國立虎尾科技大學 |

Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video/ by Olga Isupova.
作者:	Isupova, Olga.
面頁冊數:	XXV, 126 p. 27 illus., 25 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Signal processing. -
電子資源:	https://doi.org/10.1007/978-3-319-75508-3
ISBN:	9783319755083

Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video
Isupova, Olga.

Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video[electronic resource] /by Olga Isupova. - 1st ed. 2018. - XXV, 126 p. 27 illus., 25 illus. in color.online resource. - Springer Theses, Recognizing Outstanding Ph.D. Research,2190-5053. - Springer Theses, Recognizing Outstanding Ph.D. Research,.

Introduction -- Background -- Proposed Learning Algorithms for Markov Clustering Topic Model -- Dynamic Hierarchical Dirlchlet Process -- Change Point Detection with Gaussian Processes -- Conclusions and Future Work.

This thesis proposes machine learning methods for understanding scenes via behaviour analysis and online anomaly detection in video. The book introduces novel Bayesian topic models for detection of events that are different from typical activities and a novel framework for change point detection for identifying sudden behavioural changes. Behaviour analysis and anomaly detection are key components of intelligent vision systems. Anomaly detection can be considered from two perspectives: abnormal events can be defined as those that violate typical activities or as a sudden change in behaviour. Topic modelling and change-point detection methodologies, respectively, are employed to achieve these objectives. The thesis starts with the development of learning algorithms for a dynamic topic model, which extract topics that represent typical activities of a scene. These typical activities are used in a normality measure in anomaly detection decision-making. The book also proposes a novel anomaly localisation procedure. In the first topic model presented, a number of topics should be specified in advance. A novel dynamic nonparametric hierarchical Dirichlet process topic model is then developed where the number of topics is determined from data. Batch and online inference algorithms are developed. The latter part of the thesis considers behaviour analysis and anomaly detection within the change-point detection methodology. A novel general framework for change-point detection is introduced. Gaussian process time series data is considered. Statistical hypothesis tests are proposed for both offline and online data processing and multiple change point detection are proposed and theoretical properties of the tests are derived. The thesis is accompanied by open-source toolboxes that can be used by researchers and engineers.

ISBN: 9783319755083

Standard No.: 10.1007/978-3-319-75508-3doiSubjects--Topical Terms:

561459
Signal processing.

LC Class. No.: TK5102.9

Dewey Class. No.: 621.382

Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video
LDR:03551nam a22004335i 4500 001 998010
003 DE-He213
005 20200702035953.0
007 cr nn 008mamaa
008 201225s2018 gw | s |||| 0|eng d
020 $a 9783319755083 $9 978-3-319-75508-3
024 7 $a 10.1007/978-3-319-75508-3 $2 doi
035 $a 978-3-319-75508-3
050 4 $a TK5102.9
050 4 $a TA1637-1638
072 7 $a TTBM $2 bicssc
072 7 $a TEC008000 $2 bisacsh
072 7 $a TTBM $2 thema
072 7 $a UYS $2 thema
082 0 4 $a 621.382 $2 23
100 1 $a Isupova, Olga. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1289422
245 1 0 $a Machine Learning Methods for Behaviour Analysis and Anomaly Detection in Video $h [electronic resource] / $c by Olga Isupova.
250 $a 1st ed. 2018.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2018.
300 $a XXV, 126 p. 27 illus., 25 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Springer Theses, Recognizing Outstanding Ph.D. Research, $x 2190-5053
505 0 $a Introduction -- Background -- Proposed Learning Algorithms for Markov Clustering Topic Model -- Dynamic Hierarchical Dirlchlet Process -- Change Point Detection with Gaussian Processes -- Conclusions and Future Work.
520 $a This thesis proposes machine learning methods for understanding scenes via behaviour analysis and online anomaly detection in video. The book introduces novel Bayesian topic models for detection of events that are different from typical activities and a novel framework for change point detection for identifying sudden behavioural changes. Behaviour analysis and anomaly detection are key components of intelligent vision systems. Anomaly detection can be considered from two perspectives: abnormal events can be defined as those that violate typical activities or as a sudden change in behaviour. Topic modelling and change-point detection methodologies, respectively, are employed to achieve these objectives. The thesis starts with the development of learning algorithms for a dynamic topic model, which extract topics that represent typical activities of a scene. These typical activities are used in a normality measure in anomaly detection decision-making. The book also proposes a novel anomaly localisation procedure. In the first topic model presented, a number of topics should be specified in advance. A novel dynamic nonparametric hierarchical Dirichlet process topic model is then developed where the number of topics is determined from data. Batch and online inference algorithms are developed. The latter part of the thesis considers behaviour analysis and anomaly detection within the change-point detection methodology. A novel general framework for change-point detection is introduced. Gaussian process time series data is considered. Statistical hypothesis tests are proposed for both offline and online data processing and multiple change point detection are proposed and theoretical properties of the tests are derived. The thesis is accompanied by open-source toolboxes that can be used by researchers and engineers.
650 0 $a Signal processing. $3 561459
650 0 $a Image processing. $3 557495
650 0 $a Speech processing systems. $3 564428
650 0 $a Optical data processing. $3 639187
650 0 $a Artificial intelligence. $3 559380
650 0 $a Computational intelligence. $3 568984
650 1 4 $a Signal, Image and Speech Processing. $3 670837
650 2 4 $a Image Processing and Computer Vision. $3 670819
650 2 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Computational Intelligence. $3 768837
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783319755076
776 0 8 $i Printed edition: $z 9783319755090
776 0 8 $i Printed edition: $z 9783030092504
830 0 $a Springer Theses, Recognizing Outstanding Ph.D. Research, $x 2190-5053 $3 1253569
856 4 0 $u https://doi.org/10.1007/978-3-319-75508-3
912 $a ZDB-2-ENG
912 $a ZDB-2-SXE
950 $a Engineering (SpringerNature-11647)
950 $a Engineering (R0) (SpringerNature-43712)