This project tries to detect a car whenever it crosses a Red Light or overspeeds. It uses tensorflow with an ssd object detection model to detect cars and from the detections in each frame each vehicle can be tracked across a video and can be checked if it crossed a redlight and speed of that vehicle can be calculated.
The project is made by using tensorflow so you must be familiar with tensorflow and basic object detection and you must also know basic maths for understanding the tracking algorithm. You must be also familiar with linux OS as I have made this on Ubuntu and didn't test on other platforms.
Python packages to be installed
* Tensorflow (Tensorflow-gpu if you have Nvidia GPU)
* openCV
* imutils
* Pillow
* numpy
* tkinter
* urllib
* openALPR api
Make account on openalpr and get api secret key from OpenALPR
Clone the repo and paste your secret key in VehicleMoniter.py file on line 58.
run the project by the command python3 VehicleMoniter.py
Do not run the file in the object detection folder cloned from tensorflow as I have made some changes to the files.
If you find any problem you can contact me or raise an issue.
- Tensorflow - ML library
- OpenALPR - For detecting license plate and extracting license plate number
This project is licensed under the MIT License - see the LICENSE.md file for details
I specialize in web development (Full stack - MERN, MEAN, Vue...etc), Websites (Webflow, wordpress), Mobile application (Android/iOS Flutter), Desktop Application(Electron).
If your interested in my services contact me [email protected].
I have a Development firm, check it out here Prowlers.