Video Sensor-Based Complex Scene Analysis with Granger Causality
In this report, we propose a novel framework to explore the activity interactions and temporal dependencies between activities in complex video surveillance scenes. Under our framework, a low-level codebook is generated by an adaptive quantization with respect to the activeness criterion. The Hierar...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2013-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/13/10/13685 |
id |
doaj-9b76894268f243d98afd079cad1c4c72 |
---|---|
record_format |
Article |
spelling |
doaj-9b76894268f243d98afd079cad1c4c722020-11-24T20:48:01ZengMDPI AGSensors1424-82202013-10-011310136851370710.3390/s131013685Video Sensor-Based Complex Scene Analysis with Granger CausalityShuang WuShibao ZhengHua YangYawen FanHang SuIn this report, we propose a novel framework to explore the activity interactions and temporal dependencies between activities in complex video surveillance scenes. Under our framework, a low-level codebook is generated by an adaptive quantization with respect to the activeness criterion. The Hierarchical Dirichlet Processes (HDP) model is then applied to automatically cluster low-level features into atomic activities. Afterwards, the dynamic behaviors of the activities are represented as a multivariate point-process. The pair-wise relationships between activities are explicitly captured by the non-parametric Granger causality analysis, from which the activity interactions and temporal dependencies are discovered. Then, each video clip is labeled by one of the activity interactions. The results of the real-world traffic datasets show that the proposed method can achieve a high quality classification performance. Compared with traditional K-means clustering, a maximum improvement of 19.19% is achieved by using the proposed causal grouping method.http://www.mdpi.com/1424-8220/13/10/13685video surveillancescene analysistopic modelpoint processGranger causality |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shuang Wu Shibao Zheng Hua Yang Yawen Fan Hang Su |
spellingShingle |
Shuang Wu Shibao Zheng Hua Yang Yawen Fan Hang Su Video Sensor-Based Complex Scene Analysis with Granger Causality Sensors video surveillance scene analysis topic model point process Granger causality |
author_facet |
Shuang Wu Shibao Zheng Hua Yang Yawen Fan Hang Su |
author_sort |
Shuang Wu |
title |
Video Sensor-Based Complex Scene Analysis with Granger Causality |
title_short |
Video Sensor-Based Complex Scene Analysis with Granger Causality |
title_full |
Video Sensor-Based Complex Scene Analysis with Granger Causality |
title_fullStr |
Video Sensor-Based Complex Scene Analysis with Granger Causality |
title_full_unstemmed |
Video Sensor-Based Complex Scene Analysis with Granger Causality |
title_sort |
video sensor-based complex scene analysis with granger causality |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2013-10-01 |
description |
In this report, we propose a novel framework to explore the activity interactions and temporal dependencies between activities in complex video surveillance scenes. Under our framework, a low-level codebook is generated by an adaptive quantization with respect to the activeness criterion. The Hierarchical Dirichlet Processes (HDP) model is then applied to automatically cluster low-level features into atomic activities. Afterwards, the dynamic behaviors of the activities are represented as a multivariate point-process. The pair-wise relationships between activities are explicitly captured by the non-parametric Granger causality analysis, from which the activity interactions and temporal dependencies are discovered. Then, each video clip is labeled by one of the activity interactions. The results of the real-world traffic datasets show that the proposed method can achieve a high quality classification performance. Compared with traditional K-means clustering, a maximum improvement of 19.19% is achieved by using the proposed causal grouping method. |
topic |
video surveillance scene analysis topic model point process Granger causality |
url |
http://www.mdpi.com/1424-8220/13/10/13685 |
work_keys_str_mv |
AT shuangwu videosensorbasedcomplexsceneanalysiswithgrangercausality AT shibaozheng videosensorbasedcomplexsceneanalysiswithgrangercausality AT huayang videosensorbasedcomplexsceneanalysiswithgrangercausality AT yawenfan videosensorbasedcomplexsceneanalysiswithgrangercausality AT hangsu videosensorbasedcomplexsceneanalysiswithgrangercausality |
_version_ |
1716809169028251648 |