Posted on

Team Status Report – 4/26/2025

General Accomplishments

This week, we focused on completing the housing and final polish of the system:

  • Designed and 3D printed the housing for the pocket module. Although the initial version was too large, a downsized version has been completed and prepared for printing with Professor Li’s help.
  • Improved reliability and stability of the backend system, addressing minor issues such as occasional failures in image uploads and location triggers. These fixes ensure the system performs more consistently in real-world conditions.

Current Project Status

The project remains on schedule. The full system, both hardware and software, has been successfully integrated and validated. With the hardware now finalized, the focus has shifted to final documentation prep (poster, demo, and video). The migration to React has streamlined frontend development and accelerated progress on user interface features.

Design Changes

There were no major design changes this week. The overall system architecture and hardware integration remained stable. Minor iterations were made in physical form factor (downsizing the housing), but this was part of ongoing design finalization.

Next Steps

  • Final printing of the pocket module housing
  • Poster, video, and demo preparation for final project submission
  • Polish and documentation of all source code and experimental data
  • Dry runs for the demo to ensure good execution

Testing Summary: 

Reproducing from our final presentation…

Our unit tests and overall system test were categorized into verification (quantitative performance metrics) and validation (real-world functionality and user feedback):

Verification Testing

Validation Testing

 

Posted on

Team Status Report – 4/19/2025

General Accomplishments
This week we completing the end-to-end pipeline for the system. We’ve reached a major milestone with both the hardware and software components fully integrated and operational.

On the hardware front, William successfully implemented reliable location data upload from the Blues Notecard to the cloud and integrated the manual trigger button with the image capture system. The engineering portion of the hardware system is now officially completed, with the device able to trigger image capture based on either location change or manual button press.

For the software components, Rohit completed a strategic pivot from Django to React for our frontend, addressing performance issues with real-time updates when new images are captured. This migration has improved the user experience by eliminating disruptive page reloads, instead allowing for seamless updates through WebSockets. Dhruv successfully integrated the Google Maps API, enabling the web application to display actual location names derived from GPS coordinates and providing a map view of the user’s journey.

The integration pipeline is now complete, with images automatically routing from the camera to our frontend, which displays summaries and pictures in a calendar view. User settings can be configured through the web app, and the entire system has undergone initial testing to ensure all components work together reliably.

Current Project Status
The project is on schedule after addressing previous integration challenges. With the engineering portion of the system completed, our focus has shifted to final refinements, housing design, and preparation for the demo. The migration to React has actually accelerated our development timeline, with the component-based architecture facilitating faster iteration on specific features.

Design Changes
The most significant design change this week was the migration from Django to React for the frontend. This change was necessitated by performance issues encountered with Django’s server-rendered approach, particularly for real-time updates when new images are captured. The React implementation provides a more responsive user experience with WebSockets enabling seamless updates without full page refreshes.

Another important technical discovery was William’s resolution of integration issues between the Blues Notecard and Arducam by segregating them to different I2C buses (I2C0 and I2C1), which prevented interference and allowed both devices to operate smoothly together.

Next Steps

For the coming week, our focus will shift to housing and physical design, final testing and validation, and demo prep.

Posted on

William’s Status Report 4/19/2025

Accomplishments This Week

  • Successfully implemented reliable location upload from Notecard to cloud
  • Successfully soldered and integrated manual button trigger of image into the hardware system
  • Integrated code where button manual trigger or location change will trigger an image capture and location upload
  • Engineering portion of the hardware system is now officially completed. I will be shifting to the housing/design portion of the project

Reflection on Schedule

  • On schedule. This upcoming week, I will be fully focusing on housing and design now that the engineering portion of the project is officially completed.

