This demonstration application illustrates how Hierarchical Temporal Memory (HTM) can be applied to video recognition. The HTM network in this demo has been trained to locate people in surveillance video footage. You can see how the HTM operates by experimenting with the sample videos that are bundled with this application. For each video, the application will process it in real time on your machine and track the locations of people and other moving objects, while correctly discriminating between the two.
HTM networks can be applied to a wide variety of different problems in image and video recognition.
The network and video processing technology in this demonstration was developed in partnership with Vitamin D for their upcoming Smart Video application. If you would like to use HTMs in your own video applications please contact us at info@numenta.com.
No comments:
Post a Comment