%0 Conference Paper %1 liao2010detection %A Liao, Zhenmei %A Yang, Su %A Liang, Jianning %B Proceedings of the 2010 IEEE/ACM Int'L Conference on Green Computing and Communications & Int'L Conference on Cyber, Physical and Social Computing %C Washington, DC, USA %D 2010 %I IEEE Computer Society %K anomality crowd detection human markus mobility ring security %P 600--604 %R 10.1109/GreenCom-CPSCom.2010.51 %T Detection of Abnormal Crowd Distribution %U http://dx.doi.org/10.1109/GreenCom-CPSCom.2010.51 %X With the application of GPS and popularity of intelligent cell phones, the physical location of a person can be easily obtained. Thus, we attempt to analyze the spatial distribution of crowd to facilitate the swift response to the emergency of public security. The states of crowd can be represented as the spatial distribution of moving points. The fractal features are used to describe the degree of gathering of points. PCA removes the disturbed factors from feature vector so as to keep only relevant information. The abnormal distributions of crowd, which are usually caused by natural disasters or special affairs, are detected with the proposed NPA (neighboring points accumulated) algorithm. The experiment on levy-flight simulation data shows that the proposed method is effective and reliable. %@ 978-0-7695-4331-4

@inproceedings{liao2010detection, abstract = {With the application of GPS and popularity of intelligent cell phones, the physical location of a person can be easily obtained. Thus, we attempt to analyze the spatial distribution of crowd to facilitate the swift response to the emergency of public security. The states of crowd can be represented as the spatial distribution of moving points. The fractal features are used to describe the degree of gathering of points. PCA removes the disturbed factors from feature vector so as to keep only relevant information. The abnormal distributions of crowd, which are usually caused by natural disasters or special affairs, are detected with the proposed NPA (neighboring points accumulated) algorithm. The experiment on levy-flight simulation data shows that the proposed method is effective and reliable.}, acmid = {1953470}, added-at = {2017-02-25T17:41:37.000+0100}, address = {Washington, DC, USA}, author = {Liao, Zhenmei and Yang, Su and Liang, Jianning}, biburl = {https://www.bibsonomy.org/bibtex/24a4aa8f2de306f998da301fd31fe6607/becker}, booktitle = {Proceedings of the 2010 IEEE/ACM Int'L Conference on Green Computing and Communications \& Int'L Conference on Cyber, Physical and Social Computing}, description = {Detection of Abnormal Crowd Distribution}, doi = {10.1109/GreenCom-CPSCom.2010.51}, interhash = {32697a45ad721d92e97a169e98c642d3}, intrahash = {4a4aa8f2de306f998da301fd31fe6607}, isbn = {978-0-7695-4331-4}, keywords = {anomality crowd detection human markus mobility ring security}, numpages = {5}, pages = {600--604}, publisher = {IEEE Computer Society}, series = {GREENCOM-CPSCOM '10}, timestamp = {2017-02-25T17:43:19.000+0100}, title = {Detection of Abnormal Crowd Distribution}, url = {http://dx.doi.org/10.1109/GreenCom-CPSCom.2010.51}, year = 2010 }