In the last chapter, we introduced processing of each type of raw sensor data independently to realize different levels of recognition capabilities. We found that inertial sensors provide information about movement across different axes. Audio streams can be processed not only for sound types but also words and natural language. We also showed how to recognize different objects, faces, activities, and more. Now we imagine what is possible if we were able to correlate the understanding across multiple sensor types simultaneously. This ...
© Omesh Tickoo and Ravi Iyer 2017
Omesh Tickoo and Ravi Iyer, Making Sense of Sensors, 10.1007/978-1-4302-6593-1_3
3. Multimodal Recognition
Omesh Tickoo1 and Ravi Iyer2
(1)Portland, Oregon, USA
(2)3585 SW, Portland, USA
Get Making Sense of Sensors: End-to-End Algorithms and Infrastructure Design from Wearable-Devices to Data Centers now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.