{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:13:20Z","timestamp":1766067200243,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Crowd surveillance plays a key role to ensure safety and security in public areas. Surveillance systems traditionally rely on fixed camera networks, which suffer from limitations, as coverage of the monitored area, video resolution and analytic performance. On the other hand, a smart camera network provides the ability to reconfigure the sensing infrastructure by incorporating active devices such as pan-tilt-zoom (PTZ) cameras and UAV-based cameras, thus enabling the network to adapt over time to changes in the scene. We propose a new decentralised approach for network reconfiguration, where each camera dynamically adapts its parameters and position to optimise scene coverage. Two policies for decentralised camera reconfiguration are presented: a greedy approach and a reinforcement learning approach. In both cases, cameras are able to locally control the state of their neighbourhood and dynamically adjust their position and PTZ parameters. When crowds are present, the network balances between global coverage of the entire scene and high resolution for the crowded areas. We evaluate our approach in a simulated environment monitored with fixed, PTZ and UAV-based cameras.<\/jats:p>","DOI":"10.3390\/s20174691","type":"journal-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T09:35:31Z","timestamp":1597916131000},"page":"4691","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Dynamic Camera Reconfiguration with Reinforcement Learning and Stochastic Methods for Crowd Surveillance"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5704-5785","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Bisagno","sequence":"first","affiliation":[{"name":"Department of Information Engineering and Computer Science (DISI), University of Trento, 38121 Trento, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9744-4684","authenticated-orcid":false,"given":"Alberto","family":"Xamin","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science (DISI), University of Trento, 38121 Trento, Italy"}]},{"given":"Francesco","family":"De Natale","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science (DISI), University of Trento, 38121 Trento, Italy"}]},{"given":"Nicola","family":"Conci","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science (DISI), University of Trento, 38121 Trento, Italy"}]},{"given":"Bernhard","family":"Rinner","sequence":"additional","affiliation":[{"name":"Institute of Networked and Embedded Systems (NES), University of Klagenfurt, 9020 Klagenfurt, Austria"}]}],"member":"1968","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Konda, K.R., and Conci, N. (November, January 29). Optimal configuration of PTZ camera networks based on visual quality assessment and coverage maximization. Proceedings of the 2013 Seventh International Conference on Distributed Smart Cameras (ICDSC), Palm Springs, CA, USA.","DOI":"10.1109\/ICDSC.2013.6778202"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lewis, P., Esterle, L., Chandra, A., Rinner, B., and Yao, X. (2013, January 9\u201313). Learning to be different: Heterogeneity and efficiency in distributed smart camera networks. Proceedings of the 2013 IEEE 7th International Conference on Self-Adaptive and Self-Organizing Systems, Philadelphia, PA, USA.","DOI":"10.1109\/SASO.2013.20"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/MC.2014.134","article-title":"Smart Camera Networks","volume":"47","author":"Reisslein","year":"2014","journal-title":"IEEE Comput."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1016\/j.neucom.2019.08.021","article-title":"Data-driven crowd evacuation: A reinforcement learning method","volume":"366","author":"Yao","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Qureshi, F.Z., and Terzopoulos, D. (2007, January 17\u201322). Surveillance in virtual reality: System design and multi-camera control. Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383071"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Taylor, G.R., Chosak, A.J., and Brewer, P.C. (2007, January 17\u201322). Ovvv: Using virtual worlds to design and evaluate surveillance systems. Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383518"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3109","DOI":"10.1109\/TIM.2019.2927650","article-title":"Visual Sensor Placement Based on Risk Maps","volume":"69","author":"Altahir","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bour, P., Cribelier, E., and Argyriou, V. (2019). Crowd behavior analysis from fixed and moving cameras. Multimodal Behavior Analysis in the Wild, Academic Press.","DOI":"10.1016\/B978-0-12-814601-9.00023-7"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bisagno, N., Conci, N., and Rinner, B. (2018, January 3\u20134). Dynamic Camera Network Reconfiguration for Crowd Surveillance. Proceedings of the 12th International Conference on Distributed Smart Cameras, Eindhoven, The Netherlands.","DOI":"10.1145\/3243394.3243704"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/MCOM.2017.1600587CM","article-title":"UAV-based IoT platform: A crowd surveillance use case","volume":"55","author":"Motlagh","year":"2017","journal-title":"IEEE Commun. Mag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"48572","DOI":"10.1109\/ACCESS.2019.2909530","article-title":"Unmanned aerial vehicles (UAVs): A survey on civil applications and key research challenges","volume":"7","author":"Shakhatreh","year":"2019","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1109\/TAC.2015.2450611","article-title":"A payoff-based learning approach to cooperative environmental monitoring for PTZ visual sensor networks","volume":"61","author":"Hatanaka","year":"2015","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Khan, M.I., and Rinner, B. (2012, January 19\u201323). Resource coordination in wireless sensor networks by