Discovering Unusual Behavior Patterns from Motion Data

碩士 === 國立成功大學 === 工程科學系 === 102 === As there are more and more surveillance cameras installed in public places, a challenging problem is to discover unusual behavior patterns from a huge amount of video data. However, this task is currently only feasible for human beings because both object recognit...

Full description

Bibliographic Details
Main Authors: Kai-LinPang, 龐凱齡
Other Authors: Wei-Guang Teng
Format: Others
Language:en_US
Published: 2014
Online Access:http://ndltd.ncl.edu.tw/handle/25192086288873642319
id ndltd-TW-102NCKU5028015
record_format oai_dc
spelling ndltd-TW-102NCKU50280152016-05-22T04:40:30Z http://ndltd.ncl.edu.tw/handle/25192086288873642319 Discovering Unusual Behavior Patterns from Motion Data 從體感資料中發掘異常行為模式 Kai-LinPang 龐凱齡 碩士 國立成功大學 工程科學系 102 As there are more and more surveillance cameras installed in public places, a challenging problem is to discover unusual behavior patterns from a huge amount of video data. However, this task is currently only feasible for human beings because both object recognition and intention detection are still difficult for computer vision algorithms. Recently, with the release of low-cost depth cameras, motion data containing 3D coordinates of skeleton joints can be directly captured, thus facilitating following analysis tasks. In this work, we devise a complete system flow which includes steps of coordinate transformation, normalization, segmentation, feature extraction and dimensionality reduction so as to achieve the purpose of discovering unusual behavior patterns. Note that prior works generally require to predefine (either normal or abnormal) behavior patterns and then utilize data classification techniques for further analysis. Instead, we propose in this work to utilize data clustering techniques to discover unusual behavior patterns so that the inconsistencies of defining behavior patterns in various scenarios can be eased. Specifically, we adopt a density-based clustering technique and adjust the values of two parameters (i.e., radius and minimum points) to appropriately generate unusual behavior patterns. Finally, two datasets including MSR action recognition and AffectME (affective multimodal engagement) are used in our experiments for evaluation purposes. Empirical studies show that our approach is effective for discovering unusual behavior patterns. Wei-Guang Teng 鄧維光 2014 學位論文 ; thesis 48 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 工程科學系 === 102 === As there are more and more surveillance cameras installed in public places, a challenging problem is to discover unusual behavior patterns from a huge amount of video data. However, this task is currently only feasible for human beings because both object recognition and intention detection are still difficult for computer vision algorithms. Recently, with the release of low-cost depth cameras, motion data containing 3D coordinates of skeleton joints can be directly captured, thus facilitating following analysis tasks. In this work, we devise a complete system flow which includes steps of coordinate transformation, normalization, segmentation, feature extraction and dimensionality reduction so as to achieve the purpose of discovering unusual behavior patterns. Note that prior works generally require to predefine (either normal or abnormal) behavior patterns and then utilize data classification techniques for further analysis. Instead, we propose in this work to utilize data clustering techniques to discover unusual behavior patterns so that the inconsistencies of defining behavior patterns in various scenarios can be eased. Specifically, we adopt a density-based clustering technique and adjust the values of two parameters (i.e., radius and minimum points) to appropriately generate unusual behavior patterns. Finally, two datasets including MSR action recognition and AffectME (affective multimodal engagement) are used in our experiments for evaluation purposes. Empirical studies show that our approach is effective for discovering unusual behavior patterns.
author2 Wei-Guang Teng
author_facet Wei-Guang Teng
Kai-LinPang
龐凱齡
author Kai-LinPang
龐凱齡
spellingShingle Kai-LinPang
龐凱齡
Discovering Unusual Behavior Patterns from Motion Data
author_sort Kai-LinPang
title Discovering Unusual Behavior Patterns from Motion Data
title_short Discovering Unusual Behavior Patterns from Motion Data
title_full Discovering Unusual Behavior Patterns from Motion Data
title_fullStr Discovering Unusual Behavior Patterns from Motion Data
title_full_unstemmed Discovering Unusual Behavior Patterns from Motion Data
title_sort discovering unusual behavior patterns from motion data
publishDate 2014
url http://ndltd.ncl.edu.tw/handle/25192086288873642319
work_keys_str_mv AT kailinpang discoveringunusualbehaviorpatternsfrommotiondata
AT pángkǎilíng discoveringunusualbehaviorpatternsfrommotiondata
AT kailinpang cóngtǐgǎnzīliàozhōngfājuéyìchángxíngwèimóshì
AT pángkǎilíng cóngtǐgǎnzīliàozhōngfājuéyìchángxíngwèimóshì
_version_ 1718276085764849664