Plans For Next Week

  • Housing for the “pocket” module, will require more 3D printing and measuring
  • Trying to order longer jumper wires to connect pocket module onto chest

New Technologies Learned

  • I learned that I2C protocol cannot have more than one device or it would cause interference. One of the bugs on the hardware end was that blues notecard and the arducam were both using I2C0 which led to integration issues. However, once I segregated to I2C1 and I2C0 for each respective devices, both devices can run together smoothly.
  • I learned how debouncing of button works and how I needed slight delay after a button trigger was detected.
  • I learned how to solder two wires together via youtube video. The wires on the button unfortunately did not have connectors on them and were also not soldered. It was interesting to see for the first time what was inside a wire and physically soldering it together.
Posted on

Team Status Report – 4/12/2025

Accomplishments this week:
This week, Rohit built and finished the frontend. Rohit and Will also worked on 3D printed the casing for all our parts. This involved learning how to do CAD as well as 3D printing. Rohit also made a function to be able to add metadata to images. Will also worked on the manual button and was able to solder it. We are now working on the manual button integration. In addition, Will worked on the location feature and realized that our new GPS module was not good enough. He is now reverting back to using the Blue’s Notecard for location. Dhruv worked on integrating the entire pipeline together. He was able to connect the backend camera capture mechanism to the frontend code. There is now a working pipeline from camera capture to displaying the summary on the frontend. As a group we are slightly behind schedule but we made significant progress recently and are almost ready to test. Our plans for next week are to finish the pipeline and start testing.

To validate our pipeline. We will initiate a camera capture, and verify throughout the pipeline. We will verify the location data, metadata, as well as functionality on the webpage. We will then check that summaries are actually reflective of a user’s day. We will test by each using the product for a day and seeing how useful it really is. Then, we will adjust prompt and models as needed.

Posted on

Team Status Report – 3/29/25

General Accomplishments From Team

This week on the hardware side we implemented MQTT-based communication between Raspberry Pi Pico and server. Along with this, we also automated image capture system working with Arducam. Additionally, the Blues Notecard can now send location data via HTTP, but with accuracy issues.

On the software side, we completed the user auth system with login/registration. We also were able to integrate Google Maps API to convert coordinates to place names which greatly enhanced the diary view entries. We are in progress of connecting this with the image pipeline from capture to diary entry generation.

Most Significant Risks That Could Jeopardize Success of the Project

Location Accuracy: Blues Notecard providing unreliable location data and shutting down after two communications. Solution: Ordering replacement GPS module with UART interface.

Integration Challenges: Minimizing with standardized MQTT communication protocol between components.

Testing: Four weeks until final demo so we are prioritizing integration testing early.

Changes made to the existing design of the system

We are planning to replace the Blues Notecard with dedicated GPS module for better accuracy.

We are also switching from serial communication to MQTT broker architecture for improved reliability in location change to capture pipeline.

Posted on

Team Status Report 3/22/2025

General Accomplishments From Team

The general accomplishment from the team this week includes both the software and hardware end.

Dhruv successfully sent the communication from laptop into PICO through serial connection. He will transition this signal through MQTT which should be smooth since the Pico is successfully connected to the internet on the microcontroller end.

On the microcontroller development, Dhruv and I (Will) were able to successfully capture the image.

I will be spending more time on optimizing the image and we will be focusing on the Blues Notecard this week.

Rohit will be continuing to work on the web development side of things.

Most Significant Risks That Could Jeopardize Success of the Project

The most significant risks that remains include the Blues Notecard connectivity. We will be continuing in focusing on the Blues Notecard development his week.

The integration between hardware and software seems resolved as Dhruv was able to send signal from software to hardware this week.

Changes made to the existing design of the system

Since we did not get approved for reimbursement on AWS, we will be shifting towards completing this project locally as a proof of concept.

Our hardware will still be a wireless connection to the laptop, however, it needs to be under the same wifi network/mobile hotspot we will be using.

We do not see foresee any changes in the schedule of completing this project by shifting this project locally as we can develop our LLMs locally.

Anyhow, good progress is made this week and we still remain confident in a successful completion of the project.

