Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/skp-1997/deepdishtracker
The objective is to count the plates using object detection and object tracking.
https://github.com/skp-1997/deepdishtracker
Last synced: 5 days ago
JSON representation
The objective is to count the plates using object detection and object tracking.
- Host: GitHub
- URL: https://github.com/skp-1997/deepdishtracker
- Owner: skp-1997
- License: mit
- Created: 2023-10-11T04:08:23.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-02-01T22:13:30.000Z (10 months ago)
- Last Synced: 2024-02-01T23:51:18.402Z (10 months ago)
- Language: Python
- Size: 19.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Counting the dishes using detection and tracking algorithm
The objective is to count the plates using object detection and object tracking. The repository used the PyimageSearch Simple Object Tracking code frome [here](https://pyimagesearch.com/2018/07/23/simple-object-tracking-with-opencv/). The object detection model used is pre-trained Faster R-CNN model trained on [Detectron2](https://github.com/facebookresearch/detectron2) framework and a custom dataset.
# Output of the code counting the dishes!
# Installation of the environment
We encourage you to use conda environment. Once you create an environment use follwoing command to get the environment ready
```
pip install -r requirements.txt
```
# Training the Faster R-CNN Model
Follow instruction given in PlateCount_FasterRCNN.ipynb file for training the model. You can use the data from the roboflow account provided in the file.
# Inference on Images and Videos
Run the command to test on an Image
```
python test_images2.py
```
Run the command to test on a Video
```
python test_video.py
```
Make sure to provide right path of video, model file and image file in the script.
# Common Debug
1. Make sure the environment is properly installed
2. Provide complete path of the model file
3. Detectron2 installation will take time. Be patient.