{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:08:48Z","timestamp":1777705728198,"version":"3.51.4"},"reference-count":31,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2022,3,4]]},"abstract":"<jats:p>Crowd panic detection (CPD) is crucial to control crowd disasters. The recent CPD approaches fail to address crowd shape change due to perspective distortion in the frame and across the frames. To this end, we are motivated to design a simple but most effective model known as multiscale spatial-temporal atrous-net and principal component analysis (PCA) guided one-class support vector machine (OC-SVM), i.e., MuST-POS for the CPD. The proposed model utilizes two multiscale atrous-net to extract multiscale spatial and multiscale temporal features to model crowd scenes. Then we adopted PCA to reduce the dimension of the extracted multiscale features and fed them into an OC-SVM for modeling normal crowd scenes. The outliers of the OC-SVM are treated as crowd panic behavior. Three publicly available datasets: the UMN, the MED, and the Pets-2009, are used to show the effectiveness of the proposed MuST-POS. The MuST-POS achieves the detection accuracy of 99.40%, 97.61%, and 98.37% on the UMN, the MED, and the Pets-2009 datasets, respectively, and performs better to recent state-of-the-art approaches.<\/jats:p>","DOI":"10.3233\/jifs-211556","type":"journal-article","created":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T11:42:14Z","timestamp":1642765334000},"page":"3501-3516","source":"Crossref","is-referenced-by-count":7,"title":["MuST-POS: multiscale spatial-temporal 3D atrous-net and PCA guided OC-SVM for crowd panic detection"],"prefix":"10.1177","volume":"42","author":[{"given":"Santosh Kumar","family":"Tripathy","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Computing and Vision Lab, Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Repala","family":"Sudhamsh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Computing and Vision Lab, Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subodh","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, National Institute of Technology, Patna, Bihar, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajeev","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Computing and Vision Lab, Indian Institute of Technology (BHU), Varanasi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-211556_ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.010"},{"key":"10.3233\/JIFS-211556_ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-021-00220-7"},{"key":"10.3233\/JIFS-211556_ref3","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s00530-020-00667-4","article-title":"A real-time two-input stream multi-column multi-stage convolution neural network (TIS-MCMS-CNN) for efficient crowd congestion-level analysis","volume":"26","author":"Tripathy","year":"2020","journal-title":"Multimed Syst"},{"key":"10.3233\/JIFS-211556_ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"10.3233\/JIFS-211556_ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298909"},{"key":"10.3233\/JIFS-211556_ref6","doi-asserted-by":"publisher","first-page":"39172","DOI":"10.1109\/ACCESS.2019.2906275","article-title":"A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks","volume":"7","author":"Song","year":"2019","journal-title":"IEEE Access"},{"key":"10.3233\/JIFS-211556_ref7","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.comnet.2019.01.028","article-title":"Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional LSTM","volume":"151","author":"Dinesh","year":"2019","journal-title":"Comput Networks"},{"key":"10.3233\/JIFS-211556_ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301284"},{"key":"10.3233\/JIFS-211556_ref9","doi-asserted-by":"crossref","first-page":"8.1","DOI":"10.5244\/C.29.8","article-title":"Learning Deep Representations of Appearance and Motion for Anomalous Event Detection","volume":"2015","author":"Xu","year":"2015","journal-title":"Procedings Br Mach Vis Conf"},{"key":"10.3233\/JIFS-211556_ref10","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1049\/iet-cvi.2018.5240","article-title":"Autoencoder-based abnormal activity detection using parallelepiped spatio-temporal region","volume":"13","author":"George","year":"2018","journal-title":"IET Comput Vis"},{"key":"10.3233\/JIFS-211556_ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"10.3233\/JIFS-211556_ref13","doi-asserted-by":"publisher","first-page":"1992","DOI":"10.1109\/TIP.2017.2670780","article-title":"Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes","volume":"26","author":"Sabokrou","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"10.3233\/JIFS-211556_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00206"},{"key":"10.3233\/JIFS-211556_ref16","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1109\/TPAMI.2012.131","article-title":"A prototype learning framework using EMD: Application to complex scenes analysis","volume":"35","author":"Ricci","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.3233\/JIFS-211556_ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2017.19"},{"key":"10.3233\/JIFS-211556_ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2866838"},{"key":"10.3233\/JIFS-211556_ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247917"},{"key":"10.3233\/JIFS-211556_ref20","doi-asserted-by":"publisher","first-page":"31101","DOI":"10.1007\/s11042-019-07806-8","article-title":"Detecting anomalous crowd scenes by oriented Tracklets\u2019 approach in active contour region","volume":"78","author":"Lamba","year":"2019","journal-title":"Multimed Tools Appl"},{"key":"10.3233\/JIFS-211556_ref21","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.image.2016.06.007","article-title":"Spatial-temporal convolutional neural networks for anomaly detection and localization in crowded scenes","volume":"47","author":"Zhou","year":"2016","journal-title":"Signal Process Image Commun"},{"key":"10.3233\/JIFS-211556_ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00188"},{"key":"10.3233\/JIFS-211556_ref25","doi-asserted-by":"crossref","first-page":"757","DOI":"10.3390\/app9040757","article-title":"An On-Line and Adaptive Method for Detecting Abnormal Events in Videos Using Spatio-Temporal ConvNet","volume":"9","author":"Bouindour","year":"2019","journal-title":"Appl Sci"},{"key":"10.3233\/JIFS-211556_ref29","unstructured":"Statistical visual computing laboratory (SVCL) at UC SanDiego (UCSD) UCSD Anomaly Detection Dataset."},{"key":"10.3233\/JIFS-211556_ref30","doi-asserted-by":"publisher","first-page":"40","DOI":"10.5815\/ijigsp.2019.10.06","article-title":"Crowd Escape Event Detection via Pooling Features of Optical Flow for Intelligent Video Surveillance Systems","volume":"11","author":"Singh","year":"2019","journal-title":"Int J Image, Graph Signal Process"},{"key":"10.3233\/JIFS-211556_ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-021-01182-w"},{"key":"10.3233\/JIFS-211556_ref32","doi-asserted-by":"publisher","first-page":"24851","DOI":"10.1007\/s11042-020-09024-z","article-title":"Real-time frequency-based detection of a panic behavior in human crowds","volume":"79","author":"Aldissi","year":"2020","journal-title":"Multimed Tools Appl"},{"key":"10.3233\/JIFS-211556_ref33","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1007\/s00138-018-0974-3","article-title":"Statistical detection of a panic behavior in crowded scenes","volume":"30","author":"Shehab","year":"2019","journal-title":"Mach Vis Appl"},{"key":"10.3233\/JIFS-211556_ref34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.inffus.2014.09.005","article-title":"Towards crowd density-aware video surveillance applications","volume":"24","author":"Fradi","year":"2015","journal-title":"Inf Fusion"},{"key":"10.3233\/JIFS-211556_ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2276151"},{"key":"10.3233\/JIFS-211556_ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00127"},{"key":"10.3233\/JIFS-211556_ref37","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.cviu.2018.02.006","article-title":"Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes","volume":"172","author":"Sabokrou","year":"2018","journal-title":"Comput Vis Image Underst"},{"key":"10.3233\/JIFS-211556_ref38","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/6323942"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-211556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:00Z","timestamp":1777455900000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-211556"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,4]]},"references-count":31,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/jifs-211556","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,4]]}}}