Original plan:

To make a dress based on the weather

New plan:

Make a dress based on breathing

Changes:

With the original dress, I wasn’t a fan of how data viz-y the dress was looking.

I liked the idea of a mechanical dress, but I didn’t want it to just respond to stimulus, I wanted it more to look like a creature of its own.

With this new breathe dress, the only input is breathing, but the dress itself will be positioned in a metal cage-like space. The skirt of the dress will be attached in certain places using a fishing line thread reel system.

When the person inhales, the dress will float upward, and when the person exhales, it lowers, hence breathing.

Sketches:

 

 

Where I’m at now:

Dress designing/material purchasing:

I am currently in the process of choosing a material for the skirt. Since the skirt will be moving using only fishing line, it needs to be super lightweight.

 

Fabrication of the rig:

The steel for the machine itself arrived on Tuesday, and I’m am currently cutting/welding the base of the structure.

Mechanical reel system:

I am currently testing motors/finding ways to attach the spool to a motor.

Upcoming checkpoints:

April 17:

• Finish construction of the rig
• fabric purchased and measured out
• physical mechanics of reel figured out

April 22:

• reel installed and function on rig
• dress sewn

April 25:

• Prototype testing finished

April 28th:

• Crit day

Tweet 

Eye tracking data collection about sports performance by @amy_friedmann

Description

This project will focus on collecting and visualizing data about eye movement when shown athletic situations. This information can be applied to gaming, advertisements, and many other areas. I am focusing on athletics as I hope to utilize the information to create an eye tracking feedback system to improve beginners athletic performance. Understanding where to look will allow for athletes to expand their knowledge and better understand how to read another players body language.

Currently I will be collecting a system to record the data, and analyze the differences. I hope to create an interactive visualization that uses scope outside of heat map. I will be using the eyeTribe eyetracker and Processing to create this information and visualize the data.

Slides

Research

Tobii creates eyetracking devices. They note the benefits of eyetracking include: “[1] understand human behavior, [2] enable hands-free interaction, [3] create new experiences and humanized user interfaces”.

Tobii has done some tracking in sports research, but this data isnt readily available. You can use the Tobii Glasses Eye Tracker for real time data creation.

UCD School of Psychology has utilize eye trackers to distinguish between beginner and advanced golf & tennis players using the Tobii eye trackers.

Research has also been done on how judges look at racing horses to evaluate the breed in competitions.

SensoMotoric Instruments Inc. has looked into eye tracking in baseball to improve visual perception.

 

My project idea initially was to transform water puddles into portals to another universe. When I went out after rains and clicked water puddles (shown below) , I realized few things:

[gview file=”https://ems.andrew.cmu.edu/2015/wp-content/uploads/2015/04/IMG_20150407_093232123.tif”]
[gview file=”https://ems.andrew.cmu.edu/2015/wp-content/uploads/2015/04/IMG_20150407_090727608.tif”]
[gview file=”https://ems.andrew.cmu.edu/2015/wp-content/uploads/2015/04/IMG_20150407_0932321231.tif”]

1. The perfect puddle(blue sky reflected clearly) does not exist in Pittsburgh. After rains, the sky tends to be cloudy. Hence , even if the reflection is clear, it is never blue. I was planning to use the distinction of color between dark, grey pavement and sky blue of reflection to recognize the shape of puddle. Looks like it is going to be extremely difficult.

2. Assuming the sky becomes magically clear and reflects blue, the puddle reflection is not going to be nice blue of sky but a blue with a tint of the pavement color (water is transperent!). Hence, this strategy does not work.

While clicking puddles I came across manholes. These are usually of same size, circular and can be found easily at many places and pavements. Surprisingly, manholes in Pittsburgh have various patterns.

I am going to detect these manholes and transform them into portals to another world when you see them through phone application.

Where I am at:
1. Golan introduced me to ImageJ http://imagej.nih.gov/ij/
I processed 3 different manhole that I have and came up with a workflow of recognizing manhole out of the image to create masks.

Manhole type 1:
Workflow:
1. Reduce the image size (400xY)
2. Convert the image into 8 bit
3. Make Binary
4. Fill Holes
5. Run Minimize filter with pixel size 7.
6. Convert to Mask

Manhole type 2:
1. Reduce the image size (400xY)
2. Convert the image into 8 bit
3. Run the Median Blur, pixel limit 5
4. Variance with 5 pixel radius

Manhole type 3
1. Reduce the image size (400xY)
2. Convert the image into 8 bit
3. Maximum
4. convert to Binary
5. Erode 5-6 times
6. Fill holes

Future Step:
Recreate detection of manholes using ofxcv in openFrameworks.

Sidenote:
I also secretly want to be transported to Japan for this project. Japanese manholes are art pieces! Look at them, they are great image targets for unity!!

Overview

This project is an open source and accessible hardware platform for advanced cinematics. These technologies for camera movement are complicated and expensive, but this arrangement will give the same level of dynamic capability to anyone with a laptop and a DSLR Camera.

Project Update

+Hardware is currently being fabricated.
+Software Framework has been established.
+All critical hardware has been sourced.

 

Current Challenges

+Material Rigidity at low cost
(Since the desired end product is good video, any major vibration transference or lack of rigidity is not acceptable)

+Solutions Include Wood or High Density Plastics
(Metal is time / resource / financially consuming)

Remaining Tasks

+Solve Key Software Math (Coordinate Translation)
+Finalize Hardware (Refine / Polish)

Timeline Adherence / Revision

+Tue April 14th – Functioning Hardware prototype with Arduino control
*All hardware specific timing bugs are worked out

+Tue April 21st – Hacked together prototype with Kinect coordinates
*Major math has been solved. The rest of the time is for refined use cases

+Tue April 28th – Refined project

3 Questions

What projects do you know of that use Kinect for real time mechanical tracking?

Any opinions of the best hardware to use for a macbook to motor connection?

What features do you see this having from a use case scenario?