Artificial Intelligence and Machine Learning for a Digital Twin

Jurisdiction: Tasmania

The City of Hobart is developing a Digital Twin that will contain high resolution photogrammetric data and allow integration with diverse datasets owned publicly or privately. We are keen to explore the use of Artificial Intelligence (AI) and Machine Learning within these datasets.

The City of Hobart are keen to explore the use of AI and Machine Learning that involves any kind of innovative response to the representation of a city and its data; including Object Recognition, Image Classification, Semantic Segmentation and Instance Segmentation.

Consider the following:

• Smart analysis and representation of trees or other assets (based on photographic data and known geospatial locations)
• Identifying buildings and creating their 3D envelope
• Incorporating anonymised data from security camera footage (traffic counting, people counting, motion paths, hotspots etc.)
• Any other relevant innovations

Additional Information:

Additional links:

• https://www.hobartcity.com.au/Home
• https://www.hobartcity.com.au/City-services/Geographic-information-data
• https://au.opencitiesplanner.bentley.com/cityofhobart/digitaltwin (see note below)

Other relevant documents:

• Where Deep Learning Meets GIS
• Integrated Deep Learning with ArcGIS using Python
• Connected Hobart: Smart City Action Plan
• Hobart 2010 Public Spaces and Public Life - 01 Final Report - Introduction
• Hobart 2010 Public Spaces and Public Life - 02 Final Report - Analysis
• Hobart 2010 Public Spaces and Public Life - 03 Final Report - Recommendations
• Hobart 2010 Public Spaces and Public Life - 04 Final Report - Public Life Data

Note:

THE DIGITAL TWIN IS PART OF A PROOF OF CONCEPT PROJECT BEING
DEVELOPED BY CITY OF HOBART AND THERE ARE NO GUARANTEES OF
SPATIAL ACCURACIES.

DISCLAIMER:
THIS DATA IS CONFIDENTIAL AND IS NOT TO BE SUPPLIED TO ANY OTHER
PARTIES. THE DATA IS ONLY TO BE USED FOR THE REQUIRED
PROJECT/PURPOSE IN AGREEMENT WITH THE CONTRACT OF ENGAGEMENT,
AND IN ACCORDANCE WITH ANY RELEVANT COH POLICIES.
THE DATA SUPPLIED IN THESE FILES IS NOT TO BE USED FOR DESIGN OR
CONSTRUCTION PURPOSES. THE DATA HAS BEEN ACQUIRED FROM VARIOUS
SOURCES AND THEREFORE IS RECORDED AT VARYING LEVELS OF RELIABILITY
AND THE INFORMATION CONTAINED IN THESE FILES MAY NOT BE COMPLETE.
THE HOBART CITY COUNCIL DOES NOT WARRANT THE ACCURACY OR
COMPLETENESS OF THE INFORMATION CONTAINED IN THESE FILES, AND THE
INFORMATION SHOULD BE VERIFIED BY A FULL SITE SURVEY PRIOR TO ANY
DEVELOPMENT OR CONSTRUCTION WORK BEING UNDERTAKEN. THE HOBART
CITY COUNCIL ACCEPTS NO RESPONSIBILITY FOR ANY CLAIMS FOR LOSS,
DAMAGE OR INJURY SUFFERED BY ANY PERSON OR ORGANISATION
RESULTING FROM THE USE OF THE DATA CONTAINED IN THESE FILES.

Image credit: City of Hobart.

Eligibility: Use one or more datasets from CoH Open data portal and ensure the submission relates to Artificial Intelligence and Machine Learning for a CoH Digital Twin.

Entry: Challenge entry is available to all teams in Australia.

Dataset Highlight

LIST Orthophotography 2019