HeaderSIS.jpg

IS480 Team wiki: 2012T1 M.O.O.T/Project Management

From IS480
Jump to navigation Jump to search

Home

Team/Project Partners

Project Overview

Project Management

Design Specifications

Technical Applications


Project Schedule Schedule & Bug Metrics Gender Recognition Metrics Risk Management Minutes Repository

Post-Acceptance Project Schedule

Planned Schedule Summary

This is the latest schedule amended prior to the beginning of iteration 3. After numerous discussions, we have been informed that CMA would really like to have photo-taking feature. Our primary research of measurement collection in iteration 1 has also shown us that it is not possible to determine gender based on Waist-Hip ratio as waist is not detected by Kinect. The highlight of the schedule amendment is hence the changes of interactive features to photo taking feature and gender recognition based on 4 parameters: height, shoulder length, whether shopper is holding on to a handbag, and whether shopper is wearing long skirt. The focus will be on gender recognition based on neural network until midterm, followed by development of photo taking feature post midterm.


WithPhotoTakingScheduleSummary.png


Access previous planned schedules to view earlier planned schedules prior to firming up of client requirements and primary research on differences between male and female.

Weekly Progress

Week Date Scheduled Features Completed Features Pending Features/Remarks
1 17/08/12 – 24/08/12
  • Explore Classifier Algorithm (CA)
  • Measurement collection
  • Theoretical understanding of Neural Network (NN) and its classification feature
  • Measurement collection
N.A.
2 25/08/12 – 31/08/12
  • Analysis of measurement collection
  • Gender differences trend establishment
  • Gender recognition based on Waist-to-Hip Ratio (WHR)
  • NN classification
  • Analysis of physical measurement collection classification feature
  • Gender differences trend establishment based on physical measurement analysis & secondary research
  • Measurement of height based on image captured by Kinect
  • Found that waist cannot be detected by Kinect, hence dropping WHR
  • Difficulties encountered in implementing NN classification
3 01/09/12 – 08/09/12
  • NN classification & scoring system
  • Parameters expansion: neck & shoulder width
  • Passing of height and shoulder width captured by Kinect to NN
  • NN classification based on height and shoulder width
  • Decided to include parameters hasBag & hasSkirt instead of neck width in the upcoming week
4 09/09/12 – 16/09/12
  • Gender recognition based on complete set of inputs
  • Capturing shopper’s outline
  • Countdown timer
  • Gender recognition based on height & shoulder width
  • hasBag & hasSkirt displayed for consideration
  • Countdown timer
  • Refining of shopper's outline
  • hasSkirt, hasBag parameters to be improved and integrated with passing in of parameters through Kinect
5 17/09/12 – 23/09/12
  • Capturing of photo
  • Backward propagation
  • Saving learning state
  • Integration of photo taking with gender recognition
  • Capturing of photo
  • Backward propagation
  • Integration of photo taking with gender recognition
  • Saving learning state is pushed back to Iteration 6
6 24/09/12 – 29/09/12
  • Microsoft Tag
  • Advertisement Management System page
  • Refining overlaying of augmented background
  • Integration of Microsoft Tag into photos
  • Addition of behavioural parameters for gender recognition
  • Integration of gender recognition (with behavioural parameters) with photo taking
  • Microsoft Tag
  • Advertisement Management System page
  • Refining overlaying of augmented background
  • Integration of Microsoft Tag into photos
  • Addition of behavioural parameters for gender recognition
  • Integration of gender recognition (with behavioural parameters) with photo taking

