Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features
Abstract In the military and civilian surveillance domain, it is of great significance to mine regular behaviours of targets for situation awareness and command decision support. Most of the existing trajectory clustering algorithms only consider the similarity of spatial position of the trajectory,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-12-01
|
| Series: | IET Radar, Sonar & Navigation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rsn2.12317 |
| _version_ | 1798019298488221696 |
|---|---|
| author | Qiaowen Jiang Yu Liu Bencai Wang Qifang He Caisheng Zhang Ziran Ding Tao Jian |
| author_facet | Qiaowen Jiang Yu Liu Bencai Wang Qifang He Caisheng Zhang Ziran Ding Tao Jian |
| author_sort | Qiaowen Jiang |
| collection | DOAJ |
| description | Abstract In the military and civilian surveillance domain, it is of great significance to mine regular behaviours of targets for situation awareness and command decision support. Most of the existing trajectory clustering algorithms only consider the similarity of spatial position of the trajectory, without sufficient multi‐dimensional information such as time, course and velocity. Some approaches based on information fusion take these multi‐dimensional information into account, but the features with different dimensions fused by weight coefficients are not robust and universal for different scenarios. In this paper, a regular behaviour mining method based on spatiotemporal trajectory multi‐dimensional features and density clustering is proposed. Firstly, multi‐dimensional Hausdorff similarity is defined to measure spatiotemporal trajectory from different feature dimensionalities. Different from methods based on information fusion, the proposed method defines trajectory density in feature similarity of different dimensions and adaptively determines parameters according to feature distribution in different dimensions. Experimental results in simulated and radar measured trajectory data show that the proposed method can be accurate and robust in clustering evaluation indexes such as Purity, Precision, Recall and Rand Index from different scenarios, which has a good application prospect in intelligent surveillance tasks. |
| first_indexed | 2024-04-11T16:38:29Z |
| format | Article |
| id | doaj.art-94362a85550843a3ab29b3242fff699d |
| institution | Directory Open Access Journal |
| issn | 1751-8784 1751-8792 |
| language | English |
| last_indexed | 2024-04-11T16:38:29Z |
| publishDate | 2022-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Radar, Sonar & Navigation |
| spelling | doaj.art-94362a85550843a3ab29b3242fff699d2022-12-22T04:13:45ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922022-12-0116122067207810.1049/rsn2.12317Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional featuresQiaowen Jiang0Yu Liu1Bencai Wang2Qifang He3Caisheng Zhang4Ziran Ding5Tao Jian6Institute of Information Fusion Naval Aviation University Yantai ChinaInstitute of Information Fusion Naval Aviation University Yantai ChinaAir Force Early Warning Academy Wuhan ChinaInformation and Navigation College Air Force Engineering University Xi'an ChinaDepartment of Electronic Engineering Tsinghua University Beijing ChinaInstitute of Information Fusion Naval Aviation University Yantai ChinaInstitute of Information Fusion Naval Aviation University Yantai ChinaAbstract In the military and civilian surveillance domain, it is of great significance to mine regular behaviours of targets for situation awareness and command decision support. Most of the existing trajectory clustering algorithms only consider the similarity of spatial position of the trajectory, without sufficient multi‐dimensional information such as time, course and velocity. Some approaches based on information fusion take these multi‐dimensional information into account, but the features with different dimensions fused by weight coefficients are not robust and universal for different scenarios. In this paper, a regular behaviour mining method based on spatiotemporal trajectory multi‐dimensional features and density clustering is proposed. Firstly, multi‐dimensional Hausdorff similarity is defined to measure spatiotemporal trajectory from different feature dimensionalities. Different from methods based on information fusion, the proposed method defines trajectory density in feature similarity of different dimensions and adaptively determines parameters according to feature distribution in different dimensions. Experimental results in simulated and radar measured trajectory data show that the proposed method can be accurate and robust in clustering evaluation indexes such as Purity, Precision, Recall and Rand Index from different scenarios, which has a good application prospect in intelligent surveillance tasks.https://doi.org/10.1049/rsn2.12317Hausdorff distancemultidimensional featuresregular behaviourspatiotemporal trajectorytrajectory clustering |
| spellingShingle | Qiaowen Jiang Yu Liu Bencai Wang Qifang He Caisheng Zhang Ziran Ding Tao Jian Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features IET Radar, Sonar & Navigation Hausdorff distance multidimensional features regular behaviour spatiotemporal trajectory trajectory clustering |
| title | Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features |
| title_full | Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features |
| title_fullStr | Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features |
| title_full_unstemmed | Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features |
| title_short | Mining regular behaviors based on spatiotemporal trajectory multi‐dimensional features |
| title_sort | mining regular behaviors based on spatiotemporal trajectory multi dimensional features |
| topic | Hausdorff distance multidimensional features regular behaviour spatiotemporal trajectory trajectory clustering |
| url | https://doi.org/10.1049/rsn2.12317 |
| work_keys_str_mv | AT qiaowenjiang miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures AT yuliu miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures AT bencaiwang miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures AT qifanghe miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures AT caishengzhang miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures AT ziranding miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures AT taojian miningregularbehaviorsbasedonspatiotemporaltrajectorymultidimensionalfeatures |