<< Chapter < Page Chapter >> Page >
Some possible investigations in the field

There are many future directions that we can foresee for intelligent motion analysis on compressed sensing datadue to the minimal computation and data storage required.

One major point of future study is the feature extraction algorithms for compressed sensing. Our analysislooked at only a very small part of the many features that we think can be gleaned from the compressed sensing measurements. For example we can look at the acceleration, which could be trivial using the difference in the velocity feature. Our calculation of total intensity can also be fully exploited. Similarly, we believe it is possible to develop algorithms for shape recognition.

When the number of feature calculations availiable increases, a Support Vector Machine (SVM) can be used to analyze the data. The SVM is a prediction algorithm which after being trained with sufficient data can classify new data on the basis ofthe training. This is very useful when the data is multi-dimensional.

Get Jobilize Job Search Mobile App in your pocket Now!

Get it on Google Play Download on the App Store Now




Source:  OpenStax, Elec 301 projects fall 2005. OpenStax CNX. Sep 25, 2007 Download for free at http://cnx.org/content/col10380/1.3
Google Play and the Google Play logo are trademarks of Google Inc.

Notification Switch

Would you like to follow the 'Elec 301 projects fall 2005' conversation and receive update notifications?

Ask