A real-time applicable 3D gesture recognition system for automobile HMI

Abstract : We present a system for 3D hand gesture recog-nition based on 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. Our system fuses data coming from two ToF sensors which is used to build up a large database and subsequently train a multilayer perceptron (MLP). We demonstrate that we are able to reliably classify a set of ten hand gestures in real-time and describe the setup of the system, the utilised methods as well as possible application scenarios.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/hal-01098700
Contributor : Alexander Gepperth <>
Submitted on : Sunday, December 28, 2014 - 3:51:16 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Monday, March 30, 2015 - 4:15:11 PM

File

kopinski2014real.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Kopinski, Stefan Geisler, Louis-Charles Caron, Alexander Gepperth, Uwe Handmann. A real-time applicable 3D gesture recognition system for automobile HMI. IEEE International Conference On Intelligent Transportation Systems (ITSC), Oct 2014, Qingdao, China. pp.2616 - 2622, ⟨10.1109/ITSC.2014.6958109⟩. ⟨hal-01098700⟩

Share

Metrics

Record views

361

Files downloads

612