Behavior recognition and anomaly behavior detection using clustering

Feizi, A.; Aghagolzadeh, Ali; Seyedarabi, Hadi

doi:10.1109/istel.2012.6483112

Cited by 2 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors who venture to design complete proposals, from the capture of video frames up to the behavior analysis of moving objects, need to determine constraints on their models in order to make feasible the computation of the heavy workload involved in every process (Berclaz et al, 2008), (Basharat et al, 2008), (Li et al, 2012), (Jiang et al, 2011). The works of these authors and (Ermis et al, 2008), (Kiryati et al, 2008), (Shi et al, 2010), (Hanapiah et al, 2010), (Feizi et al, 2012), (Haque and Murshed, 2012), (Cong et al, 2013) are generally focused on the search for better results on a set of standard video datasets created in their own trials or adopted from research groups around the world. Some approaches also deal with real world scenes, but are generally limited in flexibility in what concerns scenarios, targets, video length and reality.…”

Section: Related Workmentioning

confidence: 99%

“…However, the size of the grid regions in our case, isn't determined empirically. In the work of (Feizi et al, 2012), the number of pixels in the cluster size is conveniently determined by their method. Already the work of (Kwon et al, 2013) used the concept of entropy to adjust the size of the regions, which they named cell in order to tune the best data arrays that detect abnormal motions.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Region-based Abnormal Motion Detection in Video Surveillance

Casagrande

Stemmer

2014

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

This article proposes a method to detect abnormal motion based on the subdivision of regions of interest in the scene. The method reduces the large amount of data generated in a tracking-based approach as well as the corresponding computational cost in training phase. The regions are spatially identified and contain data of transition vectors, resulting from the centroid tracking of multiple moving objects. On these data, we applied a one-class supervised training with one set of normal tracks on Gaussian mixtures to find relevant clusters, which discriminate the trajectory of objects. The lowest probability of transition vectors is used as the threshold to detect abnormal motions. The ROC (Receiver Operating Characteristic) curves are used to this task and also to determinate the efficiency of the model for each size increment of the region grid. The results show that there is a range of grid size values, which ensure a best margin of correct abnormal motions detection for each type of scenario, even with a significant reduction of data samples.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Region-based Abnormal Motion Detection in Video Surveillance

Casagrande

Stemmer

2014

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

show abstract

“…If either the short-term action or the trajectory are found to be ''abnormal'', this is highlighted to the user. In [7] an approach for behavior modeling and detection of certain types of anomalous behavior is proposed. This paper first, proposes busy-idle rates, as the behavior features, to define a behavior model for a block of pixels.…”

Section: Introductionmentioning

confidence: 99%

“…Then, it uses spectral clustering for classifying behaviors. Once behavior model for each cluster is obtained using the histogram of the samples, reference [7] uses these models to perform anomalous behavior detection in a test video of the same scene.…”

Section: Introductionmentioning

confidence: 99%

Using optical flow and spectral clustering for behavior recognition and detection of anomalous behaviors

Feizi

Aghagolzadeh

Seyedarabi

2013

2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP)

Self Cite

View full text Add to dashboard Cite

In this paper we propose an efficient method for behavior recognition and identification of anomalous behavior in video surveillance data. This approach consists of two phases of training and testing. In the training phase, first, we use background subtraction method to extract the moving pixels. Then optical flow vectors are extracted for moving pixels. We propose behavior features of each pixel as the average all optical flow vectors in the pixel over several frames in video data. Next, we use spectral clustering to classify behaviors wherein pixels that have similar behavior features are clustered together. Then we obtain a behavior model for each cluster using the normal distribution of the samples. Once the behavior models are obtained, in the testing phase, we use these models to detect anomalous behavior in a test video of the same scene. Experimental results on video surveillance sequences show the effectiveness and speed of proposed method.

show abstract

Behavior recognition and anomaly behavior detection using clustering

Cited by 2 publications

References 10 publications

Region-based Abnormal Motion Detection in Video Surveillance

Region-based Abnormal Motion Detection in Video Surveillance

Using optical flow and spectral clustering for behavior recognition and detection of anomalous behaviors

Contact Info

Product

Resources

About