Behavioural parameters were not very accurate

7 01/10/12 – 06/10/12
  • Using real figures instead of Kinect figures
  • Addition of behavioural parameters for gender recognition
  • Integration of gender recognition (with behavioural parameters) with photo taking
  • Integration of Microsoft Tag, gender recognition, and photo taking
  • Using real figures instead of Kinect figures
  • Addition of behavioural parameters for gender recognition
  • Integration of gender recognition (with behavioural parameters) with photo taking
  • Integration of Microsoft Tag, gender recognition, and photo taking
N.A.
8 08/10/12 – 12/10/12
  • Scene transition
  • Display shopper's silhouette
  • Make callout bubble dynamic
  • Code clean up
  • Scene transition
  • Display shopper's silhouette
  • Integration of outline-photo-taking-displaying photo with tag
  • Make callout bubble dynamic
9 15/10/12 – 19/10/12
  • Choosing of door
  • Unsupervised learning
  • Make callout bubble dynamic
  • Stick man approaching chosen door
  • Debugging of bug: crashing in the wild
  • Choosing of door
  • Auto-rescale callout bubble
  • Stick man approaching chosen door
  • Recording of learning response to database
  • Debugging of head-depth bug causing crash in wild environment
  • Callout bubble position needs to be relative to user's
  • Integration of unsupervised learning to AlterSense
10 22/10/12 – 26/10/12
  • Debug to enable reverting to scene 0
  • Relating door scene image with photo taking scene
  • Integration of unsupervised learning to AlterSense
  • Callout bubble to follow (relative to)user's position
  • Activation of training upon detection of dropping accuracy
  • Relating door scene image with photo taking scene
  • Callout bubble to follow (relative to)user's position
  • Integration of unsupervised learning to AlterSense
  • Debug to enable reverting to scene 0
  • Unsupervised learning to be modified to be less obvious
  • Activation of training upon detection of dropping accuracy
11 29/10/12 – 02/11/12
  • Debug to enable reverting to scene 0
  • Modified unsupervised learning (Scene 3)
  • Gender-targeted content insertion into AMS
  • Modified display of tag for enhanced user experience
  • Instructional callouts to choose door and scan tag
  • Error control: pick closest skeleton and display out-of-frame instruction
  • Thorough integration for User Testing 2
  • Debug to enable reverting to scene 0
  • Modified unsupervised learning (Scene 3)
  • Error control: pick closest skeleton and display out-of-frame instruction
  • Gender-targeted content insertion into AMS
  • Modified display of tag for enhanced user experience
  • Thorough integration for User Testing 2
  • Instructional callouts to choose door and scan tag

N.A.

12 05/11/12 - 09/11/12
  • Improve display of hat
  • Improve grabbing of hats
  • Self healing if accuracy drops
  • Solve raising of hand message bug
  • Solve door and tag scanning instructions bug
  • Solve raising of hand message bug
  • Increase size of hats so that they will be more noticeable by shoppers
  • Enable grabbing of hat even when shopper's elbow is not higher than shopper's shoulder
  • Solve door and tag scanning instructions bug
  • "Self healing if accuracy drops" is scrapped as reliability of hat-picking scene for gender validation was low, at 27% based on UT2
13 12/11/12 - 15/11/12
  • Instruction to stand still in Scene 0: galaxy scene
  • Hat-picking: right hand for female hat, left hand for male hat
  • Retrieving of tag information from Microsoft Server
  • Parsing of tag information
  • Display of tag information in AMS
  • Instruction to stand still in Scene 0: galaxy scene
  • Hat-picking: right hand for female hat, left hand for male hat

To be completed by Monday, 19/11/2012:

  • Retrieving of tag information from Microsoft Server
  • Parsing of tag information
  • Display of tag information in AMS

