A Smart Image Sensor With Attention Modules

• doi: 10.1109/CAMP.2005.7
• title: A smart image sensor with attention modules
• publisher: IEEE
• isbn: 0-7695-2255-6
• issn:
• rank: 1301
• access_type: LOCKED
• content_type: Conferences
• abstract: In this paper, a CMOS digital image sensor, which consists of A/D conversion, motion estimation circuits, and attention modules for ROI (region of interest) perception is presented. The functions of A/D conversion and motion estimation are implemented by 0.6 m CMOS processing circuit on chip, and attention modules are implemented off the chip as software currently. Attention modules are taken to improve limited applications of the smart image sensor. If the attention module is integrated on a smart sensor, we can use this sensor for tracking some regions of interest without outputting all pixels. The current smart image sensor responses to the changes of intensity, and uses the integration time to estimate motion. To make up for inherent property of the sensor from circuit design and extend its applications we decide to introduce some perceptive solutions to the image sensor. Attention modules for still and moving images are employed to achieve such purposes. The suggested approach also makes the smart image sensor initiate perceptive functions for such cases that motion estimation or intensity changes are not observed. Experimental results present the possibility that the smart image sensor can extract ROIs and use them when it selectively outputs pixels.
• article_number: 1508163
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1508163
• html_url: https://ieeexplore.ieee.org/document/1508163/
• abstract_url: https://ieeexplore.ieee.org/document/1508163/
• publication_title: Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05)
• conference_location: Palermo, Italy
• conference_dates: 4-6 July 2005
• publication_number: 10078
• is_number: 32311
• publication_year: 2005
• publication_date: 4-6 July 2005
• start_page: 46
• end_page: 51
• citing_paper_count: 5
• citing_patent_count: 0
• download_count: 308
• insert_date: 20050919
• index_terms:
  • ieee_terms:
    • Image sensors
    • Intelligent sensors
    • Motion estimation
    • CMOS image sensors
    • Image converters
    • Smart pixels
    • CMOS digital integrated circuits
    • Digital images
    • CMOS process
    • Application software
  • dynamic_index_terms:
    • Image Sensor
    • Camera Sensor
    • Attention Module
    • Sensor Applications
    • Circuit Design
    • Current Image
    • Motion Estimation
    • Smart Sensors
    • Processing Circuit
    • Digital Sensor
    • Motion Intensity
    • Region Of Interest Extraction
    • Feature Maps
    • Grayscale Images
    • Greyscale Images
    • Visual Attention
    • Photodiode Array
    • Visual Model
    • Feature Integration
    • Visual Map
    • Early Features
    • Early Characteristics
    • Saliency Map
    • Converter Circuit
    • A-priori Knowledge
    • Value Of Bit
    • Value Of Each Bit
    • Internal Part
    • Attention Model
    • Pixel Information
    • Information Of Each Pixel
    • Feature Extraction Part
• isbn_formats:
  • format: Print ISBN, value: 0-7695-2255-6, isbnType: Historical
• authors:
  • Author Name: Min Chul Park
    Affiliation: Systems Technology Division, Korea Institute of Science and Technology, South Korea
    Author URL: https://ieeexplore.ieee.org/author/37087186178
    ID: 37087186178
    Order: 1
    Author Affiliations:
    • Systems Technology Division, Korea Institute of Science and Technology, South Korea
    • Systems Technology Division, Korea Institute of Science
  • Author Name: Kyung Joo Cheoi
    Affiliation: LG CNS Co., Ltd
    Author URL: https://ieeexplore.ieee.org/author/37087808318
    ID: 37087808318
    Order: 2
    Author Affiliations:
    • LG CNS Co., Ltd
    • LG CNS Co., Ltd
  • Author Name: T. Harnarnoto
    Affiliation:
    Author URL: https://ieeexplore.ieee.org/author/37087808944
    ID: 37087808944
    Order: 3
    

Image Sensor

• sensor_type: CMOS digital image sensor
• resolution: 64x64 pixels
• dynamic_range: Not specified
• pixel_size: 40x40 µm
• 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: The sensor can be used in intelligent image processing for various applications including tracking regions of interest without outputting all pixels, thus enhancing image coding efficiency.
• benefits: The integration of attention modules allows for perceptive functions and improved tracking capabilities.

Supporting Organizations

• supported_by: Korea Institute of Science, LG CNS Co., Ltd, Tokyo University of Science

Manuscript Details

• publication_date: 4-6 July 2005

Relevancy Score

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

Processed JSON Filename

request_fb84ea0c-9fe5-49b4-8cc5-60e1af25f0fc-a_smart_image_sensor_with_attention_modules.json