Paper Info
Title
A single sensor NIR depth camera for gesture control
Abstract
There is a large amount of sustained research activity in the area of Human-Computer Interaction (HCI). Gesture control is one of hottest in this field. Although gesture control research began with terminals attached to computers in combination with a pointing device, the large scale implementation and utilization of gesture control continues to be infeasible today. As machine vision, image processing, and artificial intelligence algorithms are error prone, gestures will never be interpreted in the same way for all instances of the gesture's appearance, especially due to changes of the ambient light. This latter condition led to the use of near infrared (NIR) illumination such that the recorded scene is not affected by light variations. Since the posture of a gesture may require the processing of overlapping features, reliability is greatly improved through the use of images that contain a third dimension. In this paper, a smart and real-time depth camera based on a new depth generation principle is introduced. A monotonic increasing and decreasing function is used to control the frequency and duty-cycle of the NIR illumination pulses. The adjusted light pulses reflect off of the object of interest and are captured as a series of images. A reconfigurable hardware architecture calculates the depth-map of the visible face of the object in real-time from a number of images. The final depth map is then used for gesture detection, tracking and recognition. A series of tests and measurements will explain how the camera builds the depth map and how it can operate in both near and far ranges. Results on controlling video game consoles and Smart TVs using the above camera will be given.
Year
DOI
Venue
2014
10.1109/I2MTC.2014.6861016
Instrumentation and Measurement Technology Conference
Keywords
Field
DocType
cameras,frequency control,gesture recognition,infrared detectors,infrared imaging,lighting,sampled data systems,hci,nir illumination pulse control,artificial intelligence algorithm,depth generation principle,duty-cycle control,gesture control,gesture detection,gesture tracking,human-computer interaction,image processing,light pulse adjustment,machine vision,near infrared illumination,overlapping feature processing,reconfigurable hardware architecture,reliability,single sensor nir depth camera,smart tv,video game console control,digital television systems,human computer interfaces,real-time 3d camera technology,video game consoles,games,tv,human computer interaction,real time systems
Computer vision,Reconfigurable hardware architecture,Machine vision,Computer graphics (images),Computer science,Gesture,Image processing,Gesture recognition,Pointing device,Artificial intelligence,Depth map
Conference
Citations 
PageRank 
References 
0
0.34
7
Authors
7
Name
Order
Citations
PageRank
Dan Ionescu1377.58
viorel suse230.86
Cristian Gadea3378.40
Bogdan Solomon4476.54
bogdan ionescu501.35
shariful islam641.55
Marius D. Cordea7203.76