面向智能監(jiān)控攝像頭的監(jiān)控視頻大數(shù)據(jù)分析處理

邵振峰; 蔡家駿; 王中元; 馬照亭

doi:10.11999/JEIT160712

面向智能監(jiān)控攝像頭的監(jiān)控視頻大數(shù)據(jù)分析處理

doi: 10.11999/JEIT160712 cstr: 32379.14.JEIT160712

基金項目:

中央高校基本科研業(yè)務(wù)費(fèi)專項資金(2042016kf0179, 2042016kf1019, 2042016gf0033)，2016年廣州市科技計劃資助項目(201604020070)，測繪地理信息公益性行業(yè)科研專項經(jīng)費(fèi)項目(201512027)，湖北省自然科學(xué)基金(2015CFB406)，武漢市應(yīng)用基礎(chǔ)研究計劃項目(2016010101010025)

計量
- 文章訪問數(shù): 2198
- HTML全文瀏覽量: 373
- PDF下載量: 582
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-07-07
- 修回日期: 2016-12-13
- 刊出日期: 2017-05-19

Analytical Processing Method of Big Surveillance Video Data Based on Smart Monitoring Cameras

Funds:

The Fundamental Research Funds for the Central Universities (2042016kf0179, 2042016kf1019, 2042016 gf0033), The Guangzhou Science and Technology Project (2016- 04020070), The Special Funds Project on Public Welfare Industry Research of Surveying and Mapping Geographic Information (201512027), The Natural Science Fund of Hubei Province (2015CFB406), The Applied Basic Research Program of Wuhan City (2016010101010025)

摘要

摘要: 視頻監(jiān)控是安防的重要組成部分，智能監(jiān)控攝像頭以其豐富的異常行為識別功能，極大地增強(qiáng)了監(jiān)控場所的安全。隨著部署的智能攝像頭日漸增多以及視頻監(jiān)控網(wǎng)規(guī)模的不斷擴(kuò)大，海量的視頻數(shù)據(jù)給存儲、檢索及分析帶來了巨大挑戰(zhàn)。該文提出智能攝像頭異常報警事件驅(qū)動的監(jiān)控視頻大數(shù)據(jù)智能處理方法，具體包括：多點關(guān)聯(lián)分析的異常事件自動預(yù)警、事件驅(qū)動的監(jiān)控視頻選擇性存儲以及異常行為事件約束的關(guān)聯(lián)檢索，以期提高大數(shù)據(jù)時代監(jiān)控視頻數(shù)據(jù)的深度利用效率。實踐案例證實，所提方法能夠?qū)崿F(xiàn)異常事件的可信預(yù)警，錄像視頻選擇性的高效保存和破案線索的快速發(fā)現(xiàn)。
- 監(jiān)控視頻大數(shù)據(jù) /
- 關(guān)聯(lián)分析 /
- 異常事件預(yù)警 /
- 智能檢索 /
- 智能監(jiān)控系統(tǒng)
Abstract: As an important part in the security and protection system of cities, smart monitoring cameras which are equipped with intelligent video analytics ability can monitor in different scenes and pre-alarm abnormal behaviors or events. Nevertheless, with the growing number of smart monitoring cameras, the challenges to analytics, storage and retrieval of massive surveillance video data need to be solved in the big data era. This paper proposes an intelligent processing method which makes full use of smart cameras to big surveillance video data. The method consists of three parts: the intelligent pre-alarming for abnormal events, smart storage for surveillance video and rapid retrieval for evidence videos, which aim to improve the utilization efficiency of surveillance video data. Experimental results prove that the proposed approach can reliably pre-alarm abnormal events, efficiently reduce storage space of recorded video and significantly improve the evidence video retrieval rates associated with specific suspects.
- Big surveillance video data /
- Association analysis /
- Pre-alarming of abnormal events /
- Intelligent retrieval /
- Intelligent surveillance system

HTML全文

參考文獻(xiàn)(17)

DBOUK M, MCHEICK H, and SBEITY I. CityPro; an integrated city-protection collaborative platform[J]. Procedia Computer Science, 2014, 37: 72-79. doi: 10.1016/j.procs.2014.　08.014

黃凱奇, 陳曉棠, 康運(yùn)鋒, 等. 智能視頻監(jiān)控技術(shù)綜述[J]. 計算機(jī)學(xué)報, 2015, 38(6): 1093-1118. doi: 10.11897/SP.J.1016. 2015.01093.

