DocumentCode :
249837
Title :
Sparse representation based anomaly detection with enhanced local dictionaries
Author :
Biswas, S. ; Babu, R.V.
Author_Institution :
Video Analytics Lab., Indian Inst. of Sci., Bangalore, India
fYear :
2014
fDate :
27-30 Oct. 2014
Firstpage :
5532
Lastpage :
5536
Abstract :
In this paper, we propose a novel approach for anomaly detection by modeling the usual behaviour with enhanced dictionary. The corresponding sparse reconstruction error indicates the anomaly. We compute the dictionaries, for each local region, from feature descriptors obtained from usual behavior. The novelty of the proposed work is in enhancing the local dictionaries based on the similarity of usual behavior with its spatial neighbors. Dictionary enhancement is achieved by appending `transformed dictionary´ to the `local dictionary´. This `transformed dictionary´ is learned based on the transformations of behavior patterns across two neighboring regions. We conduct experiments on widely used UCSD Ped1 and Ped2 datasets to compare with the existing algorithms and demonstrate the improvement in anomaly detection with enhanced dictionaries compared to typically learned local dictionary.
Keywords :
image enhancement; image reconstruction; video signal processing; UCSD Ped1 dataset; UCSD Ped2 dataset; behavior pattern; feature descriptor; local dictionary enhancement; sparse reconstruction error; sparse representation based anomaly detection; spatial neighbor; transformed dictionary; Computational modeling; Computer vision; Conferences; Dictionaries; Feature extraction; Hidden Markov models; Integrated optics; Anomaly Detection; Dictionary Enhancement; Sparse Reconstruction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
Type :
conf
DOI :
10.1109/ICIP.2014.7026119
Filename :
7026119
Link To Document :
بازگشت