A 1000 Framess Vision Chip Using Scalable Pixelneighborhoodlevel Parallel Processing

• doi: 10.1109/JSSC.2016.2613094
• title: A 1000 frames/s Vision Chip Using Scalable Pixel-Neighborhood-Level Parallel Processing
• publisher: IEEE
• isbn:
• issn: 1558-173X
• rank: 260
• access_type: LOCKED
• content_type: Journals
• abstract: This paper presents a novel vision chip architecture based on pixel-neighborhood-level parallel processing. In the architecture, an 8-b RISC processing core is embedded in an 8×8 array of digital pixel sensors on the same focal plane. These neighborhood processors (NPs) are tiled in a 2-D array to form the final imager resolution. Program execution is carried out in parallel across the array of pixel-neighborhood processing cores, allowing for direct scalability in terms of resolution, without reduction in processing speed or frame rate. To accomplish this, a compact, low-complexity NP architecture along with a general purpose, 8-b instruction set has been designed and implemented. A prototype vision chip containing an 8×10 array of NPs with a 64×80 resolution has been designed and fabricated in a 0.13-μm 1P8M CMOS fabrication process. The system is reprogrammable and can perform a wide range of image and video processing tasks. Several example algorithms are implemented and tested on the single-chip vision system to demonstrate the functionality of pixel-neighborhood-level parallelism, including 1000-frames/s object tracking.
• article_number: 7589062
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7589062
• html_url: https://ieeexplore.ieee.org/document/7589062/
• abstract_url: https://ieeexplore.ieee.org/document/7589062/
• publication_title: IEEE Journal of Solid-State Circuits
• conference_location:
• conference_dates:
• publication_number: 4
• is_number: 7845730
• publication_year: 2017
• publication_date: Feb. 2017
• start_page: 556
• end_page: 568
• citing_paper_count: 28
• citing_patent_count: 0
• download_count: 1291
• insert_date: 20161012
• index_terms:
  • ieee_terms:
    • Program processors
    • Image resolution
    • Parallel processing
    • Arrays
    • Delays
    • Memory management
  • author_terms:
    • CMOS image sensor
    • image processing
    • neighborhood processor (NP)
    • object tracking
    • programmable
    • single instruction multiple data
    • vision chip
  • dynamic_index_terms:
    • Scalable
    • Vision Chips
    • Image Processing
    • Processing Speed
    • Psychomotor Speed
    • Educational Settings
    • Set Of Instructions
    • Frame Rate
    • Focal Plane
    • Back Focal Plane
    • Processing Tasks
    • Program Execution
    • Image Processing Tasks
    • Digital Sensor
    • Integration Time
    • Level Of Processing
    • Digital Signal
    • Static Images
    • Edge Detection
    • Median Filter
    • Global Signal
    • Data Frame
    • Fill Factor
    • Local Memory
    • Outdoor Scenes
    • Reset Voltage
    • Conditional Branches
    • Nearby Pixels
    • Data Bus
    • Clock Cycles
    • Additional Row
    • Pixel Data
    • Data For Each Pixel
    • Neighborhood Size
• authors:
  • Author Name: Joseph A. Schmitz
    Affiliation: Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
    Author URL: https://ieeexplore.ieee.org/author/37085406015
    ID: 37085406015
    Order: 1
    Author Affiliations:
    • Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
  • Author Name: Mahir K. Gharzai
    Affiliation: Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
    Author URL: https://ieeexplore.ieee.org/author/37085423892
    ID: 37085423892
    Order: 2
    Author Affiliations:
    • Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
  • Author Name: Sina Balkır
    Affiliation: Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
    Author URL: https://ieeexplore.ieee.org/author/37269491000
    ID: 37269491000
    Order: 3
    Author Affiliations:
    • Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
  • Author Name: Michael W. Hoffman
    Affiliation: Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
    Author URL: https://ieeexplore.ieee.org/author/37269479800
    ID: 37269479800
    Order: 4
    Author Affiliations:
    • Department of Electrical and Computer Engineering, University of Nebraska–Lincoln, Lincoln, NE, USA
  • Author Name: Daniel J. White
    Affiliation: Gellersen Center, Valparaiso University, Valparaiso, IN, USA
    Author URL: https://ieeexplore.ieee.org/author/38468485200
    ID: 38468485200
    Order: 5
    Author Affiliations:
    • Gellersen Center, Valparaiso University, Valparaiso, IN, USA
  • Author Name: Nathan Schemm
    Affiliation: Texas Instruments Inc, Dallas, TX, USA
    Author URL: https://ieeexplore.ieee.org/author/37398759700
    ID: 37398759700
    Order: 6
    Author Affiliations:
    • Texas Instruments Inc, Dallas, TX, USA

Image Sensor

• sensor_type: CMOS
• resolution: 64×80 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

• frame_rate: 1000 fps
• noise: 1.1% FPN (fixed-pattern noise)

Applications & Benefits

• cell_imaging: Supporting various imaging applications including outdoor tracking in natural lighting
• benefits: Reprogrammable vision chip with capabilities for real-time target tracking at high speeds.

Supporting Organizations

• supported_by: MOSIS High Education Program, NASA Nebraska Space Grant Consortium

Manuscript Details

• publication_date: Feb. 2017

Relevancy Score

• score: 9
• missing_fields:
  • dynamic_range
  • dark_current
  • quantum_efficiency
  • pixel_size
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • power_consumption
  • noise

Processed JSON Filename

request_1b3718c9-e975-4d23-a688-ff0624385f37-a_1000_framess_vision_chip_using_scalable_pixelneighborhoodlevel_parallel_processing.json