TU Darmstadt / ULB / TUbiblio

Exploring Machine Learning Object Classification for Interactive Proximity Surfaces

Braun, Andreas and Alekseew, Michael and Kuijper, Arjan (2016):
Exploring Machine Learning Object Classification for Interactive Proximity Surfaces.
In: Distributed, Ambient, and Pervasive Interactions, Springer International Publishing, Switzerland, In: 4th International Conference, DAPI 2016, Toronto, ON, Canada, July 17-22, 2016, In: Lecture Notes in Computer Science (LNCS); 9749, DOI: 10.1007/978-3-319-39862-4₁₅, [Conference or Workshop Item]

Abstract

Capacitive proximity sensors are a variety of the sensing technology that drives most finger-controlled touch screens today. However, they work over a larger distance. As they are not disturbed by non-conductive materials, they can be used to track hands above arbitrary surfaces, creating flexible interactive surfaces. Since the resolution is lower compared to many other sensing technologies, it is necessary to use sophisticated data processing methods for object recognition and tracking. In this work we explore machine learning methods for the detection and tracking of hands above an interactive surface created with capacitive proximity sensors. We discuss suitable methods and present our implementation based on Random Decision Forests. The system has been evaluated on a prototype interactive surface - the CapTap. Using a Kinect-based hand tracking system, we collect training data and compare the results of the learning algorithm to actual data.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Braun, Andreas and Alekseew, Michael and Kuijper, Arjan
Title: Exploring Machine Learning Object Classification for Interactive Proximity Surfaces
Language: English
Abstract:

Capacitive proximity sensors are a variety of the sensing technology that drives most finger-controlled touch screens today. However, they work over a larger distance. As they are not disturbed by non-conductive materials, they can be used to track hands above arbitrary surfaces, creating flexible interactive surfaces. Since the resolution is lower compared to many other sensing technologies, it is necessary to use sophisticated data processing methods for object recognition and tracking. In this work we explore machine learning methods for the detection and tracking of hands above an interactive surface created with capacitive proximity sensors. We discuss suitable methods and present our implementation based on Random Decision Forests. The system has been evaluated on a prototype interactive surface - the CapTap. Using a Kinect-based hand tracking system, we collect training data and compare the results of the learning algorithm to actual data.

Title of Book: Distributed, Ambient, and Pervasive Interactions
Series Name: Lecture Notes in Computer Science (LNCS); 9749
Publisher: Springer International Publishing, Switzerland
Uncontrolled Keywords: Guiding Theme: Smart City, Research Area: Human computer interaction (HCI), Interactive surfaces, Machine learning, Capacitive sensors, Proximity sensing
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 4th International Conference, DAPI 2016
Event Location: Toronto, ON, Canada
Event Dates: July 17-22, 2016
Date Deposited: 06 May 2019 07:22
DOI: 10.1007/978-3-319-39862-4₁₅
Export:

Optionen (nur für Redakteure)

View Item View Item