Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining. Song, L., Jiang, F., Shi, Z., Molina, R., & Katsaggelos, A. K. IEEE Transactions on Intelligent Transportation Systems, 15(3):1273–1285, jun, 2014. ![Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Our work addresses the problem of analyzing and understanding dynamic video scenes. A two-level motion pattern mining approach is proposed. At the first level, activities are modeled as distributions over patch-based features, including spatial location, moving direction, and speed. At the second level, traffic states are modeled as distributions over activities. Both patterns are shared among video clips. Compared to other works, one advantage of our method is that moving speed is considered to describe visual word. The other advantage is that traffic states are detected and assigned to every video frame. These enable finer semantic interpretation, more precise video segmentation, and anomaly detection. Specifically, every video frame is labeled by a certain traffic state, and the video is segmented frame by frame accordingly. Moving pixels in each frame, which do not belong to any activity or cannot exist in the corresponding traffic state, are detected as anomalies. We have successfully tested our approach on some challenging traffic surveillance sequences containing both pedestrian and vehicle motions. © 2000-2011 IEEE.
@article{Lei2014,
abstract = {Our work addresses the problem of analyzing and understanding dynamic video scenes. A two-level motion pattern mining approach is proposed. At the first level, activities are modeled as distributions over patch-based features, including spatial location, moving direction, and speed. At the second level, traffic states are modeled as distributions over activities. Both patterns are shared among video clips. Compared to other works, one advantage of our method is that moving speed is considered to describe visual word. The other advantage is that traffic states are detected and assigned to every video frame. These enable finer semantic interpretation, more precise video segmentation, and anomaly detection. Specifically, every video frame is labeled by a certain traffic state, and the video is segmented frame by frame accordingly. Moving pixels in each frame, which do not belong to any activity or cannot exist in the corresponding traffic state, are detected as anomalies. We have successfully tested our approach on some challenging traffic surveillance sequences containing both pedestrian and vehicle motions. {\textcopyright} 2000-2011 IEEE.},
author = {Song, Lei and Jiang, Fan and Shi, Zhongke and Molina, Rafael and Katsaggelos, Aggelos K.},
doi = {10.1109/TITS.2014.2299403},
issn = {1524-9050},
journal = {IEEE Transactions on Intelligent Transportation Systems},
keywords = {Anomaly detection,Latent Dirichlet Allocation (LDA),motion pattern analysis,video segmentation,visual surveillance},
month = {jun},
number = {3},
pages = {1273--1285},
title = {{Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining}},
url = {https://ieeexplore.ieee.org/document/6746216/},
volume = {15},
year = {2014}
}
Downloads: 0
{"_id":"wbCjbQPtaCCNWR76X","bibbaseid":"song-jiang-shi-molina-katsaggelos-towarddynamicsceneunderstandingbyhierarchicalmotionpatternmining-2014","author_short":["Song, L.","Jiang, F.","Shi, Z.","Molina, R.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"Our work addresses the problem of analyzing and understanding dynamic video scenes. A two-level motion pattern mining approach is proposed. At the first level, activities are modeled as distributions over patch-based features, including spatial location, moving direction, and speed. At the second level, traffic states are modeled as distributions over activities. Both patterns are shared among video clips. Compared to other works, one advantage of our method is that moving speed is considered to describe visual word. The other advantage is that traffic states are detected and assigned to every video frame. These enable finer semantic interpretation, more precise video segmentation, and anomaly detection. Specifically, every video frame is labeled by a certain traffic state, and the video is segmented frame by frame accordingly. Moving pixels in each frame, which do not belong to any activity or cannot exist in the corresponding traffic state, are detected as anomalies. We have successfully tested our approach on some challenging traffic surveillance sequences containing both pedestrian and vehicle motions. © 2000-2011 IEEE.","author":[{"propositions":[],"lastnames":["Song"],"firstnames":["Lei"],"suffixes":[]},{"propositions":[],"lastnames":["Jiang"],"firstnames":["Fan"],"suffixes":[]},{"propositions":[],"lastnames":["Shi"],"firstnames":["Zhongke"],"suffixes":[]},{"propositions":[],"lastnames":["Molina"],"firstnames":["Rafael"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"doi":"10.1109/TITS.2014.2299403","issn":"1524-9050","journal":"IEEE Transactions on Intelligent Transportation Systems","keywords":"Anomaly detection,Latent Dirichlet Allocation (LDA),motion pattern analysis,video segmentation,visual surveillance","month":"jun","number":"3","pages":"1273–1285","title":"Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining","url":"https://ieeexplore.ieee.org/document/6746216/","volume":"15","year":"2014","bibtex":"@article{Lei2014,\nabstract = {Our work addresses the problem of analyzing and understanding dynamic video scenes. A two-level motion pattern mining approach is proposed. At the first level, activities are modeled as distributions over patch-based features, including spatial location, moving direction, and speed. At the second level, traffic states are modeled as distributions over activities. Both patterns are shared among video clips. Compared to other works, one advantage of our method is that moving speed is considered to describe visual word. The other advantage is that traffic states are detected and assigned to every video frame. These enable finer semantic interpretation, more precise video segmentation, and anomaly detection. Specifically, every video frame is labeled by a certain traffic state, and the video is segmented frame by frame accordingly. Moving pixels in each frame, which do not belong to any activity or cannot exist in the corresponding traffic state, are detected as anomalies. We have successfully tested our approach on some challenging traffic surveillance sequences containing both pedestrian and vehicle motions. {\\textcopyright} 2000-2011 IEEE.},\nauthor = {Song, Lei and Jiang, Fan and Shi, Zhongke and Molina, Rafael and Katsaggelos, Aggelos K.},\ndoi = {10.1109/TITS.2014.2299403},\nissn = {1524-9050},\njournal = {IEEE Transactions on Intelligent Transportation Systems},\nkeywords = {Anomaly detection,Latent Dirichlet Allocation (LDA),motion pattern analysis,video segmentation,visual surveillance},\nmonth = {jun},\nnumber = {3},\npages = {1273--1285},\ntitle = {{Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining}},\nurl = {https://ieeexplore.ieee.org/document/6746216/},\nvolume = {15},\nyear = {2014}\n}\n","author_short":["Song, L.","Jiang, F.","Shi, Z.","Molina, R.","Katsaggelos, A. K."],"key":"Lei2014","id":"Lei2014","bibbaseid":"song-jiang-shi-molina-katsaggelos-towarddynamicsceneunderstandingbyhierarchicalmotionpatternmining-2014","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/6746216/"},"keyword":["Anomaly detection","Latent Dirichlet Allocation (LDA)","motion pattern analysis","video segmentation","visual surveillance"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["anomaly detection","latent dirichlet allocation (lda)","motion pattern analysis","video segmentation","visual surveillance"],"search_terms":["toward","dynamic","scene","understanding","hierarchical","motion","pattern","mining","song","jiang","shi","molina","katsaggelos"],"title":"Toward Dynamic Scene Understanding by Hierarchical Motion Pattern Mining","year":2014}