Hierarchical group process representation in multi-agent activity recognition

Zhang, Weidong; Chen, Feng; Wang, Xu; Du, Youtian

doi:10.1016/j.image.2008.09.001

Cited by 9 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is recent evidence that more efficient algorithms can be developed based on the recognition of high-level social groups detected in a hierarchical structure [32], [33]. The social grouping behavior of people shopping together is captured and evaluated by analyzing the inter-body distances [34].…”

Section: A Recognizing Social Groups In Computer Visionmentioning

confidence: 99%

Understanding Dynamic Social Grouping Behaviors of Pedestrians

Feng

Bhanu

2015

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

There have been many studies in the literature on social group recognition of crowds of pedestrians. However, most of these studies have approached the problem from a static point of view. A study on the dynamic property of social groups among people over time can provide significant insight into human behaviors and events. Inspired by sociological models of human collective behavior, in this work, we present a framework for characterizing hierarchical social groups based on evolving tracklet interaction network (ETIN) where the tracklets of pedestrians are represented as nodes and the their grouping behaviors are captured by the edges with associated weights. We use non-overlapping snapshots of the interaction network and develop the framework for a unified dynamic group identification and tracklet association. The approach is evaluated quantitatively and qualitatively on videos of pedestrian scenes where manually labeled ground-truth is given. The results of our approach are consistent to human-perceived dynamic social groups of the crowd. The performance analysis of our method shows that the approach is scalable and it provides situational awareness in a real-world scenarios.Index Terms-Dynamic social grouping behavior, pedestrian social groups, tracklet interaction network. 1932-4553

show abstract

Section: A Recognizing Social Groups In Computer Visionmentioning

confidence: 99%

Understanding Dynamic Social Grouping Behaviors of Pedestrians

Feng

Bhanu

2015

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…These approaches are typically limited to a small, known number of individuals, due to the combinatorics involved in the coupled interpretation of multiple time series. There is recent evidence that more efficient recognition of group activities is possible by using a model of the group activity process to guide interpretation of the actions of individual members [30,38].…”

Section: Related Work On Vision-based Crowd Analysismentioning

confidence: 99%

Automatically detecting the small group structure of a crowd

Collins

Ruback

2009

2009 Workshop on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Recent work on computer vision analysis of crowds tends to focus on robustly tracking individuals through the crowd or on analyzing the overall pattern of flow. Our work seeks a deeper analysis of social behavior by identifying the small group structure of crowds, forming the basis for mid-level activity analysis at the granularity of human social groups. Building upon state-of-the-art algorithms for pedestrian detection and multi-object tracking, and inspired by social science models of human collective behavior, we automatically detect small groups of individuals who are traveling together. These groups are discovered using a bottom-up hierarchical clustering approach that compares sets of individuals based on a generalized, symmetric Hausdorff distance defined with respect to pairwise proximity and velocity. We validate our results quantitatively and qualitatively on videos of real-world pedestrian scenes. Where humancoded ground truth is available, we find substantial statistical agreement between our results and the human-perceived small group structure of the crowd.

show abstract

“…It describes how irregular the motion is; 3) body aspect ratio γ = w/h, where w and h are the weight and height of the person respectively; 4) body inclination ρ, which is calculated as the angle between the major axis of the silhouette and the verticality. Both prove very useful to identifying poses [20,21]. 3-chain dynamical influence models and 3-chain influence models are used to model and recognize these activities.…”

Section: Act4mentioning

confidence: 99%

Learning interactions among multi-channel sequences with dynamical influence models

Zhang

Chen

Wang

2010

Sci. China Inf. Sci.

Self Cite

View full text Add to dashboard Cite

Many real applications involve simultaneous recording and analysis of multi-channel information sources. Learning and modeling the interactions among channels is the kernel step to analyze and recognize system characteristics. This paper presents a model that learns the dynamical influence among multi-channel sequences. The model, dynamical influence model, permits functional roles of individual channels to change and models the changing influence strength between channels. By querying the values of influence factors, we can recognize the functional role of each channel qualitatively and learn about to what extent the chains influence each other quantitatively at any time. The experimental results on synthetic data and application of multi-person interaction recognition show that our model is reliable and effective.

show abstract

Hierarchical group process representation in multi-agent activity recognition

Cited by 9 publications

References 30 publications

Understanding Dynamic Social Grouping Behaviors of Pedestrians

Understanding Dynamic Social Grouping Behaviors of Pedestrians

Automatically detecting the small group structure of a crowd

Learning interactions among multi-channel sequences with dynamical influence models

Contact Info

Product

Resources

About