Corpus ID: 16724897

Social Behavior Analysis in Visual Human Monitoring System : A Survey and Perspective

  title={Social Behavior Analysis in Visual Human Monitoring System : A Survey and Perspective},
  author={Henry Y. T. Ngan and H. Kawai and K. Kunieda and Keiji Yamada},
A social behavior analysis is used to study how a group of people interacts with another group. The analysis helps to understand how social behavior leads to its consequences such as what business decision is made after a businessmen's meeting. In this paper, we focus on visual human motion analysis which is one important component of social behavior analysis. Human motion analysis in visual surveillance usually tracks the motion of an individual or a group of people, yet social behavior is… Expand

Figures, Tables, and Topics from this paper


Recent developments in human motion analysis
  • Liang Wang, W. Hu, T. Tan
  • Computer Science
  • Pattern Recognit.
  • 2003
This paper provides a comprehensive survey of research on computer-vision-based human motion analysis, namely human detection, tracking and activity understanding, and various methods for each issue are discussed in order to examine the state of the art. Expand
Learning visual models of social engagement
  • B. Singletary, T. Starner
  • Computer Science
  • Proceedings IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems
  • 2001
A face detector for wearable computers that exploits constraints in face scale and orientation imposed by the proximity of participants in near social interactions and may be incorporated into a user interface to improve the quality of mobile face recognition software. Expand
Value-Directed Human Behavior Analysis from Video Using Partially Observable Markov Decision Processes
  • J. Hoey, J. Little
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
This paper presents a method for learning decision theoretic models of human behaviors from video data that obviates the need for labeled data from expert knowledge about which behaviors are significant and removes bias about what behaviors may be useful to recognize in a particular situation. Expand
Combining Face Detection and Novelty to Identify Important Events in a Visual Lifelog
  • A. Doherty, A. Smeaton
  • Computer Science
  • 2008 IEEE 8th International Conference on Computer and Information Technology Workshops
  • 2008
The concept of novelty to help determine the importance of events in a lifelog is introduced by combining novelty with face-to-face conversation detection, which improves on previous approaches. Expand
Searching Human Behaviors using Spatial-Temporalwords
This paper proposes an approach to searching human behaviors in videos using spatial-temporal words which are learnt from unlabelled data with various human behaviors through unsupervised learning, represented by codewords frequencies, which capture the intrinsic information of motion and appearance of human behaviors. Expand
Vision-based human behavior recognition by a mobile robot
This paper shows an examination about a vision-based moving human posture measurement by a moving mobile robot. The purpose of this study is to show that a moving human motion is measurable by theExpand
Estimation system of human behaviors using fuzzy neural network based object selection
A method is proposed for promptly estimating the behavioral targets by applying a fuzzy neural network (FNN) based on the human velocity, the angle of the human relative to an object, and the distance between the human and an object. Expand
Learning semantic scene models from observing activity in visual surveillance
  • D. Makris, T. Ellis
  • Computer Science, Medicine
  • IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2005
This paper considers the problem of automatically learning an activity-based semantic scene model from a stream of video data. A scene model is proposed that labels regions according to anExpand
Modeling and Analyzing Individual's Daily Activities using Lifelog
This study proposes an integrated technique to process the lifelog data using the correlations between different kinds of captured data from multiple sensors, instead of dealing with them separately. Expand
Verification and validation of fuzzy rules-based human behavior models
  • Fei Liu, Ming Yang, Peng Shi
  • Computer Science
  • 2008 Asia Simulation Conference - 7th International Conference on System Simulation and Scientific Computing
  • 2008
This paper presents a fuzzy Petri nets-based method for verification and validation of fuzzy rules-based human behavior models, which consists of verification of fuzzy rule bases, static validation of human Behavior Model Verification, and dynamic validation ofhuman behavior models. Expand