IS480 Team wiki: 2012T1 M.O.O.T/Project Management
Project Schedule | Schedule & Bug Metrics | Gender Recognition Metrics | Risk Management | Minutes Repository |
Contents
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.
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 |
|
|
N.A. |
2 | 25/08/12 – 31/08/12 |
|
|
|
3 | 01/09/12 – 08/09/12 |
|
|
|
4 | 09/09/12 – 16/09/12 |
|
|
|
5 | 17/09/12 – 23/09/12 |
|
|
|
6 | 24/09/12 – 29/09/12 |
|
|
Behavioural parameters were not very accurate |
7 | 01/10/12 – 06/10/12 |
|
|
N.A. |
8 | 08/10/12 – 12/10/12 |
|
|
|
9 | 15/10/12 – 19/10/12 |
|
|
|
10 | 22/10/12 – 26/10/12 |
|
|
|
11 | 29/10/12 – 02/11/12 |
|
|
N.A. |
12 | 05/11/12 - 09/11/12 |
|
|
|
13 | 12/11/12 - 18/11/12 |
|
|
N.A. |
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 |
| ||
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 | Planned to push to Iteration 6 | Dropped | Dropped - time required exceeds possible value added | |
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 |
|
Midterm Wiki
M.O.O.T Midterm Wiki |
|