Grocery Shopping Assistant Carolina Galleguillos Pixel-café / June 2 2006.

Slides:



Advertisements
Similar presentations
McGraw-Hill/Irwin Copyright © 2013 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 9 Emerging Trends and Technologies: Business, People,
Advertisements

Carolina Galleguillos and Serge Belongie Department of Computer Science and Engineering, UCSD Grocery shopping is a common activity.
RFID IN UNIVERSITY OF JAMMU RFID is used in libraries primarily to automate the book handling process including checkout, inventory maintenance, and check-in.
1 State Records Center Searching and Requesting Inventory  Versatile web address:  Look for any new ‘Special.
3D Mobile Mapping Dave Henderson Topcon Positioning Systems
Team RFEyes Presents:. Project SmartCart Sponsored By Dr. Andrew Szeto & The National Science Foundation Tatsani Inkhamfong Andres Flores Alain Iamburg.
I-Cane (get it?? ‘eye’-cane) - Brian Loo (bloo) - Zane Starr (zcs) - Geeta Shroff (gshroff)
Orientation and Mobility. What is Orientation and Mobility? Orientation – learning where one is in space, also in relation to other people or things Mobility.
School of Retail & Services Management Managing Cultural Diversity.
Express Stores Reducing Shoplifting. The Problem What can Express #892 do to reduce shoplifting?
TPS – UNIQUE HARDWARE ( Option 1: Transaction Processing Systems.
Jewelry Inventory Management Software Your Logo Here Welcome to a demonstration of Del Mar Data Systems Jewelry Inventory Management.
Polymorph Technologies Pte Ltd “ The Leader in Information Technology” ACCPOL (Point-of-Sales)
A Beginners Guide to Web Site Design. What we will cover…. Planning your site. Creating a template. Images and Fonts. Absolute vs. Relative Links.
Trinetra (“The Third Eye”) Virtual Sight for the Visually Impaired Priya Narasimhan Carnegie Mellon University
Mobility Aid For The Blind By Amir Gonnen. The oldest aids Walking Cane Guide dog Problems: – Skills and Training phase – Range – Very little information.
A New Paradigm for E-Groceries IS 485, Professor Matt Thatcher.
Assessing for Adaptive Technology Needs Disability Training Network July 2007.
Input devices, processing and output devices Hardware Senior I.
SmartCart The Interactive Shopping Cart Display UCSB ECE 189A/B, Fall 2012 – Spring 2013 Pallavi Jain Deniz Kaplan Peter Nguyen Vivian Vasquez.
BlindAid Semester Final Presentation Sandra Mau, Nik Melchior, and Maxim Makatchev.
Mobile commerce – what, how and where? Alfio Grasso Deputy Director Auto-ID Lab, ADELAIDE.
1 P ersonal S hopping A ssistant Presented By: John Chang Team Members: Albert Ayres, Jeremy Allen, Steve Eleyet, & Tony Taylor Copyright © ,
1 Designing Need-based Internet Web Sites in Counseling and Career Services James P. Sampson, Jr. Florida State University Copyright 2002 by James P. Sampson,
Input, Chapter 4 ITSC 1401, Intro to Computers Instructor: Glenda H. Easter.
Alternative Input Devices Part B There will be a test on this information (both part a & b).
Usability By: Sharett Wooten and Gwen Payne. What is Usability Usability addresses the relationship between tools and their users. In order for a tool.
XP Practical PC, 3e Chapter 13 1 Working with Graphics.
A questionnaire is a effective way of gaining information quickly and directly from an audience, and the results from a questionnaire can be displayed.
IGCSE ICT Communicating Ideas.  identify the advantages and disadvantages of using common applications to communicate ideas:  Multimedia presentations.
DATA COLLECTION METHODS CONTENT PAGE How data is collected via questionnaires. How data is collected via questionnaires. How data is collected with mark.
The Marketing Plan Business Organization and Management Chapter 10.
What is the Wirelesscafé Solution? Restaurant application providing always on connection to your customer smart phone Mobile marketing engine for restaurants.
Section 8.1 Create a custom theme Design a color scheme Use shared borders Section 8.2 Identify types of graphics Identify and compare graphic formats.
OCR GCSE Computing © Hodder Education 2013 Slide 1 OCR GCSE Computing Chapter 2: Memory.
INFO 355Week #71 Systems Analysis II User and system interface design INFO 355 Glenn Booker.
Problemsolving Problem Solving – 4 Stages Analysis Design Development Evaluate (ADDE) Note: In this unit Evaluate is not covered in depth.
1 Research Question  Can a vision-based mobile robot  with limited computation and memory,  and rapidly varying camera positions,  operate autonomously.
By Phileo Don - Okhuofu. DATA COLLECTION  Data can be collected by the use of questionnaires or data collection forms.  These could be printed out and.
The Supply Chain Doctors Warehousing Fundamentals The Supply Chain Doctors Kimball Bullington, Ph.D. Cliff Welborn, Ph.D.
AN INTELLIGENT ASSISTANT FOR NAVIGATION OF VISUALLY IMPAIRED PEOPLE N.G. Bourbakis*# and D. Kavraki # #AIIS Inc., Vestal, NY, *WSU,
1 Electrical and Computer Engineering Aura Ganz, James Schafer, Yang Tao, Carole Wilson, Meg Robertson & Laura Bozeman Indoor Navigation for the Visually.
Introduction to the new mainframe © Copyright IBM Corp., All rights reserved. 1 Main Frame Computing Objectives Explain why data resides on mainframe.
Understand The Use Of Technologies In Fashion Merchandising And Marketing FM 3.02.
Using Adaptive Tracking To Classify And Monitor Activities In A Site W.E.L. Grimson, C. Stauffer, R. Romano, L. Lee.
HOW SCANNERS WORK A scanner is a device that uses a light source to electronically convert an image into binary data (0s and 1s). This binary data can.
Gates Winkler Jordan Samuel Fei Yin Shen 9 September 2009 Virtual Wallet Design Proposal To create a handheld device which will save money and time through.
  Computer vision is a field that includes methods for acquiring,prcessing, analyzing, and understanding images and, in general, high-dimensional data.
Marketing Technology iDOG By DreamWeaver. Image of our iDOG.
What do you know about guide dogs Guide dogs Guide dog puppies.
Lesson 8 - Merchandising VIRTUAL BUSINESS - RETAILING.
Year 12: Unit 2, living in the digital world. 1. What is ICT? ICT is the use of technology to convert data to information. It covers many areas, especially.
Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects for Blind Persons.
Understand The Use Of Technologies In Fashion Merchandising And Marketing FM 3.02.
Assistive Technologies In the Classroom Resources for Special Needs.
 Many people like the flexibility of digital images. For example:  They can be shared by attaching to /uploading to Internet  Sent via mobiles.
RECORDS MANAGEMENT Judith Read and Mary Lea Ginn Chapter 12 Electronic Media and Image Records 1 © 2016 Cengage Learning ®. May not be scanned, copied.
Section 8.1 Section 8.2 Create a custom theme Design a color scheme
Understand The Use Of Technologies In Fashion Merchandising And Marketing FM 3.02.
Polymorph Technologies Pte Ltd “ The Leader in Information Technology”
Input and output devices for visually impaired users
English for Advance Learners I
Chapter 13 Working with Graphics
Blind Guidance system (BGS)
Open Minds ESL Electronic Shelf Label
Chapter 2: Input and output devices
Review on Smart Solutions for People with Visual Impairment
Interactive Visual System
Understand The Use Of Technologies In Fashion Merchandising And Marketing FM 3.02.
Presentation transcript:

