Unusual Activity Analysis Using Video Epitomes and pLSA

Choudhary, Ayesha; Pal, Mikhil R.; Banerjee, Subhashis; Chaudhury, Santanu

doi:10.1109/icvgip.2008.89

Cited by 12 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second category is unsupervised learning. This is a type of learning whereby the network clusters the data without any labels [7] - [10]. In order to cluster the data into abnormal or normal behavior, certain statistical properties and methods are needed.…”

Section: Related Workmentioning

confidence: 99%

A Robust Abnormal Behavior Detection Method Using Convolutional Neural Network

Tay

Connie

Ong

et al. 2018

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

A behavior is considered abnormal when it is seen as unusual under certain contexts. The definition for abnormal behavior varies depending on situations. For example, people running in a field is considered normal but is deemed abnormal if it takes place in a mall. Similarly, loitering in the alleys, fighting or pushing each other in public areas are considered abnormal under specific circumstances. Abnormal behavior detection is crucial due to the increasing crime rate in the society. If an abnormal behavior can be detected earlier, tragedies can be avoided. In recent years, deep learning has been widely applied in the computer vision field and has acquired great success for human detection. In particular, Convolutional Neural Network (CNN) has shown to have achieved state-ofthe-art performance in human detection. In this paper, a CNN-based abnormal behavior detection method is presented. The proposed approach automatically learns the most discriminative characteristics pertaining to human behavior from a large pool of videos containing normal and abnormal behaviors. Since the interpretation for abnormal behavior varies across contexts, extensive experiments have been carried out to assess various conditions and scopes including crowd and single person behavior detection and recognition. The proposed method represents an end-to-end solution to deal with abnormal behavior under different conditions including variations in background, number of subjects (individual, two persons or crowd), and a range of diverse unusual human activities. Experiments on five benchmark datasets validate the performance of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

A Robust Abnormal Behavior Detection Method Using Convolutional Neural Network

Tay

Connie

Ong

et al. 2018

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…This section provides a recent review of the works closely related to object detection, human behavior recognition, with machine learning and probabilistic model. The purpose of human behavior detection is to recognize, or learn interesting events, which is defined as "suspicious event" [3], "irregular behavior" [4], "uncommon trajectory" [5], unusual activity/behavior [6][7][8][9][10][11][12][13], "abnormal behavior" [14][15][16] to predict dangerous situation for pedestrians. For the improvement of public safety level and prevention of the crime, intelligent real-time human behavior recognition is more important in daily life.…”

Section: A Abnormal Human Behavior Detectionmentioning

confidence: 99%

Behavior tracking model in dynamic situation using the risk ratio EM

Jung

Yoon

2015

2015 International Conference on Information Networking (ICOIN)

View full text Add to dashboard Cite

Closed Circuit Television (CCTV) system has been popular in daily life such as traffic, airport, street and public place. The common goal of CCTV system is the prevention of crime and disorder by observing objects. In the future, smart CCTV camera combined with mobile phone will be used to protect human from crime and dangerous situations. Intelligent CCTV system in public place will monitor human behavior in real-time and transfer image data to control tower for the security purpose. In this paper, we propose an abnormal behavioral tracking model for prediction of abnormal situation by using Expectation Maximization (EM) algorithm combined with Viterbi algorithm. The tracking model will detect objects from CCTV image in dynamic environment for the prediction of dangerous situation. This tracking system has five main steps. (1) The detection of object and their environment, (2) Feature extraction from objects and situations such as human body posture, weather, and time (3) Location information such as object trajectory and area safety level (4) knowledge update and decision making (5) prediction of abnormal situation and maximized risk rates.

show abstract

“…Multiple topics are discovered by the model. Examples of local features that have been used with these models include optical flow vectors [11], foreground patches [12], spatio-temporal words [13] and space-time shape features extracted using epitomes [3]. Often these local features can be computed reliably and since the model inferences activities using global statistics across documents the model works well even if features are not detected in a few frames.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised discovery of activity correlations using latent topic models

Faruquie

Banerjee

Kalra

2010

Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing

Self Cite

View full text Add to dashboard Cite

Topic models such as probabilistic Latent Semantic Analysis (pLSA) and Latent Dirichlet Allocation (LDA) have been successfully used to discover individual activities in a scene. However these methods do not discover group activities which are commonly observed in real life videos of public places. In this paper we address the problem of discovering activities and their associations as a group activity in an unsupervised manner. We propose a method that uses a two layer hierarchical latent structure to correlate individual activities in lower layer with group activity in higher layer. Our model considers each scene to be composed of a mixture of group activities. Each group activity is in turn composed as a mixture of individual activities represented as multinomial distributions. Each individual activity is represented as a distribution over local visual features. We use a Gibbs sampling based algorithm to infer these activities. Our method can summarize not only the individual activities but also the common group activities in a video. We demonstrate the strength of our method by mining activities and the salient correlation amongst them in real life videos of crowded public scenes.

show abstract

Unusual Activity Analysis Using Video Epitomes and pLSA

Cited by 12 publications

References 6 publications

A Robust Abnormal Behavior Detection Method Using Convolutional Neural Network

A Robust Abnormal Behavior Detection Method Using Convolutional Neural Network

Behavior tracking model in dynamic situation using the risk ratio EM

Unsupervised discovery of activity correlations using latent topic models

Contact Info

Product

Resources

About