Neural Network Based Data Fusion for Hand Pose Recognition with Multiple ToF Sensors

Abstract : We present a study on 3D based hand pose recognition us-ing 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 in-dividually for each class, and similarly by designing information-theoretic online measures for assessing confidences of decisions, we show that ap-propriately 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-01098697
Contributor : Alexander Gepperth <>
Submitted on : Sunday, December 28, 2014 - 3:45:04 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Monday, March 30, 2015 - 4:11:09 PM

File

kopinski2014neural.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Kopinski, Alexander Gepperth, Stefan Geisler, Uwe Handmann. Neural Network Based Data Fusion for Hand Pose Recognition with Multiple ToF Sensors. International Conference on Artificial Neural Networks (ICANN), Sep 2014, Hamburg, Germany. pp.233 - 240, ⟨10.1007/978-3-319-11179-7_30⟩. ⟨hal-01098697⟩

Share

Metrics

Record views

270

Files downloads

460