Grocery Shopping Assistant Carolina Galleguillos Pixel-café / June

Description GroZi project (grocery shopping assistant) Increase independence of people with low vision (specially blind) to perform grocery shopping in a supermarket or store. Help to plan shopping list, walking path to the store and grocery shopping.

Motivation 1.3 million legally blind people in the U.S Grocery store are underselling to this market. Blind people are high cost customers. Advance research on object recognition for mobile robotics with constrained computing resources.

Motivation Characteristics Grocery Store: Structured Environment (+). Controlled Lightening (+). Maintained by staff (+). Well indexed (+). People moving around aisles (-). Huge amount of products (30K) (-).

Motivation Possible existing solutions: 1.Seeing-eye dog trained. 2.RFID tags (aisle, shelf, product). 3.Barcode scanning (shelf). 4.Help of sighted guide/customer service. 5.Memorize store layout. 6.Home delivery.

Why computer vision? 1.Limited ability of dogs. 2.RFID tags bring privacy concerns and heavy infrastructure. 3.Eye safety and mislabeling. 4.Independence. 5.Store layout changes constantly. 6.Autonomy.

Our Solution Develop a handheld device that performs visual object recognition with haptic feedback. Avail of complementary resources (RFID, Barcode scan, sighted guide) We are focusing on the computer vision aspects of this problem.

MoZi Box General purpose low-cost mobile system geared for computer vision applications. MoZi is a combination of the Mobile Vision System (MoVs) and ZigZag Finite memory : Compact Flash (CF) cards ranging from 256 MB to 4 GB. Processor speed: in the neighborhood of MHz Frame rate: enough snapshots to cover the shelf with some overlap (as in panoramic stitching) (15fps instead of 30fps?). Color Calibration: Macbeth color chart to calibrate the color space.

Use of the System Creating a Shopping List. Getting to the Grocery Store. Navigating the Store.

Shopping List Online Website: –Website stores data and images of different products. –Feedback from users. –Provides walking path. Prepare shopping list. Download information into Mozi Box.

On the way Separate project. Mozi Box with GPS. Visual waypoints. Traffic/Street sign reading. Use in addition to cane and asking sighted bystanders.

Inside the Store Finding aisle (OCR, RFID, ask). Avoiding obstacles (cane). Finding products (sweep of aisle, spot product, barcode check). Checking out (coupon and cash).

Obtaining training data Online Images (Web). Collecting from MoZi box (in situ). Collecting from embedded camera near the barcode scanner (in situ). Known databases (COIL-100,ETH- 80, etc.)(more research oriented) Synthetic examples. Active learning.

Obtaining training data Active learning problem: Find UPC for the corresponding image (labeling). Semi-supervised. Weakly labeled.

Obtaining training data Sunshine UCSD. –Venue for pilot study. –4K items in stock. –1749 sq. ft. (assignable) –We want to scale to a bigger number of products (30K). –No bakery or vegetables.

Object Recognition 2 types of recognition (m:n, m<<n): Detection (of objects). Verification (objects detected are in that list). Algorithms: SIFT, AdaBoost cascade, Multiclass Adaboost, Probabilistic Boosting tree, Color histogram matching, etc.

Text Detection Standard OCR is unlikely to be sufficient. Low resolution and distortion are main problems. Reading aisle signs, text on shelves.

Considerations Occlusion and clutter of products (caused by people and shopping carts). Multiple images of same shelf to perform hole-fill-in. Cannot fit dominant plane to the front of product shelves. Large number of items.

Acknowledgements People (UCSD/Calit2): Serge Belongie John Miller Stephan Steinbach Michele Merler Tom Duerig Captions: Dennis Metz/ D. Stein [ X. Chen and A. Yuille ]

Questions? Comments?