 

 

 

 

Posted on

Team Status Report for 3/15/2025

Will successfully resolved the Wi-Fi connection reliability issues with the Raspberry Pi Pico W, which was one of our major technical obstacles from last week. This achievement establishes a stable foundation for our hardware communication. While the Blues Notecard still has some connection challenges, progress is being made and a resolution is expected soon.

Dhruv made progress on the software backend, completing the location change detection program and implementing a simulation environment to demonstrate the system’s functionality. His work includes a map interface with user movement simulation that triggers image capture when the simulated user becomes stationary. He’s also integrated a vision model for image analysis and connected it to the OpenAI API for summary generation.

Rohit completed the implementation of the calendar view interface in Django and the API endpoints needed for handling image and location data from the hardware components. He’s also developed a working prototype of the daily summary generator using the OpenAI API, which aligns with Dhruv’s simulation work.

The most significant risks currently facing the project are:

  1. Blues Notecard Connectivity: While the Raspberry Pi Pico W connection has been stabilized, the Blues Notecard is still experiencing some connectivity issues with our hotspot. This risk is being managed by Will’s troubleshooting.
  2. Integration Between Hardware and Software Components: As we move towards integrating the hardware (Raspberry Pi Pico W, Blues Notecard, Arducam) with the software (location detection, image processing, web interface), there’s a risk of compatibility issues. We’re mitigating this by establishing clear API contracts between components and developing modular code that can be adapted if requirements change. Dhruv’s simulation environment also helps us test the software side independently of hardware completion.There have been no significant changes to the overall system design this week. The core architecture, consisting of wearable hardware for image capture, cloud infrastructure for storage and processing, and a web application for user interaction remains the same.

For the coming week, our focus will shift to:

  1. Will will continue working on the Blues Notecard configuration and then transition to setting up the Arducam.
  2. Dhruv, having made significant progress on the software backend, will assist William with the Arducam setup to accelerate hardware development.
  3. Rohit will focus on finalizing the user authentication system, implementing the settings interface, and preparing for integration testing with the hardware components.
Posted on

Team Status Report for 3/8/2025

One of the most significant risks currently facing the project is ensuring stable communication between the RPI Pico W and the Blues Notecard. Initial tests are indicating some reliability issues with maintaining a Wi-Fi connection, which could impact data transmission. To mitigate this, we are experimenting with different network configurations and will consider implementing a fallback mechanism that attempts reconnection in case of failure.

On the software side, integrating cloud services remains a challenge. While we initially planned to use AWS, we are still working within the constraints of the free-tier model. If we encounter limitations, we will most likely have to pay out-of-pocket in available AWS services.

Our contingency plan involves storing data locally on the Pico W and batch uploading it when a stable connection is available.

There are currently no design changes to our system architecture.

Thus, this week, we successfully flash the RPI Pico W and establish a basic Wifi connection. We also set up initial configurations for Blues, though further debugging is required to achieve stable data transmission.

Global Factors (written by William Wang)

GlassMate addresses a global need for effortless journaling by automating image capture and AI-driven summaries. It benefits travelers, professionals, and individuals with memory challenges by reducing cognitive load and eliminating manual documentation.

The system leverages IoT and cloud computing for scalable, secure data management, making it accessible worldwide. Privacy concerns are addressed with configurable capture settings and allowing users to not use glasses when doing sensitive tasks, ensuring ethical data collection. By integrating widely supported platforms like Raspberry Pi Pico W and Django, GlassMate remains adaptable and easy-to-use for all types of interested users.

Cultural Factors (written by Dhruv Dixit)

GlassMate considers cultural sensitivities around photography and privacy, allowing users to control when and where images are taken. Multilingual support in the web app enhances accessibility across diverse communities.

Beyond personal use, GlassMate benefits professionals by enabling automated documentation of fieldwork and events during the day. Its AI-generated summaries cater to both visual and text-based memory-keeping preferences, ensuring broad cultural relevance.

Environmental Factors (Written by Rohit Chand)

GlassMate prioritizes sustainability with energy-efficient components, data compression for reduced cloud storage use, and a modular design for easy upgrades.

