Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation
碩士 === 國立臺灣科技大學 === 電子工程系 === 102 === In this theme, we consider the analysis of abnormally behavior in surveillance system. To simplify the problem, we formalized it as an outlier detection problem. In our case, all behaviors in training data are normal. By creating a model by training data, we can...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/95546677836042558374 |
id |
ndltd-TW-102NTUS5428164 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-102NTUS54281642016-03-09T04:30:59Z http://ndltd.ncl.edu.tw/handle/95546677836042558374 Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation 以核函式為基礎的直接密度比率估測在雍塞環境下局部異常行為偵測 Chih-Yuan Lee 李治原 碩士 國立臺灣科技大學 電子工程系 102 In this theme, we consider the analysis of abnormally behavior in surveillance system. To simplify the problem, we formalized it as an outlier detection problem. In our case, all behaviors in training data are normal. By creating a model by training data, we can define abnormalities whose probability is below a certain threshold under this model. Based on this, we use Kullback–Leibler importance estimation procedure (KLIEP) to compute the ratio of training data and testing data which we used as our inlier score. The KLIEP is a method to estimate the inlier score, not the probability densities themselves. This formulation allows us to avoid non-parametric density estimation, which is known to be a difficult task. After computing inlier score by KLIEP, we create a model by training data and testing data. According to this model, other testing data can also get a inlier score which can represent the degree of similarity between training data and testing data. Based on the concept of inlier-based outlier detection and normal score, we can determine an appropriate threshold and find which location at testing data is abnormal. In our evaluation we used PASCAL metric to evaluate our localization rate by ground truth. Through computer simulations, we find that our method has high accuracy of localization rate in UCSD dataset compared with previous works. Wen-Hsien Fang 方文賢 2014 學位論文 ; thesis 46 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣科技大學 === 電子工程系 === 102 === In this theme, we consider the analysis of abnormally behavior in surveillance system. To simplify the problem, we formalized it as an outlier detection problem. In our case, all behaviors in training data are normal. By creating a model by training data, we can define abnormalities whose probability is below a certain threshold under this model.
Based on this, we use Kullback–Leibler importance estimation procedure (KLIEP) to compute the ratio of training data and testing data which we used as our inlier score. The KLIEP is a method to estimate the inlier score, not the probability densities themselves. This formulation allows us to avoid non-parametric density estimation, which is known to be a difficult task.
After computing inlier score by KLIEP, we create a model by training data and testing data. According to this model, other testing data can also get a inlier score which can represent the degree of similarity between training data and testing data. Based on the concept of inlier-based outlier detection and normal score, we can determine an appropriate threshold and find which location at testing data is abnormal.
In our evaluation we used PASCAL metric to evaluate our localization rate by ground truth. Through computer simulations, we find that our method has high accuracy of localization rate in UCSD dataset compared with previous works.
|
author2 |
Wen-Hsien Fang |
author_facet |
Wen-Hsien Fang Chih-Yuan Lee 李治原 |
author |
Chih-Yuan Lee 李治原 |
spellingShingle |
Chih-Yuan Lee 李治原 Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation |
author_sort |
Chih-Yuan Lee |
title |
Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation |
title_short |
Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation |
title_full |
Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation |
title_fullStr |
Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation |
title_full_unstemmed |
Abnormal Crowd Behavior Detection and Localization via Kernel Based Direct Density Ratio Estimation |
title_sort |
abnormal crowd behavior detection and localization via kernel based direct density ratio estimation |
publishDate |
2014 |
url |
http://ndltd.ncl.edu.tw/handle/95546677836042558374 |
work_keys_str_mv |
AT chihyuanlee abnormalcrowdbehaviordetectionandlocalizationviakernelbaseddirectdensityratioestimation AT lǐzhìyuán abnormalcrowdbehaviordetectionandlocalizationviakernelbaseddirectdensityratioestimation AT chihyuanlee yǐhéhánshìwèijīchǔdezhíjiēmìdùbǐlǜgūcèzàiyōngsāihuánjìngxiàjúbùyìchángxíngwèizhēncè AT lǐzhìyuán yǐhéhánshìwèijīchǔdezhíjiēmìdùbǐlǜgūcèzàiyōngsāihuánjìngxiàjúbùyìchángxíngwèizhēncè |
_version_ |
1718202392950865920 |