Project Planned vs Actual Schedule

Iterations Planned Actual Comments
1 Explore Classifier Algorithm Week 1 Week 1 Found out about Neural Network
Primary research: measurement collection 24/08/12 24/08/12 58 participants (30 males, 28 females)
Analysis of measurement collection Week 2 Week 2
Gender differences trend establishment Week 2 Week 2
  • Decided to use height, shoulder width, and probably hip width
  • Secondary research yielded possibility to explore Centre of Moment
Gender recognition based on Waist-to-Hip Ratio Week 2 Dropped Decided to drop Waist-to-Hip Ratio as Kinect cannot detect waist
Neural Network classification to determine gender based on Waist-to-Hip Ratio Week 2 Height measurement & face tracking on Kinect Week 2
2 Neural Network classification & scoring system Week 3 Gender classification based on height & shoulder width Week 3
Physical parameter expansion: neck & shoulder width Week 3 Shoulder width & height passed in as parameters,but not neck Week 3 Behavioural parameters: hasBag, hasSkirt, hasLongHair (related to neck)coded but not passed in as parameters
3 Gender recognition based on physical & behavioural parameters Week 4 Skirt & bag behavioural displayed, but not used for gender recognition Ongoing
Countdown timer Week 4 Week 4
Capturing shopper's outline Week 4 Week 4 Edges refined as well
Capturing of photo Week 5 Week 5
Backward propagation Week 5 Week 5
Saving learning state Week 5 Pushed to Iteration 6
Integration of photo taking with physical gender recognition Week 5 Week 5
4 Microsoft Tag creation Week 6 Week 6
Advertisement Management System page Week 6 Week 6
Refining image overlaying Week 6 Week 6
Incorporate tag into photo Week 6 Week 6
Gender recognition: physical + behavioural Week 6 Week 7
Integration of gender recognition (physical+behavioural) with photo taking Week 6 Week 7
5 Scene transition Week 8 Week 8
Display shopper's silhouette Week 8 Week 8
Make callout bubble dynamic Week 8 Week 9 Dynamic size was completed in week 8, but more time was required to make the position relative to user's
Choosing of door Week 9 Week 9
Unsupervised learning Week 9 Week 10 Direct questioning: Yes or No for guess
Stick man Week 9 Week 9
Debugging: error control for crashing upon deployment in uncontrolled environment Week 9 Week 9
6 Enable auto refreshing of scene - back to scene 0 Week 10 Week 11
Integration: door scene to photo taking scene Week 10 Week 10
Integration: unsupervised learning to after door scene Week 10 Week 10
Relative position of callout bubble to user Week 10 Week 10
Switch for activation of training Week 10 Week 10
Hat-picking unsupervised learning (scene 3) Week 11 Week 11 Modification of the direct unsupervised learning
Error control: pick nearest skeleton Week 11 Week 11
Error control: user out of-frame Week 11 Week 11
Separate tag and photo displays Week 11 Week 11
Gender-targeted content insertion into AMS Week 11 Week 11
Instructions for choosing door and scanning tag Week 11 Week 11
7 Improve display of hat Week 12 Week 12 Make hats more noticeable - expand and shrink
Improve grabbing of hats Week 12 Week 12 Enable grabbing with lower elevation of elbow
Self healing if accuracy drops Week 12 Dropped Reliability of hat-picking scene for unsupervised learning is only 27% based on UT2, may be more damaging than helpful for gender validation
Debug: message from door scene remains to hat-picking scene Week 12 Week 12
Debug: choosing of door instruction does not appear Week 12 Week 13
Debug: scanning of tag instruction does not appear Week 12 Week 13
Instruction to stand still in galaxy scene Week 13 Week 13
Hat picking: enable grabbing with either left or right hand Week 13 Week 13
Retrieval of tag information from Microsoft Server Week 13 Week 13
Parse tag information Week 13 Week 13
Display tag information in AMS Week 13 Week 13

Finals Wiki

M.O.O.T Final Wiki
1. Project Progress Summary
1.1. Project Highlights
1.2. Project Challenges
1.3. Project Achievements
2. Project Management
2.1. Project Schedule
2.2. Project Metrics
2.3. Technical Complexity
3. Quality of Product
3.1. Project Deliverable
3.2. Quality
3.3. Deployment
3.4. Testing
4. Reflection
4.1. Sponsor Comment
4.2. Team Reflection
4.3. Individual Reflection

Midterm Wiki

M.O.O.T Midterm Wiki
1. Project Progress Summary
1.1. Project Highlights
2. Project Management
2.1. Project Status
2.2. Project Schedule
2.3. Project Metrics
2.4. Project Risks
2.5. Technical Complexity
3. Quality of Product
3.1. Intermediate Deliverables
3.2. Deployment
3.3. Testing
4. Reflection
4.1. Team Reflection
4.2. Individual Reflection

Pre-Acceptance

MOOTschedule.jpg