Inspiration

The inspiration for PhillyGO came from the need for safer navigation in Philadelphia. With increasing concerns about crime and personal safety while navigating the streets of Philadelphia, we aimed to supply users with different routes to help them make informed decisions about their travel routes. Our goal was to create a tool that not only provides directions but also prioritizes safety, ensuring peace of mind for residents and visitors alike.

What it does

PhillyGO is an app designed to generate safe travel routes throughout Philadelphia. Utilizing data on crime and car accidents, the app provides users with multiple route options that prioritize safety. Users can input their starting point and destination, and PhillyGO will suggest a balanced safer and quick path.

How we built it

First, we used OSMnx to turn the map of Philadelphia, PA into graphs with bike lanes, walking paths, and car routes. We then used pandas to turn a csv file of all crime incidents from 2006-Present into a list of tuples containing the x and y coordinates of where the crime happened and created a heat map of crimes with these coordinates. We then used these to create an algorithm that uses a weighing system that takes into account crimes and distance in to travel to the next area.

Challenges we ran into

Throughout the development of PhillyGO, we faced the challenge of using new libraries such as OSMnx and folium. However, the biggest challenge for us was implementing the weights of different crimes into our path finding algorithm.

Accomplishments that we're proud of

We are proud of successfully developing a pathfinding system that not only accounts for speed but also prioritizes safety using real-world crime data. Our ability to convert crime statistics into a practical, usable map for the public is a significant accomplishment for us. Additionally we are also proud of our team’s ability to learn and implement complex libraries like OSMnx and folium within a short timeframe.

What we learned

We learned how to use geographic data libraries like OSMnx and visualize data effectively with folium. We also gained a deeper understanding of how different types of crime affect public perception of safety and the technical complexities involved in assigning appropriate weights to these factors in our algorithm.

What's next for PhillyGO

We aim to further develop PhillyGO and transform it into a mobile app. Additionally, we plan to integrate real-time crime tracking into the routing algorithm, ensuring users can avoid active crime zones.

Built With

Share this project:

Updates