BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250919T203610Z UID:AD6D382E-097B-42F9-B67E-EF7D205B1756 DTSTART;TZID=America/New_York:20250918T125000 DTEND;TZID=America/New_York:20250918T134000 DESCRIPTION:Abstract: To sustainably intensify agricultural production and food supply while preserving the environment\, we must radically improve t he efficiency and resilience of our agri-food systems through automation a nd AI-driven digital agriculture. In this talk\, I will go over multiple r esearch projects that leverage agricultural robotics and deep learning to address challenges spanning the food chain from breeding to harvest and po stharvest handling. I will present a novel modular agricultural robotic sy stem (MARS) that is an autonomous\, multi-purpose\, and affordable robotic platform for in-field automated phenotyping and precision farming. The ro botic system is empowered by machine learning-based vision intelligence\, including object detection and semantic/instance segmentation for detectin g plants and plant parts in 2D images\, video frame-based multi-object tra cking for plant organ counting\, and 3D deep learning models for point clo ud segmentation and architectural trait extraction. Another project will h ighlight a patented sensor to emulate berry fruit and quantify mechanical impacts during the mechanical harvesting and postharvest handling processe s\, as well as a deep learning-based hyperspectral imaging approach for be rry internal bruise detection and quantification.\n\nCo-sponsored by: UF M AE Department\n\nSpeaker(s): Dr. Changying "Charlie" Li\, \n\nRoom: 303\, Bldg: MAE-A\, 939 Sweetwater Dr\, University of Florida\, GAINESVILLE\, Fl orida\, United States\, 32611 LOCATION:Room: 303\, Bldg: MAE-A\, 939 Sweetwater Dr\, University of Florid a\, GAINESVILLE\, Florida\, United States\, 32611 ORGANIZER:schuejk@ufl.edu SEQUENCE:36 SUMMARY:Automation and Deep Learning to Advance Digital Agriculture URL;VALUE=URI:https://events.vtools.ieee.org/m/498703 X-ALT-DESC:Description: <br /><p class="MsoNormal"><strong style="mso-bidi- font-weight: normal\;"><span style="font-family: 'Times New Roman'\,serif\ ;">Abstract: </span></strong><span style="font-family: 'Times New Roman'\, serif\;">To sustainably intensify agricultural production and food supply while preserving the environment\, we must radically improve the efficienc y and resilience of our agri-food systems through automation and AI-driven digital agriculture. In this talk\, I will go over multiple research proj ects that leverage agricultural robotics and deep learning to address chal lenges spanning the food chain from breeding to harvest and postharvest ha ndling. <span style="color: black\;">I will present</span> <span style="co lor: black\;">a novel modular agricultural robotic system (MARS) that is a n autonomous\, multi-purpose\, and affordable robotic platform for in-fiel d automated phenotyping and precision farming</span>. The robotic system i s empowered by machine learning-based vision intelligence\, including obje ct detection and semantic/instance segmentation for detecting plants and p lant parts in 2D images\, video frame-based multi-object tracking for plan t organ counting\, and 3D deep learning models for point cloud segmentatio n and architectural trait extraction. Another project will highlight a pat ented sensor to emulate berry fruit and quantify mechanical impacts during the mechanical harvesting and postharvest handling processes\, as well as a deep learning-based hyperspectral imaging approach for berry internal b ruise detection and quantification. </span></p> END:VEVENT END:VCALENDAR