Terra Object Detection (v. 0.9.0 Beta)
An application based on ImageAI library which can run object detection tasks from device cameras and IP cameras in real time.
- Detects and saves detections as separate images as well as immediately notifies user about detection
- Availability to choose detection speed and accuracy
- Up to 8 cameras can be saved and work simultaneously in the current version
Object Detection
An application uses YOLOv3 and TinyYOLOv3 models for object detection.
Requirements for Developers
- Python 3.7.4
- ImageAI 2.1.5
- Tensorflow 1.11
- OpenCV 4.1.0.25
- Keras 2.2.4
- yolo.h5 and yolo-tiny.h5 models
Installation
- Install ImageAI 2.1.5 and all necessary dependencies
- ImageAI:
pip3 install imageai --upgrade
- Tensorflow:
pip3 install tensorflow==1.11.0
- OpenCV:
pip3 install opencv-python
- Keras:
pip3 install keras
- Download yolo.h5 and yolo-tiny.h5 and locate them together with other files in venv\ directory
- Locate __ init __.py in venv\Lib\site-packages\imageai\Detection (change the existing file)
Run _appearance.py to launch the application.
License
This project is licensed under the MIT License.

Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.


