavior recognition is one of the most important and challenging objectives performed by intelligent vision systems. Several issues must be faced in this domain ranging from the extraction of reliable and meaningful features from video streams, to the accurate definition of models able to characterize in a discriminative but, at the same time, general enough way people actions. In this work to cope with these problems a Dynamic Bayesian Network (DBN) model is proposed to recognize people interactions using their patterns of movement. Couples of observed interacting trajectories are processed by the Instantaneous Topological Map (ITM) algorithm to automatically create a topological map used to define the states of the DBN. The trajectories are encoded into the model where conditional probability densities are learned in order to statistically describe interactions. Finally, an online cumulative measure is defined to recognize interactions both in simulated and real-world environments.

show abstract

Section: B Interaction Recognition Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Interaction Analysis with a Bayesian Trajectory Model

Dore

Regazzoni

2010

IEEE Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Furthermore, in a healthcare system, the activity recognition can help the rehabilitation of patients, such as the automatic recognition of patient's action to facilitate the rehabilitation processes. There have been numerous research efforts reported for various applications based on human activity recognition, more specifically, home abnormal activity [1], ballet activity [2], tennis activity [3,4], soccer activity [5], human gestures [6], sport activity [7,8], human interaction [9], pedestrian traffic [10] and simple actions [11][12][13][14][15][16][17][18][19][20][21][22], and healthcare applications [1,[23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]. In this paper, the video based technologies for human activity recognition will be extensively reviewed and discussed.…”

Section: Introductionmentioning

confidence: 99%

“…The dynamic time warping (DTW) [14,16], a method for measuring similarity between two temporal sequences, which may vary in time or speed, is one of the most common temporal classification algorithms due to its simplicity; however, DTW is not appropriate for a large number of classes with many variations. Some probability-based methods by generative models (dynamic classifiers) are proposed such as Hidden Markov Models (HMM) [1,4,6,17,[75][76][77] and Dynamic Bayesian Networks (DBN) [7,9,78]. On the other hand, discriminative models (static classifiers) such as Support Vector Machine (SVM) [18,19,79,80], Relevant Vector Machine (RVM) [54,81,82] and Artificial Neural Network (ANN) [29,83,84], can also be used in this stage.…”

Section: Introductionmentioning

confidence: 99%

A Review on Video-Based Human Activity Recognition

et al. 2013

View full text Add to dashboard Cite

This review article surveys extensively the current progresses made toward video-based human activity recognition. Three aspects for human activity recognition are addressed including core technology, human activity recognition systems, and applications from low-level to high-level representation. In the core technology, three critical processing stages are thoroughly discussed mainly: human object segmentation, feature extraction and representation, activity detection and classification algorithms. In the human activity recognition systems, three main types are mentioned, including single person activity recognition, multiple people interaction and crowd behavior, and abnormal activity recognition. Finally the domains of applications are discussed in detail, specifically, on surveillance environments, entertainment environments and healthcare systems. Our survey, which aims to provide a comprehensive state-of-the-art review of the field, also addresses several challenges associated with these systems and applications. Moreover, in this survey, various applications are discussed in great detail, specifically, a survey on the applications in healthcare monitoring systems. OPEN ACCESSComputers 2013, 2 89

show abstract

Interaction-Feature Enhanced Multiuser Model Learning for a Home Environment Using Ambient Sensors

Chiang

2014

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Activity recognition (AR) is a key enabler for a context-aware smart home since knowing what the residents' current activities helps a smart home provide more desirable services. This is why AR is often used in assistive technologies for cognitively impaired people to evaluate their abilities to undertake activities of daily living. In a real-life scenario, multiple-resident AR has been considered as a very challenging problem, primarily due to the complexity of data association. In addition, most prior research has not considered the potential interpersonal interactions among residents to simplify complexity, especially in an environment monitored by ambient sensors. In this study, we propose two types of multiuser activity models, both of which are derived from an interaction-feature enhanced multiuser model learning framework. These two models consider interpersonal interactions and data association for multiuser AR using ambient sensors. We then compare their performance with the other two baseline models with or without consideration of data association and interpersonal interactions. The experimental results show that the derived models outperform other baseline classifiers. Therefore, the proposed approach can increase the opportunities for providing context-aware services for a multiresident smart home. C 2014 Wiley Periodicals, Inc.

show abstract

Human Interaction Representation and Recognition Through Motion Decomposition

Cited by 40 publications

References 8 publications

Interaction Analysis with a Bayesian Trajectory Model

Interaction Analysis with a Bayesian Trajectory Model

A Review on Video-Based Human Activity Recognition

Interaction-Feature Enhanced Multiuser Model Learning for a Home Environment Using Ambient Sensors

Contact Info

Product

Resources

About