Metadata-Version: 2.1
Name: cctv-analysis
Version: 0.0.1
Summary: A ready-to-use server to analyse cctv feeds. Pip install, boot up server, and make requests to analyse videos.
Home-page: https://github.com/midusi/cctv_analysis
Author: Juan Tomás Barrón - Gustavo Risso - Facundo Quiroga
Author-email: fquiroga@lidi.info.unlp.edu.ar
License: GNU Affero General Public License v3 or later (AGPLv3+)
Project-URL: Bug Tracker, https://github.com/midusi/cctv_analysis/issues
Project-URL: Documentation, https://github.com/midusi/cctv_analysis
Project-URL: Source Code, https://github.com/midusi/cctv_analysis
Platform: UNKNOWN
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: License :: OSI Approved :: Python Software Foundation License
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Requires-Python: >=3.6.0
Description-Content-Type: text/markdown
Requires-Dist: flask
Requires-Dist: gdown
Requires-Dist: numpy
Requires-Dist: python-opencv
Requires-Dist: tensorflow-gpu
Requires-Dist: keras
Requires-Dist: pillow
Requires-Dist: matplotlib
Requires-Dist: tqdm


# CCTV analysis.

A cctv analysis server to asynchronously analyse videos for objects such as persons or cars in cctv camera feeds.
[![license](https://img.shields.io/github/license/mashape/apistatus.svg)](LICENSE)

## Introduction.

KERAS implementation of YOLOv3 (Tensorflow backend) inspired by [allanzelener/YAD2K](https://github.com/allanzelener/YAD2K).

---

## Initial setup for model.

1. Clone the repository on your computer.
2. Download YOLOV3 weights and the yolo.h5 file from this drive link https://drive.google.com/drive/folders/1PHLAmDVdO3DWp0Igf2_T_uBnDsvJZghy?usp=sharing , or use de wget instruction above
3. Put the weights files in the weights folder "/cctv_analysis/model/weights", and the file yolo.h5 inside the cfg folder "/cctv_analysis/model/cfg".
4. Run the app.


To run the server localy:

At the server folder "cctv_analysis/server/"
python app.py  
server runs at http://127.0.0.1:5000/ localy,
use the "seleccionar archivo" button, then select video, once the video is selected click at the "enviar" button, after procesing the output can be found at the files folder (cctv_analysis/server/files" as a json file called data.

PD: the files folder can be modified from the user_cfg.json file at the server folder




