A Realtime Motionfeatureextraction Vlsi Employing Digitalpixelsensorbased Parallel Architecture

• doi: 10.1109/TCSVT.2014.2313899
• title: A Real-Time Motion-Feature-Extraction VLSI Employing Digital-Pixel-Sensor-Based Parallel Architecture
• publisher: IEEE
• isbn:
• issn: 1558-2205
• rank: 901
• access_type: OPEN_ACCESS
• content_type: Journals
• abstract: A very-large-scale integration capable of extracting motion features from moving images in real time has been developed employing row-parallel and pixel-parallel architectures based on the digital pixel sensor technology. Directional edge filtering of input images is carried out in row-parallel processing to minimize the chip real estate. To achieve a real-time response of the system, a fully pixel-parallel architecture has been explored in adaptive binarization of filtered images for essential feature extraction as well as in their temporal integration and derivative operations. As a result, self-speed-adaptive motion feature extraction has been established. The chip was designed and fabricated in a 65-nm CMOS technology and used to build an object detection system. Motion-sensitive target image localization was demonstrated as an illustrative example.
• article_number: 6778799
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6778799
• html_url: https://ieeexplore.ieee.org/document/6778799/
• abstract_url: https://ieeexplore.ieee.org/document/6778799/
• publication_title: IEEE Transactions on Circuits and Systems for Video Technology
• conference_location:
• conference_dates:
• publication_number: 76
• is_number: 6913590
• publication_year: 2014
• publication_date: Oct. 2014
• start_page: 1787
• end_page: 1799
• citing_paper_count: 10
• citing_patent_count: 0
• download_count: 4204
• insert_date: 20140326
• index_terms:
  • ieee_terms:
    • Image edge detection
    • Feature extraction
    • Very large scale integration
    • Image sensors
    • System-on-chip
  • author_terms:
    • Block-readout scheme
    • digital pixel sensor (DPS)
    • motion feature extraction (MFE)
    • parallel architecture
    • vision chip
  • dynamic_index_terms:
    • Parallelization
    • Parallel Computing
    • Directed Graph
    • Directed Edge
    • Motion Features
    • Motion Characteristics
    • Image Filtering
    • Temporal Integration
    • Edge Filter
    • Sensor Pixel
    • 65-nm CMOS
    • Image Processing
    • Imaging Data
    • Sequence Length
    • Image Recognition
    • Image Sensor
    • Camera Sensor
    • Motion Detection
    • Motion Sensors
    • Primary Visual Cortex
    • Primary Visual Cortices
    • Still Images
    • Gradient Values
    • Image Processing Algorithms
    • Clock Cycles
    • Digital Circuits
    • Digital Circuitry
    • Static Random Access Memory
    • Motion Recognition
    • Local Feature Extraction
    • High-speed System
    • Global Feature Extraction
    • Image Processing System
    • Processing Circuit
    • Pixel Data
    • Data For Each Pixel
    • Filter Kernel
    • Video Surveillance
• authors:
  • Author Name: Hongbo Zhu
    Affiliation: VLSI Design and Education Center, University of Tokyo, Tokyo, Japan
    Author URL: https://ieeexplore.ieee.org/author/37534140300
    ID: 37534140300
    Order: 1
    Author Affiliations:
    • VLSI Design and Education Center, University of Tokyo, Tokyo, Japan
  • Author Name: Tadashi Shibata
    Affiliation: Japan Society of Applied Physics, Center for Innovative Integrated Systems, Tohoku University, Sendai, Japan
    Author URL: https://ieeexplore.ieee.org/author/37278610500
    ID: 37278610500
    Order: 2
    Author Affiliations:
    • Japan Society of Applied Physics, Center for Innovative Integrated Systems, Tohoku University, Sendai, Japan
    • Institute of Space and Astronautical Science, Japan Aerospace Exploration Agency, Tokyo, Japan

Image Sensor

• sensor_type: Digital Pixel Sensor (DPS)
• resolution: 100x100
• 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
• power_consumption: 9 mW

Applications & Benefits

• cell_imaging: Multi-object recognition and motion feature extraction for various applications such as automotive systems, video surveillance, and human-computer interaction.
• benefits: Real-time motion feature extraction, adaptive processing for speeds, low power consumption, compact implementation on-chip.

Supporting Organizations

• supported_by: VLSI Design and Education Center, University of Tokyo; STARC; e-Shuttle Inc.; Fujitsu Ltd.; Synopsys, Inc.; Cadence Design Systems, Inc.; Mentor Graphics, Inc.

Manuscript Details

• publication_date: Oct. 2014

Relevancy Score

• score: 10
• missing_fields:
  • fill factor
  • quantum efficiency
  • readout speed
  • noise sources
  • analog-to-digital conversion techniques
  • microlenses
  • on-chip colour filters
  • global or rolling shutters
  • backside illumination

Processed JSON Filename

request_39036444-f46f-41b0-b26a-37c2cc603c15-a_realtime_motionfeatureextraction_vlsi_employing_digitalpixelsensorbased_parallel_architecture.json