DocumentCode :
2696636
Title :
Kinect=IMU? Learning MIMO Signal Mappings to Automatically Translate Activity Recognition Systems across Sensor Modalities
Author :
Baños, Oresti ; Calatroni, Alberto ; Damas, Miguel ; Pomares, Héctor ; Rojas, Ignacio ; Sagha, Hesam ; Del R Millan, Jose ; Tröster, Gerhard ; Chavarriaga, Ricardo ; Roggen, Daniel
Author_Institution :
Wearable Comput. Lab., ETH Zurich, Zurich, Switzerland
fYear :
2012
fDate :
18-22 June 2012
Firstpage :
92
Lastpage :
99
Abstract :
We propose a method to automatically translate a preexisting activity recognition system, devised for a source sensor domain S, so that it can operate on a newly discovered target sensor domain T, possibly of different modality. First, we use MIMO system identification techniques to obtain a function that maps the signals of S to T. This mapping is then used to translate the recognition system across the sensor domains. We demonstrate the approach in a 5-class gesture recognition problem translating between a vision-based skeleton tracking system (Kinect), and inertial measurement units (IMUs). An adequate mapping can be learned in as few as a single gesture (3 seconds) in this scenario. The accuracy after Kinect → IMU or IMU → Kinect translation is 4% below the baseline for the same limb. Translating across modalities and also to an adjacent limb yields an accuracy 8% below baseline. We discuss the sources of errors and means for improvement. The approach is independent of the sensor modalities. It supports multimodal activity recognition and more flexible real-world activity recognition system deployments.
Keywords :
MIMO communication; computer vision; gesture recognition; learning (artificial intelligence); object tracking; sensors; IMU; Kinect translation; MIMO signal mapping learning; MIMO system identification techniques; activity recognition systems; flexible real-world activity recognition system; gesture recognition problem; inertial measurement units; multimodal activity recognition; sensor modalities; vision-based skeleton tracking system; Acceleration; Accuracy; Joints; MIMO; Position measurement; Smart phones; Target recognition; HCI; IMU; Kinect; MIMO models; activity recognition; signal translation; template translation; transfer learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Wearable Computers (ISWC), 2012 16th International Symposium on
Conference_Location :
Newcastle
ISSN :
1550-4816
Print_ISBN :
978-1-4673-1583-8
Type :
conf
DOI :
10.1109/ISWC.2012.17
Filename :
6246149
Link To Document :
بازگشت