cooperative reinforcement learning. Proceedings of the 2012 IEEE International Conference on Pervasive Computing and Communications Workshops, Lugano, Switzerland.","DOI":"10.1109\/PerComW.2012.6197639"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Khan, U.A., and Rinner, B. (2012, January 20\u201323). A reinforcement learning framework for dynamic power management of a portable, multi-camera traffic monitoring system. Proceedings of the 2012 IEEE International Conference on Green Computing and Communications, Besancon, France.","DOI":"10.1109\/GreenCom.2012.85"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rudolph, S., Edenhofer, S., Tomforde, S., and H\u00e4hner, J. (2014, January 4\u20137). Reinforcement learning for coverage optimization through PTZ camera alignment in highly dynamic environments. Proceedings of the International Conference on Distributed Smart Cameras, Venezia Mestre, Italy.","DOI":"10.1145\/2659021.2659052"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","article-title":"Social force model for pedestrian dynamics","volume":"51","author":"Helbing","year":"1995","journal-title":"Phys. Rev. E"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1109\/MSP.2010.937333","article-title":"Video Analysis in PTZ Camera Networks - From master-slave to cooperative smart cameras","volume":"27","author":"Micheloni","year":"2010","journal-title":"IEEE Signal Process Mag."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Foresti, G.L., M\u00e4h\u00f6nen, P., and Regazzoni, C.S. (2000). Multimedia Video-Based Surveillance Systems: Requirements, Issues and Solutions, Springer Science & Business Media.","DOI":"10.1007\/978-1-4615-4327-5"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MMUL.2007.3","article-title":"Automated visual surveillance in realistic scenarios","volume":"14","author":"Shah","year":"2007","journal-title":"IEEE MultiMedia"},{"key":"ref_20","first-page":"66","article-title":"Crowd analysis using computer vision techniques","volume":"27","author":"Junior","year":"2010","journal-title":"IEEE Signal Process Mag."},{"key":"ref_21","unstructured":"Azzari, P., Di Stefano, L., and Bevilacqua, A. (2005, January 15\u201316). An effective real-time mosaicing algorithm apt to detect motion through background subtraction using a PTZ camera. Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, Como, Italy."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kang, S., Paik, J.K., Koschan, A., Abidi, B.R., and Abidi, M.A. (2003). Real-time video tracking using PTZ cameras. Sixth International Conference on Quality Control by Artificial Vision. Proc. SPIE Int. Soc. Opt. Eng., 103\u2013112.","DOI":"10.1117\/12.514945"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Bevilacqua, A., and Azzari, P. (2006, January 22\u201324). High-quality real time motion detection using ptz cameras. Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance, Sydney, Australia.","DOI":"10.1109\/AVSS.2006.57"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MC.2015.209","article-title":"Self-aware and self-expressive camera networks","volume":"48","author":"Rinner","year":"2014","journal-title":"IEEE Computer"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ryan, A., Zennaro, M., Howell, A., Sengupta, R., and Hedrick, J.K. (2004, January 14\u201317). An overview of emerging results in cooperative UAV control. Proceedings of the 43rd IEEE Conference on Decision and Control, Nassau, Bahamas.","DOI":"10.1109\/CDC.2004.1428700"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.adhoc.2017.09.001","article-title":"Drone networks: Communications, coordination, and sensing","volume":"68","author":"Yanmaz","year":"2018","journal-title":"Ad Hoc Networks"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1109\/TCYB.2016.2628161","article-title":"Cooperative Robots to Observe Moving Targets: A Review","volume":"48","author":"Khan","year":"2018","journal-title":"IEEE Trans. Cybern."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1109\/TCSVT.2017.2669658","article-title":"Guest Editorial Introduction to the Special Issue on Group and Crowd Behavior Analysis for Intelligent Multicamera Video Surveillance","volume":"27","author":"Yao","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_29","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement learning: An introduction, MIT Press."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Esterle, L. (2017, January 18\u201322). Centralised, decentralised, and self-organised coverage maximisation in smart camera networks. Proceedings of the 2017 IEEE 11th International Conference on Self-Adaptive and Self-Organizing Systems (SASO), Tucson, AZ, USA.","DOI":"10.1109\/SASO.2017.9"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Vejdanparast, A., Lewis, P.R., and Esterle, L. (2018, January 3\u20134). Online zoom selection approaches for coverage redundancy in visual sensor networks. Proceedings of the 12th International Conference on Distributed Smart Cameras, Eindhoven, The Netherlands.","DOI":"10.1145\/3243394.3243697"},{"key":"ref_32","unstructured":"Jones, M., and Viola, P. (2003). Fast Multi-View Face Detection, Mitsubishi Electric Research Lab.. Technical Report TR-20003-96."},{"key":"ref_33","unstructured":"Juliani, A., Berges, V.P., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C., Gao, Y., Henry, H., and Mattar, M. (2018). Unity: A General Platform for Intelligent Agents. arXiv."},{"key":"ref_34","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018). Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/17\/4691\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:03:43Z","timestamp":1760177023000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/17\/4691"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":34,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20174691"],"URL":"https:\/\/doi.org\/10.3390\/s20174691","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2020,8,20]]}}}