A Smart Camera For Multimodal Human Computer Interaction

• doi: 10.1109/ISCE.2006.1689443
• title: A Smart Camera for Multimodal Human Computer Interaction
• publisher: IEEE
• isbn: 1-4244-0216-6
• issn: 2159-1423
• rank: 924
• access_type: LOCKED
• content_type: Conferences
• abstract: A smart camera is an embedded vision system which, in addition to image capture, performs image analysis and pattern recognition to provide as output a high-level understanding of the imaged scene. Smart cameras are essential components to build active and automated control systems for many applications, such as surveillance, machine vision, and interactive visualization systems. The heart of smart camera is the intelligent image processing algorithms that turn raw data into knowledge. The design of smart camera is challenging because on one hand video processing has insatiable demand for performance and power, and on the other hand embedded systems place considerable constraints on the design. In this paper we firstly present an overview of smart camera technologies and the process to design smart cameras as embedded systems. We then present the design and implementation of a smart camera, called GestureCam, which can recognize simple hand and head gestures. The camera uses a CMOS image sensor as capture front-end, and the image processing and gesture recognition is completely built on a single FPGA device. The experimental results have shown it to be robust with enough performance to meet real-time constraints. We plan to use the GestureCam to build next generation of natural multimodal human computer interfaces.
• article_number: 1689443
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1689443
• html_url: https://ieeexplore.ieee.org/document/1689443/
• abstract_url: https://ieeexplore.ieee.org/document/1689443/
• publication_title: 2006 IEEE International Symposium on Consumer Electronics
• conference_location: St. Petersburg, Russia
• conference_dates: 28 June-1 July 2006
• publication_number: 11112
• is_number: 35627
• publication_year: 2006
• publication_date: 28 June-1 July 2006
• start_page: 1
• end_page: 6
• citing_paper_count: 3
• citing_patent_count: 3
• download_count: 474
• insert_date: 20060911
• index_terms:
  • ieee_terms:
    • Smart cameras
    • Human computer interaction
    • Machine vision
    • Image processing
    • Embedded system
    • CMOS image sensors
    • Image analysis
    • Pattern recognition
    • Layout
    • Automatic control
  • author_terms:
    • Human Computer Interface
    • Computer Vision
    • Smart Cameras
    • Embedded System
  • dynamic_index_terms:
    • Human-computer Interaction
    • User Interaction
    • Smart Cameras
    • Image Processing
    • Visual System
    • Image Sensor
    • Camera Sensor
    • Image Capture
    • Machine Vision
    • Visual Navigation
    • Hand Gestures
    • Gesture Recognition
    • Automatic Control System
    • Low-pass
    • Low-pass Filter
    • Hidden Markov Model
    • Skin Color
    • Complexion
    • Skin Tone
    • Processing Tasks
    • Algorithm Design
    • Motion Detection
    • Motion Sensors
    • Hardware Architecture
    • Digital Output
    • RGB Color Space
    • Commercial Camera
    • Heading Angle
    • Gesture Classification
    • Image Moments
    • Moment Invariants
    • Frame Grabber
    • Host PC
    • Video Output
    • Tracing Algorithm
    • Current Pixel
    • Raw Video
• isbn_formats:
  • format: Print ISBN, value: 1-4244-0216-6, isbnType: Historical
• authors:
  • Author Name: Yu Shi
    Affiliation: Australian Technology Park, NICTA, Eveleigh, NSW, Australia
    Author URL: https://ieeexplore.ieee.org/author/37087347757
    ID: 37087347757
    Order: 1
    Author Affiliations:
    • Australian Technology Park, NICTA, Eveleigh, NSW, Australia
  • Author Name: P. Raniga
    Affiliation: University of Sydney, Darlington, NSW, Australia
    Author URL: https://ieeexplore.ieee.org/author/37294456700
    ID: 37294456700
    Order: 2
    Author Affiliations:
    • University of Sydney, Darlington, NSW, Australia
  • Author Name: I. Mohamed
    Affiliation: University of Queensland, Brisbane, QLD, Australia
    Author URL: https://ieeexplore.ieee.org/author/38055865000
    ID: 38055865000
    Order: 3
    Author Affiliations:
    • University of Queensland, Brisbane, QLD, Australia

Image Sensor

• sensor_type: CMOS
• resolution: SXGA (1280x1024) at 15 fps, VGA (640x480) at 30 fps
• dynamic_range: Not specified
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

• frame_rate: 15 fps (SXGA), 30 fps (VGA)

Applications & Benefits

• cell_imaging: Not specified
• benefits: Enables gesture recognition in multimodal human-computer interaction.

Supporting Organizations

• supported_by: Not specified

Manuscript Details

• publication_date: 28 June-1 July 2006

Relevancy Score

• score: 8
• missing_fields:
  • fill factor
  • quantum efficiency
  • readout speed
  • noise sources

Processed JSON Filename

request_1e4ff0c4-f461-4fca-9288-ca54d53cfee8-a_smart_camera_for_multimodal_human_computer_interaction.json