BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:An App for Tree Trunk Diameter Estimation from Coarse Optical Dept
 h Maps - Frank Feng\, Independent Researcher
DTSTART:20240607T120000Z
DTEND:20240607T130000Z
UID:TALK212386@talks.cam.ac.uk
CONTACT:114742
DESCRIPTION:\nZoom link:\nhttps://cam-ac-uk.zoom.us/j/88158575361\nMeeting
  ID: 881 5857 5361\nPasscode: 277705\n\nAbstract:\n\nTrunk diameter is rel
 ated to the overall health and level of carbon sequestration in a tree. Tr
 unk diameter measurement\, therefore\, is a key task in both forest plot a
 nd urban settings. Unlike the traditional approach of manual measurement w
 ith a measuring tape or calipers\, several recent approaches rely on sophi
 sticated technologies such as LiDAR and time-of-flight cameras that provid
 e fine-grain depth maps. These technologies are supported only on speciali
 zed devices or high-end smartphones. We present a mobile application calle
 d GreenLens that only uses coarse-grain depth maps derived from an optical
  sensor\, and so can be run on most common Android devices. Moreover\, we 
 use a state-of-the-art deep neural network to estimate trunk diameter from
  an image and its corresponding coarse depth map (RGB-D). We tested our ap
 p under challenging conditions including occlusion\, leaning trees\, and i
 rregular shapes and found that our algorithm is comparable to accuracy fro
 m fine-grain depth maps.\n\nCurrently\, we are developing GreenLens2. Unli
 ke our previous work\, we are using a game engine (Unreal Engine) to creat
 e a highly photo-realistic virtual forest\, making it easy to collect unli
 mited and diverse data for training neural networks. At the same time\, we
  have proposed a multi-task neural network that performs trunk segmentatio
 n and end-to-end trunk diameter prediction simultaneously. We have also re
 fined the app's user journey to make it more interactive\, straightforward
 \, and user-friendly.\n\nBio:\n\nFrank Feng is currently an undergraduate 
 researcher and will join the Department of Computer Science and Technology
  at the University of Cambridge as a PhD student in October 2024.
LOCATION:GN06\, William Gates Building and on Zoom: https://cam-ac-uk.zoom
 .us/j/88158575361
END:VEVENT
END:VCALENDAR