Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nicholaskajoh/ivy
Video-based object counting software.
https://github.com/nicholaskajoh/ivy
computer-vision object-counter object-counting video-analysis video-processing
Last synced: about 2 months ago
JSON representation
Video-based object counting software.
- Host: GitHub
- URL: https://github.com/nicholaskajoh/ivy
- Owner: nicholaskajoh
- License: mit
- Archived: true
- Created: 2018-10-08T17:03:46.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2022-10-02T17:29:42.000Z (almost 2 years ago)
- Last Synced: 2024-07-27T17:58:18.741Z (about 2 months ago)
- Topics: computer-vision, object-counter, object-counting, video-analysis, video-processing
- Language: Python
- Homepage:
- Size: 47.6 MB
- Stars: 425
- Watchers: 17
- Forks: 170
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Ivy
Ivy is an open-source video-based object counting software for tallying pretty much anything (vehicles, people, animals — you name it).
> Need help setting up Ivy and analyzing the logs? Visit https://trafficlogic.co or send an email to [email protected].
## Requirements
- Python 3 (tested with version 3.7)
## Setup
- Clone this repo `[email protected]:nicholaskajoh/ivy.git`.
- Create and/or use a virtual environment (optional but recommended) `mkvirtualenv -p python3.7 ivy`.
- Install the dependencies in _requirements.txt_ `pip install -r requirements.txt`.
- Choose a detector and install its dependencies where necessary (if you're not sure what to pick, we recommend you start with `yolo`).
| Detector | Description | Dependencies |
|---|---|---|
| `yolo` | Perform detection using models created with the YOLO (You Only Look Once) neural net. https://pjreddie.com/darknet/yolo/ | |
| `tfoda` | Perform detection using models created with the Tensorflow Object Detection API. https://github.com/tensorflow/models/tree/master/research/object_detection | CPU: `pip install tensorflow-cpu`
GPU: `pip install tensorflow-gpu` |
| `detectron2` | Perform detection using models created with FAIR's Detectron2 framework. https://github.com/facebookresearch/detectron2 | `python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'` (https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md) |
| `haarcascade` | Perform detection using Haar feature-based cascade classifiers. https://docs.opencv.org/3.4/db/d28/tutorial_cascade_classifier.html | |
## Run
- Create a _.env_ file (based on _.env.example_) in the project's root directory and edit as appropriate.
- Run `python -m main`.
- Run using Docker `docker build -t nicholaskajoh/ivy .`.
## Demo
Download [ivy_demo_data.zip](https://drive.google.com/open?id=1JtEhWlfk1CiUEFsrTQHQa0VkTi3IKbze) and unzip its contents in the [data directory](/data). It contains detection models and a sample video.
## Test
```
python -m pytest
```
## Debug
By default, Ivy runs in "debug mode" which provides you a window to monitor the object counting process. You can:
- press the `p` key to pause/play the counting process
- press the `s` key to capture a screenshot
- press the `q` key to quit the program
- click any point on the window to log the coordinates of the pixel in that position
## Community
Got questions, contributions, suggestions, concerns? [Let us know](https://github.com/nicholaskajoh/ivy/discussions)! Also follow us on Twitter [@CountWithIvy](https://twitter.com/CountWithIvy) to get notified about new features, fixes and initiatives.