top of page
ML main image.png

Machine Learning Model to Predict Crowd Density for Public Event Accessibility

Inclusive Design Response Project (2 weeks)
June 2022

While attending a series of Toronto public events in the summer of 2022, the effect of crowd density on how able and disabled bodies could navigate these spaces, really stood out to me.

Events that were marked accessible, only indicated the provision of accessible features like washrooms, rather than being indicative of the event's overall accessibility.

To address these factors, I trained a machine learning model to identify how crowded a space was (using images), so people could decide if they would have the space to use their assistive mobility devices at public events.

In practice, the concept could work by scanning public social media pictures or live videos of a public event someone wanted to attend and indicate if it was too crowded or not (for their accessibility requirements).

Click on the video on the left to see the model in action, or refer to the keyframes below.

High density output read, in response to an image of a crowd
Medium density output read, in response to an image of a crowd
Low density output read, in response to an image of a crowd
  • Design Opportunity
    Based on market analysis and mapping out a timeline of assault, I found that majority of products only address the time between when a threat becomes apparent and the (potential) attack. Current solutions also had their own reasons that made them less effective/popular. There was an opportunity to create a non-violent product that initiated a system to address multiple stages of the assault timeline, through the local community.
  • Look Book
  • Process Highlights
    Background and Problem Space: -Research -Interviews Understanding Context: -Interviews -Mapping -Documentaries -UN reports Ideation and Concept Generation: -Sketches -Prototypes -Probes -Analogous Objects Product Creation: -Material Investigation -Screen Printing -Flat Pattern -User testing Link to process book here (hyperlinked)
  • Key Takeaways
    1. Concept lives beyond the product: In designing for such a nuanced space, the concept requires as much (if not more) design than the product itself. In this particular case, the concept can be adapted into the local ecosystem (through local tailors, weavers, sewing shops, etc) even if the product is not available. 2. The user is also the designer: Ongoing re-design; users (communities) may create alternative or new meanings to the signalling modes, based on their personal needs and the needs of others in their community. 3. Social sustainability: By designing a product or concept that is capable of changing to meet current and future needs (through the user's ongoing re-design), the product becomes a living system that sustains itself.
bottom of page