Discussion
=============

The PeopleNet system allows us to detect and recognize people in various environments. Through our examples, we were able to see how the system can be applied to a variety of different applications.

.. raw:: html

    <div style="background: #CFFDE1" class="admonition note custom">
        <p style="background: #68B984" class="admonition-title">
            Group Discussion Points
        </p> 
        <ul>
            <li> 
                If you could enhance the PeopleNet system, what additional features or applications would you like to incorporate?
            </li>
            <li>
                How would you train your PeopleNet model for a specific use case? 
                <ul>
                    <li>
                        When creating a machine learning model, we need a model architecture and data to train the said architecture.
                        Depending on the application, we may import a pre-trained PeopleNet model but fine-tune it with our own data for our specific task.
                        For example, for detecting and tracking people in a retail environment, we would need multiple surveillance videos that are labeled by professionals to train our model.
                        This would help the model to better recognize people in a specific context and improve its overall performance.
                    </li>
                </ul>
            </li>
            <li>
                What potential ethical concerns or privacy issues might arise when using PeopleNet in certain scenarios, and how can they be addressed?
            </li>
        </ul>
    </div>