BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Pacific/Auckland BEGIN:DAYLIGHT DTSTART:20220925T030000 TZOFFSETFROM:+1200 TZOFFSETTO:+1300 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=9 TZNAME:NZDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20220403T020000 TZOFFSETFROM:+1300 TZOFFSETTO:+1200 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4 TZNAME:NZST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220602T025448Z UID:C361D62C-1322-40ED-BC65-F06E3FD99CC6 DTSTART;TZID=Pacific/Auckland:20220602T120000 DTEND;TZID=Pacific/Auckland:20220602T130000 DESCRIPTION:Ultrasonic Arrays for Pasture Biomass Estimation and Grape Occl usion Detection\n\nDr Mathew Legg / Baden Parr\n\nThe ability to accuratel y measure pasture biomass can have a significant effect on the profit farm ers can achieve from their pastures. One method previously used to estimat e pasture biomass has been to measure pasture height using ultrasound. A t ransducer is fixed to a farm bike and the distance to the top of the grass is measured. This method assumes that the ground is a set distance below the transducer. However\, errors occur when the bike tilts and bounces and when pasture density varies. This talk will describe the development of a novel air-coupled ultrasonic array system for pasture biomass estimation developed by Mathew and Stuart Bradley. Improved biomass estimation is ach ieved by imaging through the grass to estimate both pasture density and gr ound location. It is the first pasture biomass estimation system to have r eported these capabilities using proximal (remote) sensing techniques. Thi s talk will also describe a study performed by Baden and Mathew using a hi gh-resolution ultrasonic array to image through leaves to detect occluded grapes. This is the first-time ultrasound has been used to image fruit occ luded by leaves. This has the potential for helping to improve automated g rape yield estimation.\n\nDetecting and Counting Sheep in UAV Videos\n\nFa rah Sarwar\n\nThe focus of this research work is to detect\, count and mon itor livestock in a paddock using an unmanned aerial vehicle (UAV). It inv olves no disruption to the farm animals as the UAV will barely be noticeab le from the chosen flight altitude. Recorded images and videos are process ed using a combination of deep learning and machine learning algorithms to perform the aforementioned tasks. The data set was designed after collect ing data from different paddocks to cover a variety of background\, weathe r and paddock conditions. The achievement of 98% recall for object detecti on and high accuracy for multiple object tracking suggests that this resea rch will be beneficial for farmers in terms of saving time and reducing co sts.\n\nSpeaker(s): Dr Mathew Legg\, Dr Farah Sarwar\n\nAgenda: \n12:00 Dr Mathew Legg/Baden Parr: Pasture Biomass Estimation and Detection of Occlu ded Grapes using Ultrasonic Arrays\n\n12:30 Farah Sarwar: Detecting and Co unting Sheep in UAV Videos\n\nRoom: Room ALR6/421W-501\, Level 5\, Bldg: A rchitecture and Planning Building (421)\, University of Auckland\, City Ca mpus\, \, Symonds Street\, Auckland\, Auckland\, North Island\, New Zealan d\, 1010\, Virtual: https://events.vtools.ieee.org/m/315457 LOCATION:Room: Room ALR6/421W-501\, Level 5\, Bldg: Architecture and Planni ng Building (421)\, University of Auckland\, City Campus\, \, Symonds Stre et\, Auckland\, Auckland\, North Island\, New Zealand\, 1010\, Virtual: ht tps://events.vtools.ieee.org/m/315457 ORGANIZER:m.legg@massey.ac.nz SEQUENCE:13 SUMMARY:Ultrasonic Arrays for Pasture Biomass Estimation and Grape Occlusio n Detection / Detecting and Counting Sheep in UAV Videos URL;VALUE=URI:https://events.vtools.ieee.org/m/315457 X-ALT-DESC:Description: <br /><p><strong>Ultrasonic Arrays for Pasture Biom ass Estimation and Grape Occlusion &nbsp\;Detection</strong></p>\n<p><span style="text-decoration: underline\;">Dr Mathew Legg / Baden Parr</span></ p>\n<p>The ability to accurately measure pasture biomass can have a signif icant effect on the profit farmers can achieve from their pastures. One me thod previously used to estimate pasture biomass has been to measure pastu re height using ultrasound. A transducer is fixed to a farm bike and the d istance to the top of the grass is measured. This method assumes that the ground is a set distance below the transducer. However\, errors occur when the bike tilts and bounces and when pasture density varies. This talk wil l describe the development of a novel air-coupled ultrasonic array system for pasture biomass estimation developed by Mathew and Stuart Bradley. Imp roved biomass estimation is achieved by imaging through the grass to estim ate both pasture density and ground location. It is the first pasture biom ass estimation system to have reported these capabilities using proximal ( remote) sensing techniques. This talk will also describe a study performed by Baden and Mathew using a high-resolution ultrasonic array to image thr ough leaves to detect occluded grapes. This is the first-time ultrasound h as been used to image fruit occluded by leaves. This has the potential for helping to improve automated grape yield estimation.</p>\n<p><strong>Dete cting and Counting Sheep in UAV Videos</strong></p>\n<p><span style="text- decoration: underline\;">Farah Sarwar</span></p>\n<p>The focus of this res earch work is to detect\, count and monitor livestock in a paddock using a n unmanned aerial vehicle (UAV). It involves no disruption to the farm ani mals as the UAV will barely be noticeable from the chosen flight altitude. Recorded images and videos are processed using a combination of deep lear ning and machine learning algorithms to perform the aforementioned tasks. The data set was designed after collecting data from different paddocks to cover a variety of background\, weather and paddock conditions. The achie vement of 98% recall for object detection and high accuracy for multiple o bject tracking suggests that this research will be beneficial for farmers in terms of saving time and reducing costs.&nbsp\;</p><br /><br />Agenda: <br /><p>12:00 <span style="text-decoration: underline\;">Dr Mathew Legg/B aden Parr</span>: Pasture Biomass Estimation and Detection of Occluded Gra pes using Ultrasonic Arrays</p>\n<p>12:30 <u>Farah Sarwar:</u> Detecting a nd Counting Sheep in UAV Videos</p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR