shirley-kt / facade-proposal

Facade Proposal For Urban Area Version 1.0.0

A modified facade recognization system including AR application to adding advertisement overlay.

Getting Started

Pre-requirements

1. Facade Recognition: Python 3.5, Tensorflow, Opencv, MaskRCNN, matplotlib, yaml, PIL, skimage, datetime.
2. Tool: jupyter.
3. AR: Unity.

Installing

1. Clone Repository

git clone https://github.com/raphealshirley/Facade-Proposal.git

2. Run server:
   Under FacadeProposalfARApplication/server.
   Noted that different platforms should be under same loacal area network and do not forget to change IP address in the file.
   

python3 ./TcpServer.py

3. Run ML model under Facade Proposal folder.

python3 ./facade.py

Result

Modified MaskRCNN improved facade recognition recall by 11.8% compared with SegNet using Tensorflow.

Built With

Python 3.5

Tensorflow

Opencv

MaskRCNN

matplotlib

yaml

PIL

skimage

Unity

Versioning

Version 1.0.0

Model training and testing on SageMaker; AR application;

Version 2.0.0

Design Web UI; Deployed on AWS.

License

This system is licensed under MIT license.

facade-proposal's Issues

Package Versions

Hello,

I would like to try out your build. Unfortuantely, I can't seem to get it to work, which is as far as I have research related to version problems between keras, tensorflow and mrcnn.

Could you specifiy your package versions or copy the results of "pip list/conda list" for me? This would help me a lot.

Thanks in advance!