Posted on

Team Status Report for 02/08/2025

Risks & Management:

  • Object Detection Confusion
    • Risk
      • The camera may struggle to differentiate between similar looking items (e.g. Fiji apples vs Honeycrisp apples) or misidentify certain products.
    • Risk management
      • Collect & train the YOLOv8 model with wider variety of grocery products to improve detection accuracy. Optimize confidence thresholds in detection.
    • Contingency Plan
      • Implement a User Confirmation Step: When the app detects similar items, prompt the user with a choice selection (e.g. “Was the item you just put in A, B, or C?”) for quick correction.

Design Changes & Justification:

  • Initially, we planned to populate our own dataset of Aldi grocery items to account for environmental and lighting discrepancies. However, we plan to limit our scope of the dataset to use the online Aldi database of products to prioritize functionality of our prototype. Now, it should be able to recognize a standard set of grocery items without hindering our progress if we were to spend too much time creating a brand new custom dataset.

Progress:

  • App setup & design
  • Yolov8 and Open CV pipeline finalization
  • Aldi’s dataset collection started
  • Finalized  to-be-purchased hardware devices
  • Designed device shell
Posted on

Lekha’s Status Report for 02/08/2025

Work Accomplished:

This week, I focused on the initial research and preparation for the necessary hardware components of our projects. Some of my key accomplishments include:

  1. Finalized  to-be-purchased hardware devices pending TA approval
    • NVIDIA Jetson Orin Nano Developer Kit – $249
      • This specific kit offers performance improvements over the base kit, proving useful for AI (object detection tasks). This will prove especially useful for our computer vision capabilities in identifying grocery products.
      • Barrel Jack Power Supply for powering device
    • Arducam IMX477 – $80
      • Real-time object identification for video streams (identify grocery items as it is being placed in cart)
        • 60 FPS
      • Compatible with Jetson Orin Nano
  2. Decided to 3D print case encompassing Jetson Orin Nano and Arducam
    • customizable compact case fit to device sizes
  3. Consolidated research on setting up Jetson Orin Nano and connecting with specific camera 

Progress Status:

I am on track with our current timeline of finalizing device options in order to start preparing device setup for next week.

Next Week’s Goal:

  • Submit purchase forms for each of the hardware devices on Monday with TA approval
  • Mockup of hardware design on prototyping platform in most compact and efficient manner
  • Setup training procedure for YOLOv8 model
Posted on

Aanya’s Status Report for 02/08/2025

Work Accomplished:

This week, I focused on the initial research and setup phase of the computer vision pipeline for SmartCart.

  • Started curating a dataset by sourcing existing grocery product images from GitHub repositories and other publicly available datasets.
  • Investigated USFDA food data to map size-to-weight ratios for grocery items, which will be useful for estimating weights when barcode or packaging data is unavailable.
  • Reviewed OCR-based text extraction methods for distinguishing visually similar products by identifying brand names and labels.

Progress Status:

I have laid the groundwork for the data acquisition and preprocessing steps necessary for real-time product recognition. The insights gained this week will guide dataset preparation and the initial implementation of YOLOv8.

Next Week’s Goal:

For next week, I plan to move into dataset preparation and initial model setup by:

  • Finalizing a structured dataset of Aldi grocery products by combining GitHub-sourced images, USFDA data, and web-scraped product images.
  • Implementing OpenCV preprocessing techniques for image enhancement and noise reduction.
  • Setting up a baseline YOLOv8 model with an initial subset of grocery product images.
  • Developing a basic pipeline to match detected objects with database records, using text recognition and visual similarity scoring.
Posted on

Lois’s Status Report for 02/08/2025

Work Accomplished:

This week, I focused on the initial design and setup phase of the mobile application. My key accomplishments include:

  • UI Wireframe Design using an iPad

  • React Native Framework Setup in VSCode
  • Figma UI Design for essential screens

Progress Status:

I am currently on track with the project schedule. The goals for this week (Design UI Wireframe, Set up React Native Framework) were completed.

Next Week’s Goal:

For next week, my focus will be on developing the UI for adding detected products to the cart. This will involve:

  • Finishing Figma app mock-ups
  • Implementing the UI Components for product detection & selection
  • Simulating detected products using mock data