A 34Mu W Objectadaptive Cmos Image Sensor With Embedded Feature Extraction Algorithm For Motiontriggered Objectofinterest Imaging

• doi: 10.1109/JSSC.2013.2284350
• title: A 3.4-$\mu$ W Object-Adaptive CMOS Image Sensor With Embedded Feature Extraction Algorithm for Motion-Triggered Object-of-Interest Imaging
• publisher: IEEE
• isbn:
• issn: 1558-173X
• rank: 405
• access_type: LOCKED
• content_type: Journals
• abstract: We report a low-power object-adaptive CMOS imager, which suppresses spatial temporal bandwidth. The object-adaptive imager has embedded a feature extraction algorithm for identifying objects of interest. The sensor wakes up triggered by motion sensing and extracts features from the captured image for the detection of object-of-interest (OOI). Full-image capturing operation and image signal transmission are performed only when the interested objects are found, which significantly reduces power consumption at the sensor node. This motion-triggered OOI imaging significantly saves a spatial bandwidth more than 96.5% from the feature output and saves a temporal bandwidth from the motion-triggered wakeup and object adaptive imaging. The sensor consumes low power by employing a reconfigurable differential-pixel architecture with reduced power supply voltage and by implementing the feature extraction algorithm with mixed-signal circuitry in a small area. The chip operates at 0.22 μW/frame in motion-sensing mode and at 3.4 μW/frame for feature extraction, respectively. The object detection from on-chip feature extraction circuits has demonstrated a 94.5% detection rate for human from a set of 200 sample images.
• article_number: 6642143
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6642143
• html_url: https://ieeexplore.ieee.org/document/6642143/
• abstract_url: https://ieeexplore.ieee.org/document/6642143/
• publication_title: IEEE Journal of Solid-State Circuits
• conference_location:
• conference_dates:
• publication_number: 4
• is_number: 6690141
• publication_year: 2014
• publication_date: Jan. 2014
• start_page: 289
• end_page: 300
• citing_paper_count: 55
• citing_patent_count: 0
• download_count: 3181
• insert_date: 20131021
• index_terms:
  • ieee_terms:
    • Feature extraction
    • Imaging
    • Bandwidth
    • Power demand
    • Wireless sensor networks
    • Capacitors
  • author_terms:
    • CMOS image sensor
    • feature extraction
    • low power
    • motion detection
    • wireless sensor networks
  • dynamic_index_terms:
    • Image Sensor
    • Camera Sensor
    • Feature Extraction Algorithm
    • Power Consumption
    • Object Detection
    • Object Of Interest
    • Image Signal
    • Power Supply Voltage
    • Operation Mode
    • Block Size
    • Low Power Consumption
    • Image Capture
    • Wireless Sensor
    • Multiple Blocks
    • Scale-invariant Feature Transform
    • Pixel Array
    • Small Pixel
    • Order Memory
    • Pixel Pitch
    • Test Set Of Images
    • Wireless Sensor Nodes
    • Low-power Sensors
    • Reset Voltage
    • Voltage Scaling
    • Sign Bit
    • Different Modes Of Operation
    • Small Pixel Size
    • Digital Circuits
    • Digital Circuitry
    • Differential Amplifier
• authors:
  • Author Name: Jaehyuk Choi
    Affiliation: Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
    Author URL: https://ieeexplore.ieee.org/author/37066872300
    ID: 37066872300
    Order: 1
    Author Affiliations:
    • Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
  • Author Name: Seokjun Park
    Affiliation: Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
    Author URL: https://ieeexplore.ieee.org/author/38240901800
    ID: 38240901800
    Order: 2
    Author Affiliations:
    • Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
  • Author Name: Jihyun Cho
    Affiliation: Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
    Author URL: https://ieeexplore.ieee.org/author/38238016500
    ID: 38238016500
    Order: 3
    Author Affiliations:
    • Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
  • Author Name: Euisik Yoon
    Affiliation: Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA
    Author URL: https://ieeexplore.ieee.org/author/37275464600
    ID: 37275464600
    Order: 4
    Author Affiliations:
    • Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA

Image Sensor

• sensor_type: CMOS
• resolution: 256x256 pixels
• dynamic_range: Not specified
• pixel_size: 5.9 µm
• 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: 15 fps
• power_consumption: 0.22 W (motion sensing mode), 3.4 W (feature extraction mode)

Applications & Benefits

• cell_imaging: Included in biomedical applications such as endoscopy, microscopy, and retinal implants.
• benefits: Low-power operation from limited energy sources, high spatial resolution, and high temporal resolution.

Supporting Organizations

• supported_by: Samsung Advanced Institute of Technology, University of Michigan

Manuscript Details

• publication_date: Jan. 2014

Relevancy Score

• score: 10
• missing_fields:
  • dynamic_range
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • noise

Processed JSON Filename

request_2afcc304-958e-4c54-970f-d782620fc478-a_34mu_w_objectadaptive_cmos_image_sensor_with_embedded_feature_extraction_algorithm_for_motiontriggered_objectofinterest_imaging.json