This project’s aim is to conceptualize and implement an open-source, simple, and extensible framework for continuous image analysis using the TensorFlow Object Detection API.
The setup script should take care of any dependencies automatically; however, it should be noted that these packages will be installed on your system if all goes well:
mysql-server
git
(if not installed already)protobuf-compiler
python-pip
tensorflow
pillow
lxml
jupyter
matplotlib
ipython
mysql-connector=2.1.4
jsonpickle
exifread
The setup script will create the following folder structure used by the database and the ongoing processing scripts:
- /srv/ObjectDB
- /EXIF
- /odapi_output
- /unprocessed
- /processed
All folders are owned by the mysql usergroup, and the current user at setup time will be added to the mysql
group.
- Install Git if necessary:
$ sudo apt install git -y
- Clone the repository:
$ git clone https://github.com/UHMC/object-analysis.git
- Change directory into the project folder:
$ cd object-analysis
- Run the setup script:
$ ./setup_ubuntu1604.sh
- Add demo images to unprocessed folder:
$ cp Resources/demo-images/* /srv/ObjectDB/unprocessed/
- Wait.
- TensorFlow Object Detection API
- "Speed/accuracy trade-offs for modern convolutional object detectors." Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I, Wojna Z, Song Y, Guadarrama S, Murphy K, CVPR 2017
- Mario Canul - Undergraduate Cybersecurity Researcher
- Saxon Knight - Undergraduate Cybersecurity Researcher