Ai Driven Wide Dynamic Range Cmos Image Sensor

• doi: 10.1109/AICAS54282.2022.9870003
• title: AI driven Wide Dynamic Range CMOS Image Sensor
• publisher: IEEE
• isbn: 978-1-6654-0997-1
• issn:
• rank: 1356
• access_type: LOCKED
• content_type: Conferences
• abstract: This work proposes the implementation of a wide dynamic range CMOS image sensors using on-chip DNN. A given pixel is read in the linear mode under low light illumination and in logarithmic mode under high light where the mode of operation of pixel is decided using comparator. The compressive nature of logarithmic pixel is leveraged using amplifier to enhance the dynamic range. To further enhance the dynamic range, three hardware efficient DNN models, SiDCNet, SiDCNet (inr.) and SiDCNet (fire), are implemented and compared. On an average, the PSNR and SSIM of 31.17 dB and 0.95, respectively, is observed on standard test images. A comparison between post DNN inference is drawn with the linear-logarithmic acquisition, resulting an increase in image quality of 8.5 dB and 0.14 in terms of PSNR and SSIM.
• article_number: 9870003
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9870003
• html_url: https://ieeexplore.ieee.org/document/9870003/
• abstract_url: https://ieeexplore.ieee.org/document/9870003/
• publication_title: 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
• conference_location: Incheon, Korea, Republic of
• conference_dates: 13-15 June 2022
• publication_number: 9869844
• is_number: 9869845
• publication_year: 2022
• publication_date: 13-15 June 2022
• start_page: 366
• end_page: 370
• citing_paper_count: 0
• citing_patent_count: 0
• download_count: 507
• insert_date: 20220905
• index_terms:
  • ieee_terms:
    • Image quality
    • Semiconductor device modeling
    • Neural networks
    • Dynamic range
    • CMOS image sensors
    • Hardware
    • System-on-chip
  • author_terms:
    • Linear-Logarithmic (Lin-Log) Pixel
    • High Dy-namic Range
    • CMOS Image Sensor
    • Re-configurable Readout
    • Deep Learning
    • Convolutional Neural Networks
  • dynamic_index_terms:
    • Dynamic Range
    • Image Sensor
    • Camera Sensor
    • Image Quality
    • Deep Neural Network
    • Operation Mode
    • High Light
    • High Light Intensity
    • Low Light
    • Standard Imaging
    • Linear Mode
    • Linear Transition
    • Deep Neural Network Model
    • Low Illumination
    • Light Intensity
    • Aspect Ratio
    • Photodiode
    • Charge Carriers
    • Single Exposure
    • High Light Conditions
    • CMOS Process
    • Hardware Accelerators
    • Hardware-accelerated
    • Conversion Gain
• isbn_formats:
  • format: Print on Demand(PoD) ISBN, value: 978-1-6654-0997-1, isbnType: New-2005
  • format: Electronic ISBN, value: 978-1-6654-0996-4, isbnType: New-2005
• authors:
  • Author Name: Wilfred Kisku
    Affiliation: Department of Electrical Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
    Author URL: https://ieeexplore.ieee.org/author/37088896069
    ID: 37088896069
    Order: 1
    Author Affiliations:
    • Department of Electrical Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
  • Author Name: Mohit Bhushan
    Affiliation: Department of Electrical Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
    Author URL: https://ieeexplore.ieee.org/author/37089516592
    ID: 37089516592
    Order: 2
    Author Affiliations:
    • Department of Electrical Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
  • Author Name: Amandeep Kaur
    Affiliation: Department of Electrical Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
    Author URL: https://ieeexplore.ieee.org/author/37085856535
    ID: 37085856535
    Order: 3
    Author Affiliations:
    • Department of Electrical Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
  • Author Name: Deepak Mishra
    Affiliation: Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India
    Author URL: https://ieeexplore.ieee.org/author/37085433827
    ID: 37085433827
    Order: 4
    Author Affiliations:
    • Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, India

Image Sensor

• sensor_type: CMOS
• resolution: 128x128
• dynamic_range: 142dB
• 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: Includes applications such as surveillance, healthcare, and wildlife monitoring.
• benefits: Low power consumption, technology scaling advantages, and ability to operate in conditions with varying illumination.

Supporting Organizations

• supported_by: Indian Institute of Technology Jodhpur

Manuscript Details

• publication_date: 13-15 June 2022

Relevancy Score

• score: 10
• missing_fields:
  • pixel_size
  • fill_factor
  • quantum_efficiency
  • dark_current
  • signal_to_noise_ratio
  • power_consumption
  • frame_rate
  • sensitivity
  • shutter_speed
  • noise

Processed JSON Filename

request_75efbf2a-514c-4504-af3b-780d02baab53-ai_driven_wide_dynamic_range_cmos_image_sensor.json