Small group human activity recognition

Yin, Yafeng; Yang, Guang; Xu, Jin; Man, Hong

doi:10.1109/icip.2012.6467458

Cited by 24 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recognition is finally given by a study of trajectories and a set of rules for different situations. Adaptive Mean Shift is used to track the individuals and the Gaussian process is used to cluster people in groups [9].…”

Section: Related Workmentioning

confidence: 99%

Detection of Groups of People in Surveillance Videos Based on Spatio-Temporal Clues

Colque

Cámara-Chávez

Schwartz

2014

Advanced Information Systems Engineering

View full text Add to dashboard Cite

Abstract. Video surveillance has been widely employed in our society in the past years. In this context, humans play an important role and are the major players since they are responsible for changing the state of the scene through actions and activities. Therefore, the design of automatic methods to understand human behavior and recognize activities are important to determine which subjects are involved in an activity of interest. The computer vision research area has contributed vastly for the development of methods related to detection, tracking and recognition of humans. However, there is still a lack of methods able to recognize higher level activities (e.g., interaction among people that might be involved in an illegal activity). The first step to be successful in this enterprise is to detect and locate groups of people in the scene, which is essential to make inferences regarding interactions among persons. Aiming at such direction, this paper presents a group detection approach that combines motion and spatial information with low-level descriptors to be robust to situations such as partial occlusions. The experimental results obtained using the PETS 2009 and the BEHAVE datasets demonstrate that the proposed combination indeed achieves higher accuracies, indicating a promising direction for future research.

show abstract

Section: Related Workmentioning

confidence: 99%

Detection of Groups of People in Surveillance Videos Based on Spatio-Temporal Clues

Colque

Cámara-Chávez

Schwartz

2014

Advanced Information Systems Engineering

View full text Add to dashboard Cite

show abstract

“…semantic social entropy. If multiple things have been merged as a group of things in the current place, a small group event recognition [20] will be performed and all human objects in the place will form a new thing, i.e. a "group", and its corresponding action will become the group action.…”

Section: Pcfg In Visual Sensingmentioning

confidence: 99%

“…Inspired by the theoretic analysis of the social network [85] and its extensions on group activity recognitions [73], we introduce a new set of features to describe the dynamic properties of the human object interactions. Figure 3.22 shows the overview of this approach.…”

Section: Social Network Analysis Based Hoi Featurementioning

confidence: 99%

“…Second stage is constructing the social network graphs and extracting the SNA features to describe the temporal dynamic of an interaction in each sequence. This is inspired by Yin et al [73], in which individual humans were modeled as nodes in social networks and hence the SNA feature set were used to describe small human group activities. At the last stage, two classifiers are applied to the feature vectors, namely, a K-means cluster followed by SVM and a Hidden Markov model classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MSEE: Stochastic Cognitive Linguistic Behavior Models for Semantic Sensing

Man¹,

Yao²

2013

Self Cite

View full text Add to dashboard Cite

“…A larger body of work addresses the general case of multiple interactions. Yin et al [5] proposed a method for human activity classification using social network analysis and a conditional Gaussian-process dynamic model. Ni et al [7] used localized causalities: interactions are represented within, between, and among motion trajectories, encoding the group-activities with three types of causalities (self, pair, and group).…”

Section: B Trajectory Analysismentioning

confidence: 99%

Pair-Activity Analysis From Video Using Qualitative Trajectory Calculus

AlZoubi

Al-Diri

Pike

et al. 2018

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-The automated analysis of interacting objects or people from video has many uses, including the recognition of activities, and identification of prototypical or unusual behaviors. Existing techniques generally use temporal sequences of quantifiable real-valued features, such as object position or orientation; however, more recently, qualitative representations have been proposed. In this paper we present a novel and robust qualitative method which can be used both for classification and clustering of pair-activities. We use Qualitative Trajectory Calculus (QT C) to represent the relative motion between two objects, and encodes their interactions as a trajectory of QT C states. A key element is a general and robust means of determining the sequence similarity, which we term Normalized Weighted Sequence Alignment; we show that this is an effective metric for both recognition and clustering problems. We have evaluated our method across three different datasets, and shown that it out-performs state of the art quantitative methods, achieving an error rate of no more than 4.1% for recognition, and cluster purities higher than 90%. Our motivation originates from an interest in automated analysis of animal behaviors, and we present a comprehensive video dataset of fish behaviors (Gasterosteus aculeatus), collected from lab-based experiments.

show abstract

Small group human activity recognition

Cited by 24 publications

References 13 publications

Detection of Groups of People in Surveillance Videos Based on Spatio-Temporal Clues

Detection of Groups of People in Surveillance Videos Based on Spatio-Temporal Clues

MSEE: Stochastic Cognitive Linguistic Behavior Models for Semantic Sensing

Pair-Activity Analysis From Video Using Qualitative Trajectory Calculus

Contact Info

Product

Resources

About