A Novel Stereovision Architecture For Realtime Obstacle Detection

• doi: 10.1109/ICAPP.1995.472210
• title: A novel stereovision architecture for real-time obstacle detection
• publisher: IEEE
• isbn: 0-7803-2018-2
• issn:
• rank: 1227
• access_type: LOCKED
• content_type: Conferences
• abstract: This paper presents a novel stereo architecture to implement a stereovision algorithm suited to obstacle detection and collision avoidance applications in real-time environments. The algorithm is derived from the spatio-frequency analysis proposed by Marr and Poggio (1979), with the matching primitives resulting from a local extremum extraction in the band-pass filtered stereopair images. A VLSI implementation is motivated both by the high processing speed required in such a real-time content and by the simplicity and regularity of the algorithm. We have therefore designed a retina-like architecture, with an in-line parallel processing unit interfaced with an on-chip photodiode matrix sensor. This stereo retina system has been succesfully simulated with real scenes images taken from a running car on a highway. A 128-pixel line CMOS retina has been designed and fabricated. First-hand experiments are positive.<>
• article_number: 472210
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=472210
• html_url: https://ieeexplore.ieee.org/document/472210/
• abstract_url: https://ieeexplore.ieee.org/document/472210/
• publication_title: Proceedings 1st International Conference on Algorithms and Architectures for Parallel Processing
• conference_location: Brisbane, QLD, Australia
• conference_dates: 19-21 April 1995
• publication_number: 3315
• is_number: 9947
• publication_year: 1995
• publication_date: 19-21 April 1995
• start_page: 395
• end_page: 403 vol.1
• citing_paper_count: 1
• citing_patent_count: 0
• download_count: 48
• insert_date: 20020806
• index_terms:
  • ieee_terms:
    • Retina
    • Collision avoidance
    • Image analysis
    • Algorithm design and analysis
    • Band pass filters
    • Matched filters
    • Very large scale integration
    • Parallel processing
    • Photodiodes
    • Layout
  • dynamic_index_terms:
    • High Speed
    • Highway
    • Freeway
    • Motorway
    • Stereopsis
    • Stereoscopic Vision
    • Stereovision
    • Local Extrema
    • Real-time Environment
    • Visual Features
    • Visual Characteristics
    • Localization Performance
    • Local Operators
    • Positive Performance
    • Gaussian Filter
    • Image Sensor
    • Camera Sensor
    • Object Size
    • Amount Of Computation
    • Amount Of Calculation
    • Matching Process
    • Left Image
    • Stereo Pairs
    • Disparity Map
    • Capacitance Ratio
• isbn_formats:
  • format: Print ISBN, value: 0-7803-2018-2, isbnType: Historical
• authors:
  • Author Name: B. Arion
    Affiliation: EPH-CAO, Institut National Télécommunications, Evry, France
    Author URL: https://ieeexplore.ieee.org/author/37353736400
    ID: 37353736400
    Order: 1
    Author Affiliations:
    • EPH-CAO, Institut National Télécommunications, Evry, France
  • Author Name: Yang Ni
    Affiliation: EPH-CAO, Institut National Télécommunications, Evry, France
    Author URL: https://ieeexplore.ieee.org/author/37087354104
    ID: 37087354104
    Order: 2
    Author Affiliations:
    • EPH-CAO, Institut National Télécommunications, Evry, France
  • Author Name: F. Devos
    Affiliation: Institut dElecrronique Fondamentale, Université Paris Sud, Orsay, France
    Author URL: https://ieeexplore.ieee.org/author/37353735800
    ID: 37353735800
    Order: 3
    Author Affiliations:
    • Institut dElecrronique Fondamentale, Université Paris Sud, Orsay, France

Image Sensor

• sensor_type: CMOS
• resolution: 128 pixels
• 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

Applications & Benefits

• cell_imaging: Not specified
• benefits: Real-time obstacle detection and collision avoidance in automotive systems.

Supporting Organizations

• supported_by: GIE PSA Peugeot Citroen

Manuscript Details

• publication_date: 19-21 April 1995

Relevancy Score

• score: 8
• missing_fields:
  • dynamic_range
  • pixel_size
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • frame_rate
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • power_consumption
  • noise
  • cell_imaging
  • benefits
  • publication_date

Processed JSON Filename

request_5b4f9cd0-ff3f-4a7e-a083-2b07e5398238-a_novel_stereovision_architecture_for_realtime_obstacle_detection.json