BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/St_Johns BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0430 TZOFFSETTO:-0330 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:NDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0330 TZOFFSETTO:-0430 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:NST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20231203T143840Z UID:669F67E0-07B2-49CE-9B55-EFDE3BD8229D DTSTART;TZID=America/St_Johns:20231130T093000 DTEND;TZID=America/St_Johns:20231130T103000 DESCRIPTION:Dear all\,\n\nWe kindly invite you to attend the 1st invited te chnical talk orgaized by IEEE OES NL Chapter for 2023\, the talk informati on:\n\nThe title of the talk:\n\nUnderwater Image Enhancement Based on Rei nforcement Learning\n\nAbstract:\n\nReinforcement learning is a family of methods for optimizing models in a sequential trial-and-error fashion. It can achieve optimal results for complicated models which can hardly be add ressed by ordinary optimization methods. Underwater optical imaging involv es complicated procedures including imaging process\, visualization\, and applications such as object detection in underwater optical images. How to achieve underwater optimal optical imaging for the purpose of high-qualit y image enhancement\, good visualization and accurate object detection rem ains challenging problems. To address these challenges\, we develop reinfo rcement learning strategies for optimizing the three procedures involved i n underwater optical imaging. Specifically\, we describe how to conduct op timal configuration of underwater optical imaging process\, how to obtain optimal representation by underwater optical visualization\, and how to ac hieve optimal performance for underwater optical object detection. Our pre liminary study paves a possible way for exploiting reinforcement learning for obtaining underwater optimal optical imaging results.\n\nPresenter:\n\ nDr. Peng Ren (China University of Petroleum (East China))\n\nShort bio:\n \nDr. Ren received the BEng and MEng degrees both in electronic engineerin g from Harbin Institute of Technology\, China\, and PhD in computer scienc e from the University of York\, UK. He is currently a full professor with the College of Oceanography and Space Informatics\, China University of Pe troleum (East China). He is the director of Shandong Youth Innovative Team of offshore unmanned observation and also the director of Qingdao Interna tional Research Center for Intelligent Forecast and Detection of Oceanic C atastrophes. He received the Taishan Scholarship from Shandong Province\, the K. M. Scott Prize from the University of York\, the Natural Science aw ard (first rank) from China Institute of Electronics\, and the Eduardo Cai aniello Best Student Paper Award from 18th International Conference on Ima ge Analysis and Processing as one co-author. He serves as associate editor s of IEEE TGRS and IEEE J-MASS. His research interests include learning ba sed underwater imaging and remote sensing\, unmanned vehicle observation\, and on-orbit FPGA computation\, etc. Dr. Ren is a senior member of IEEE.\ n\nTime:\n\n9:30 am - 10:30 am\, November 30\, 2023\n\nTalk link\n\nhttps: //mun.webex.com/meet/weimin\n\nSpeaker(s): Peng Ren\, \n\nVirtual: https:/ /events.vtools.ieee.org/m/381782 LOCATION:Virtual: https://events.vtools.ieee.org/m/381782 ORGANIZER:weimin@mun.ca SEQUENCE:2 SUMMARY:IEEE NL OES chapter invited talk 1 URL;VALUE=URI:https://events.vtools.ieee.org/m/381782 X-ALT-DESC:Description: <br /><p>Dear all\,</p>\n<p>We kindly invite you to attend the 1st invited technical talk orgaized by IEEE OES NL Chapter for 2023\, the talk information:</p>\n<p><strong>The title of the talk:</stro ng></p>\n<p>Underwater Image Enhancement Based on Reinforcement Learning</ p>\n<p><strong>Abstract:</strong></p>\n<p>Reinforcement learning is a fami ly of methods for optimizing models in a sequential trial-and-error fashio n. It can achieve optimal results for complicated models which can hardly be addressed by ordinary optimization methods. Underwater optical imaging involves complicated procedures including imaging process\, visualization\ , and applications such as object detection in underwater optical images. How to achieve underwater optimal optical imaging for the purpose of high- quality image enhancement\, good visualization and accurate object detecti on remains challenging problems. To address these challenges\, we develop reinforcement learning strategies for optimizing the three procedures invo lved in underwater optical imaging. Specifically\, we describe how to cond uct optimal configuration of underwater optical imaging process\, how to o btain optimal representation by underwater optical visualization\, and how to achieve optimal performance for underwater optical object detection. O ur preliminary study paves a possible way for exploiting reinforcement lea rning for obtaining underwater optimal optical imaging results.</p>\n<p><s trong>Presenter:</strong></p>\n<p>Dr. Peng Ren (China University of Petrol eum (East China))</p>\n<p><strong>Short bio:&nbsp\;</strong></p>\n<p>Dr. R en received the BEng and MEng degrees both in electronic engineering from Harbin Institute of Technology\, China\, and PhD in computer science from the University of York\, UK. He is currently a full professor with the Col lege of Oceanography and Space Informatics\, China University of Petroleum (East China). He is the director of Shandong Youth Innovative Team of off shore unmanned observation and also the director of Qingdao International Research Center for Intelligent Forecast and Detection of Oceanic Catastro phes. He received the Taishan Scholarship from Shandong Province\, the K. M. Scott Prize from the University of York\, the Natural Science award (fi rst rank) from China Institute of Electronics\, and the Eduardo Caianiello Best Student Paper Award from 18th International Conference on Image Anal ysis and Processing as one co-author. He serves as associate editors of IE EE TGRS and IEEE J-MASS. His research interests include learning based und erwater imaging and remote sensing\, unmanned vehicle observation\, and on -orbit FPGA computation\, etc. Dr. Ren is a senior member of IEEE.</p>\n<p ><strong>Time:</strong></p>\n<p>9:30 am - 10:30 am\, November 30\, 2023</p >\n<p><strong>Talk link</strong></p>\n<p><a href="https://mun.webex.com/me et/weimin">https://mun.webex.com/meet/weimin</a></p> END:VEVENT END:VCALENDAR