SafeStreets

logo

Inspiration

SafeStreets is essential due to the rising violent crime rates in New York City, especially in the Bronx. In 2023 alone, there were over 1,500 reported violent crimes in the Bronx, including assaults, robberies, and shootings.

What it does

SafeStreets is a mobile application focused on New York and the Bronx areas. It features a dynamic map displaying a heatmap of historical crime data and real-time markers for user-reported incidents. Users can report violent acts, and the app notifies them when they are near a reported incident, allowing them to take immediate precautions. Other features include a relevant news section and automatic image caption generation for faster reports.

How we built it

We used React Native for the front end, Python and Flask for the backend, Firestore and Firebase Storage for data storage, and Python with Selenium for web scraping. We've fine-tuned the CLIPxGPT Captioner model to provide accurate image descriptions over 120 epochs on the Flickr30k dataset, consisting of 30,000 images.

Challenges we ran into

Integrating the backend and training the model was difficult. We almost gave up and tried using Chat GPT 4.

Accomplishments that we're proud of

We are proud to learn how to incorporate a flask backend with an Android emulator utilizing React Native. Making sure that users were updated, affected, and notified of other concurrent user actions was difficult. Implementing the trainer model was difficult. Throughout the project, we learned how to do this and got better at it.

What's next for SafeStreets

Outside of improving the accuracy of the image captioning model, we hope to incorporate not only a visual aspect but an auditory form of report as well to make users be able to report incidents faster and more efficiently.