deepfusionai / social-distance-detector

Winter of Code (WoC) projects and products related to Deep Fusion AI!

Winter of Code 2020

Winter of Code (WoC) projects and products related to Deep Fusion AI!

Deep Fusion AI is a mentoring organization for Winter of Code 2020. AI can help, but it’s not a silver bullet: tackling societal challenges requires a concerted, collaborative effort across all sectors of society. At Deep Fusion AI, we’re conducting research that advances the state-of-the-art in the field, applying Deep Learning to products and to new domains, and developing tools to ensure that everyone can access AI.

Deep Fusion AI aims to recruit talented WoC students to help us advance the field of Artificial Intelligence with open-source software (and hardware). All code contributed by WoC students will be shared under open-source licenses and any data products derived from Deep Fusion AI data will be shared under Deep Fusion AI's Creative Commons license (CC BY-NC-SA 4.0).

In the IDEA.md file of this repository, we list project ideas from mentors. Deep Fusion AI also encourages you -- as a WoC student -- to propose your own original project ideas (as PRs to IDEA.md).

After you sign up as a WoC student please refer to the Deep Fusion AI Contribution Guide and the Deep Fusion AI Proposal Template as you draft your proposal.

Questions?

Ask WoC-specific questions in the Deep Fusion AI WhatsApp workspace.

More questions about being a WoC mentor or student? Check out the WoC mentor & student guides.

Deep Fusion AI uses the #deepfusionai channel on the Freenode (irc.freenode.net) network. Join the #DeepFusionAI IRC Channel

social-distance-detector's Issues

TensorFlow Lite model for pedestrian detection

Goal

Come up with a TensorFlow Lite model (an optimized FlatBuffer format with the .tflite file extension) that is capable of detecting pedestrians from a scene.

Deliverables

• The TensorFlow Lite model.
• A Colab Notebook showing the model conversion process and how to make predictions with the TensorFlow Lite model on static images.

Distance calculation between two pedestrians from real-time video feeds

Goal

To come up with a Python script that can take a video feed in real-time, detect pedestrians, and spit out their distances from each other.

Deliverables

• A Colab Notebook that demonstrates the distance calculation algorithm
• A Python script that can take a video feed in real-time, detect pedestrians, and spit out their distances from each other.

Considerations

Before starting to work on this issue, please discuss how you do you plan to implement the algorithm via the comments.

Pedestrian detection from real-time video feeds

Goal

Detect pedestrians from real-time video feeds. You can use pre-trained object detectors for this task. This would serve as a reasonable baseline. Later, if needed, you can train an object detector solely to detect pedestrians.

Considerations

• As the detector would be running on real-time video feeds using TensorFlow Lite with Python on a Raspberry Pi 4 Model B, you should focus on the latency aspects of it without compensating for its accuracy. An ideal model would be fast and at the same time won't produce too many false positives. Also, consider if the detector should run on every single frame of a video feed, or could we minimize it?
• As you would try out different models for the purpose please do a thorough study of their latency along with their detection performance on videos. This information will make it easier for us to decide which model we might want to go with.

Deliverables

• A Colab Notebook to demonstrate the idea.
• A Python script (you can modularize code with multiple scripts too) for the end-to-end execution i.e. this script will take real-time video feeds as its input from a Pi Camera, detect pedestrians, and will display the results on the screen.

Tools

You are free to use open-source pre-trained models. If you use someone else's please attribute it. If your code is plagiarized then you will be suspended (applicable only if you are a WoC participant).