Roboflow's inference server to analyze video streams. This project extracts insights from video frames at defined intervals and generates informative visualizations and CSV outputs.

Factories & stores can:

• Save time
• Count items at intervals, avoiding stockouts.
• Restock efficiently using data.
• Enhance operations

This is counting products on shelf, every 5 minutes, categorically and in total.

Make sure you have docker installed. Learn more about building, pulling, and running the Roboflow Inference Docker Image in our documentation.

x86 CPU:

docker run --net=host roboflow/roboflow-inference-server-cpu:latest

NVIDIA GPU

docker run --network=host --gpus=all roboflow/roboflow-inference-server-gpu:latest

git clone https://github.com/roboflow/inference-dashboard-example.git
cd inference-dashboard-example
pip install -r requirements.txt

python main.py --dataset_id [YOUR_DATASET_ID] --api_key [YOUR_API_KEY] --video_path [PATH_TO_VIDEO] --interval_minutes [INTERVAL_IN_MINUTES]

"""
--dataset_id: Your dataset name on Roboflow.
--version_id: The version ID for inference (default: 1).
--api_key: Your API key on Roboflow.
--video_path: Path to the video file for analysis.
--interval_minutes: Interval in minutes to extract predictions (default: 1).
"""

Feel free to open an issue, submit a PR, or share your feedback. All contributions are welcome!