TY  - CHAP
U1  - Buchbeitrag
A1  - Kopinski, Thomas
A1  - Gepperth, Alexander
A1  - Handmann, Uwe
A1  - Geisler, Stefan
T1  - Neural Network Based Data Fusion for Hand Pose Recognition with Multiple ToF Sensors
T2  - Artificial Neural Networks and Machine Learning – ICANN 2014
N2  - We present a study on 3D based hand pose recognition using a new generation of low-cost time-of-flight(ToF) sensors intended for outdoor use in automotive human-machine interaction. As signal quality is impaired compared to Kinect-type sensors, we study several ways to improve performance when a large number of gesture classes is involved. We investigate the performance of different 3D descriptors, as well as the fusion of two ToF sensor streams. By basing a data fusion strategy on the fact that multilayer perceptrons can produce normalized confidences individually for each class, and similarly by designing information-theoretic online measures for assessing confidences of decisions, we show that appropriately chosen fusion strategies can improve overall performance to a very satisfactory level. Real-time capability is retained as the used 3D descriptors, the fusion strategy as well as the online confidence measures are computationally efficient.
Y1  - 2014
UR  - http://www.handmann.net/pdf/ICANN-KopHanEtAl2014.pdf
UR  - https://link.springer.com/chapter/10.1007/978-3-319-11179-7_30
UR  - https://hal.inria.fr/hal-01098697/document
SN  - 978-3-319-11179-7
SB  - 978-3-319-11179-7
U6  - https://doi.org/10.1007/978-3-319-11179-7_30
DO  - https://doi.org/10.1007/978-3-319-11179-7_30
IS  - vol 8681
SP  - 233
EP  - 240
S1  - 8
PB  - Springer
ER  -