HUANG Kaiqi, CHEN Xiaotang, KANG Yunfeng, et al. Intelligent visual surveillance: A review[J]. Chinese Journal of Computers, 2015, 38(6): 1093-1118. doi: 10.11897/SP.J.1016. 2015.01093.

張誠, 馬華東, 傅慧源. 基于時空關(guān)聯(lián)圖模型的視頻監(jiān)控目標(biāo)跟蹤[J]. 北京航空航天大學(xué)學(xué)報, 2015, 41(4): 713-720. doi: 10.13700/j.bh.1001-5965.2014.0472.

ZHANG Cheng, MA Huadong, and FU Huiyuan. Object tracking in surveillance videos using spatial-temporal correlation graph model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2015, 41(4): 713-720. doi: 10.13700/j.bh.1001-5965.2014.0472 .

GUO Xiaoyan, CAO Yu, and TAO Jun. SVIS: Large Scale Video Data Ingestion into Big Data Platform[M]. Hanoi: Springer, 2015: 300-306.

SHVACHKO K, KUANG H, RADIA S, et al. The hadoop distributed file system[C]. IEEE 26th Symposium on MASS Storage Systems and Technologies, Nevada, 2010: 1-10. doi: 10.1109/MSST.2010.5496972.

KIM H, LEE S, KIM Y, et al. Weighted joint-based human behavior recognition algorithm using only depth information for low-cost intelligent video-surveillance system[J]. Expert Systems with Applications, 2016, 45(C): 131-141. doi: 10.1016 /j.eswa.2015.09.035.

CHEN Chunyu, SHAO Yu, and BI Xiaojun. Detection of anomalous crowd behavior based on the acceleration feature[J]. IEEE Sensors Journal, 2015, 15(12): 7252-7261. doi: 10.1109/JSEN.2015.2472960.

CALDERARA S, CUCCHIARA R, and PRATI A. Detection of abnormal behaviors using a mixture of Von Mises distributions[C]. IEEE International Conference on Advanced Video and Signal Based Surveillance, London, 2007: 141-146. doi: 10.1109/AVSS.2007.4425300.

BALLAN L, BERTINI M, DEL BIMBO A, et al. Effective codebooks for human action categorization[C]. IEEE 12th International Conference on Computer Vision Workshops, Kyoto, 2009: 506-513. doi: 10.1109/ICCVW.2009.5457658.

WANG Kejun and OLUWATOYIN P P. Ant-based clustering of visual-words for unsupervised human action recognition[C]. World Congress on Nature and Biologically Inspired Computing, Fukuoka, 2010: 654-659. doi: 10.1109/NABIC. 2010.5716377.

COLLINS R T, LIPTON A J, KANADE T, et al. A system for video surveillance and monitoring[R]. Technical report CMU-RI-TR-00-12, Pittsburgh: Camegie Mellon University, 2000.

HUANG Kaiqi and TAN Tieniu. Vs-star: A visual interpretation system for visual surveillance[J]. Pattern Recognition Letters, 2010, 31(14): 2265-2285. doi: 10.1016/j. patrec. 2010.05.029.

GARCIA C R, QUESADAARENCIBIA A, CRISTOBAL T, et al. An intelligent system proposal for improving the safety and accessibility of public transit by highway[J]. Sensors, 2015, 15(8): 20279-20304. doi: 10.3390/s150820279.

HANCKE G P, SILVA B C, and HANCKE G P. The role of advanced sensing in smart cities[J]. Sensors, 2012, 13(1): 393-425. doi: 10.3390/s130100393.

HELBING D and BALIETTI S. From social data mining to forecasting socio-economic crises[J]. European Physical Journal Special Topics, 2011, 195(1): 3-68. doi: 10.1140/ epjst/e2011-01401-8.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計