wAIste

Title
Home Page
Upload Page
Results Page

Inspiration

At UMD, every waste disposal area has 3 signs indicating to the person what is compost, recyclable, or trash and has respective bins for these sections before the person throws away their item. This helps people decide which bin to throw their items in. However, this feature is not available everywhere, but we felt that we could make it accessible with an app where people can upload pictures of their items and determine their classification accordingly. Furthermore, our inspiration for wAIste came from a shared concern about the environmental impact of waste mismanagement and the potential of artificial intelligence to address this issue. We were inspired by the idea of using AI to optimize recycling processes and promote sustainability.

What it does

wAIste is an innovative project that utilizes AI technology to streamline waste management and recycling efforts. The platform allows users to upload images of various waste items, which are then analyzed by AI algorithms to determine the appropriate recycling category. It provides users with real-time feedback on how to properly dispose of different materials, ultimately promoting more effective recycling practices.

How we built it

We built wAIste using a combination of frontend and backend technologies. The frontend was developed using Flutter, a cross-platform framework for building mobile applications, allowing us to create a user-friendly interface for image uploading and result display. On the backend, we used Flask, a lightweight web framework in Python, to handle image processing and AI inference. We integrated with inference SDKs to leverage pre-trained models for waste detection and classification.

Challenges we ran into

One of the main challenges we faced was integrating multiple AI models seamlessly within the application. We had to ensure smooth communication between the frontend and backend while handling different types of image data and processing results efficiently. Additionally, optimizing the performance of AI inference on mobile devices posed technical challenges that required careful optimization and testing.

Accomplishments that we're proud of

We're proud to have successfully developed a functional prototype of wAIste that demonstrates the potential of AI in waste management. Despite facing various technical challenges, we were able to overcome them through collaboration and perseverance. Our accomplishment lies in creating a solution that has the potential to make a positive impact on environmental sustainability.

What we learned

Throughout the development process, we learned valuable lessons about the complexities of integrating AI into real-world applications. We gained insights into mobile development, backend infrastructure, and AI model deployment. Additionally, we deepened our understanding of waste management practices and the importance of promoting recycling awareness.

What's next for wAIste

In the future, we plan to further enhance wAIste by integrating additional features and expanding its capabilities. This includes improving the accuracy of AI predictions, adding support for different types of waste materials, and incorporating user feedback to enhance the user experience. We also aim to explore partnerships with recycling organizations and municipalities to scale the impact of wAIste and promote sustainable waste management on a larger scale.