BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-asia-2023//speaker//CJCQ
 GN
BEGIN:VTIMEZONE
TZID:KST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:KST
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-asia-2023-WEAGWW@talks.staging.osgeo.org
DTSTART;TZID=KST:20231128T140000
DTEND;TZID=KST:20231128T180000
DESCRIPTION:Moving feature data can represent various phenomena\, including
  vehicles\, people\, animals\, weather patterns\, and more. Conceptually\,
  Moving Features are dynamic geospatial data that change location and poss
 ibly other characteristics over time. \n\nOGC API – Moving Features (OGC
  API – MF) provides a standard and interoperable way to manage such data
 \, with valuable applications in transportation management\, disaster resp
 onse\, environmental monitoring\, and beyond. OGC API – MF also includes
  operations for filtering\, sorting\, and aggregating moving feature data 
 based on location\, time\, and other properties. \n\nThis workshop will ge
 t you started with OGC API – MF and its implementation in MF-API Server 
 that is based on pygeoapi and MobilityDB\, covering the following question
 s:\n- What is the core concept of OGC API – MF (and OGC MF-JSON format)?
 \n- How to implement OGC API – MF with pygeoapi and MobilityDB?\n- How c
 an we visualize its results with STINUUM (with CesiumJS)?\n- How can we im
 plement a new feature that hasn't been implemented yet?\n\nThe below open 
 sources will be used in this workshop:\n- MF-API Server based on pygeoapi:
  https://github.com/aistairc/mf-api \n- OGC API – Moving Features offici
 al GitHub repository: https://github.com/opengeospatial/ogcapi-movingfeatu
 res\n- MobilityDB (and its Python driver\, PyMEOS\, and MEOS): https://git
 hub.com/MobilityDB \n- STINUUM: https://github.com/aistairc/mf-cesium \nTh
 e installation of each program will use a Docker file.\n\nLastly\, you can
  check many helpful information about OGC API – MF here: https://ogcapi.
 ogc.org/movingfeatures/
DTSTAMP:20261015T134431Z
LOCATION:Taepyeong Hall
SUMMARY:OGC API – Moving Features\, an introduction with MF-API Server ba
 sed on pygeoapi and MobilityDB - Wijae Cho\, Taehoon Kim\, Hirofumi Hayash
 i\, Tsubasa Shimizu\, Tran Thuan Bang\, Kyoungsook Kim
URL:https://talks.staging.osgeo.org/foss4g-asia-2023/talk/WEAGWW/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-foss4g-asia-2023-GF8WUG@talks.staging.osgeo.org
DTSTART;TZID=KST:20231130T112000
DTEND;TZID=KST:20231130T114000
DESCRIPTION:The point cloud is becoming a valuable resource for building Di
 gital Twins\, the virtual representation of a real-world physical feature\
 , with the LiDAR developments. The semantic information of each point (suc
 h as walls\, floors\, doors\, windows\, etc.) is essential to handle and a
 nalyzing point clouds. However\, the raw point cloud captured from the LiD
 AR sensor doesn’t have semantics\, and the annotation task for adding se
 mantics is time-consuming and needs expert experience with commercial soft
 ware. Therefore\, we set up two goals for accelerating the 3D point clouds
  annotation task:\n- Machine-based assistants\, such as AI techniques\, an
 d\n- Task-based collaboration.\n\nRecently\, deep learning has been used t
 o derive semantic classes by automated classification and segmentation. Th
 erefore\, it can be used to address the manual task (bottleneck) in the tr
 aditional annotation process. Also\, the data format for deploying is esse
 ntial for collaboration. It should be easy to understand and efficient to 
 share.\n\nPCAS (Point Cloud Annotation System) is a 3D point cloud annotat
 ion system that enhances the quality and speed of annotation tasks with de
 ep learning techniques. This system can be summarized as four key points:\
 n- This system mainly develops based on Potree[1]\, an open-source library
  for point cloud visualization. It also utilizes various open sources\, su
 ch as open3d[2] and torch-points3d[3]\, for handling point clouds with dee
 p learning modules.\n- This system supports three tools to accelerate anno
 tation work: semi-automatic labeling with a deep learning module\, 3D shap
 e object-based labeling\, and normal vector-based cluster labeling.\n- The
  annotation task can be easily shared and tracked\, similar to GitHub.\n- 
 The annotation task results are stored as an HDF5 file based on a predefin
 ed profile[4] for the labeled point clouds\, easily sharing and managing s
 emantic information.\nThis talk will introduce the four main points above\
 , including the structure of PCAS with other open sources\, the design pur
 pose\, and problems and solutions encountered during development.\n\nRefer
 ences:  \n[1] Potree\, WebGL point cloud viewer for large datasets\, https
 ://github.com/potree/potree  \n[2] torch-points3d\, Pytorch framework for 
 doing deep learning on point clouds\, https://github.com/torch-points3d/to
 rch-points3d  \n[3] Open3D\, A Modern Library for 3D Data Processing\, htt
 ps://github.com/isl-org/Open3D  \n[4] The HDF5 profile for labeled point c
 loud data\, https://docs.ogc.org/dp/21-077.html
DTSTAMP:20261015T134431Z
LOCATION:Workshop Room
SUMMARY:Accelerating the 3D Point Clouds Annotation Task with Deep Learning
  and Collaboration - Wijae Cho\, Taehoon Kim\, Kyoungsook Kim
URL:https://talks.staging.osgeo.org/foss4g-asia-2023/talk/GF8WUG/
END:VEVENT
END:VCALENDAR