Its reliance on cloud-based AI processing minimizes hardware requirements, lowering energy and waste consumption. Future iterations can incorporate recycled materials, reducing e-waste while maintaining product longevity and efficiency.

Posted on

Team status report – 2/22/2025

The most significant risk that could jeopardize the success of the project is more on the software end. We were recently informed before our proposal that the course staff typically cannot reimburse software purchases with AWS. As for resolving this issue, we will first use the “free tier” from AWS Educate. If this does not end up working out, we will try using Google Cloud Platform.

In regards to the hardware end, we have pretty much finalized and hope to get more into the development process of the RPI Pico W and the integration of the various components.

Finally, there are currently no changes that will be made to the existing design of the system.

Posted on

Team status report – 2/15/2025

Weekly Status Report (2/15/2025)
The biggest risk that can currently jeopardize our project is not being able to send data between the hardware and cloud. We are trying to do a hotspot connection to transfer images from Arduino cam to cloud. However, we do not have experience in this area so we are not sure how difficult it is. To prevent these risks, we are thinking of many options to send data to the cloud. Our first option is buying a raspberry pi Pico with a blues Notecard. This blues notecard has hotspot and a cellular data card. The cellular data card has a limited data capacity so it won’t last forever but we know it would work. The other option is getting a blues notecard with only wifi. This means we would have to connect with hotspot. If this does not work, the raspberry pi pico also has wifi so we can try hotspot from there. We will get one of these options to work.

From last week, we changed the battery we are going to use because we realized that the raspberry Pi pico needs more power than we thought. It did not cost us that much. Other than that, are design is the same and we plan to continue forward. We are continuously analyzing our designs to make sure that we run into minimal roadblocks.

We have also been working on the design presentation as a group and we are ready to present.

Part A was written by William Wang
GlassMate makes it easier for people to remember and reflect on their daily lives without the stress of manual journaling. By automatically capturing key moments and summarizing them, it helps with mental well-being, especially for those with memory challenges or busy lifestyles. Having a clear record of daily activities can bring a sense of organization and mindfulness, reducing anxiety and improving self-awareness. For individuals who rely on routine, such as professionals or elderly users, GlassMate offers a way to track their days effortlessly, helping them feel more in control of their time and experiences.

From a safety perspective, GlassMate provides passive location tracking that can help users retrace their steps if needed. Whether it’s remembering where you left an item or recalling a past event, having an automated log enhances personal security. By reducing the need for manual note-taking or constant phone use, it also minimizes distractions while commuting or moving through public spaces. In terms of welfare, GlassMate creates an accessible and low-effort way to preserve meaningful memories, ensuring that important moments aren’t lost in the busyness of everyday life. It’s a small but impactful tool that improves peace of mind and personal well-being through technology.

Part B was written by Dhruv Dixit
GlassMate makes it much easier for humans to document their lives and make it more accessible for people to see what they do throughout the day if they live busy lives. It is also a great use case for people that have memory impairments so that they can stop living life forgetting every moment. It is also a great use for families or people traveling to document their journeys effortlessly and not having to pull out the camera every 2 seconds.

This product covers privacy concerns by allowing user’s to choose when and where they take pictures (with setting). Economically, this product can also have an impact on other products being made in the industry that involve journalling. A shift towards products that allow for effortless documentation can enter the market.

Part C was written by Rohit Chand
For production, we would have to use bulk purchasing of components and automated assembly lines to reduce per-unit costs while maintaining proper quality standards. The manufacturing approach would focus on lightweight, durable materials that can be sourced reliably and assembled efficiently. Distribution can be done by partnering with existing technology companies and eyewear manufacturers so that we can use existing channels to minimize infra costs and maximize our market reach. We believe that this kind of model reduces our distribution overhead while getting us into the market. From a consumption perspective, we would implement a tiered pricing strategy with a base hardware cost of around $200-300, complemented with a subscription model for cloud storage and AI features. Additionally, scalability is built into the product itself as for the modular design that allows for easy component upgrades.