Selfputing A 057 W 15 Fps Vision Chip With Selfpowered Inpixel Computing And Inmemory Computing For Visual Perception On The Edge

• doi: 10.1109/ESSERC62670.2024.10719556
• title: Selfputing: A 0.57 μW @ 15 fps Vision Chip with Self-powered In-Pixel Computing and In-Memory Computing for Visual Perception on the Edge
• publisher: IEEE
• isbn: 979-8-3503-8814-5
• issn: 1930-8833
• rank: 3510
• access_type: LOCKED
• content_type: Conferences
• abstract: This paper presents an intelligent vision chip featuring self-powered in-pixel computing and in-memory computing (Selfputing) for distributed vision sensor nodes. The sensed light signal is processed with computing-in-pixel (CIP) scheme in the pixel array utilizing light-induced photocurrent to extract convolutional features. The output of CIP array is processed by SRAM-based charge-domain computing-in-memory (CIM) array to derive the image classification result. A power-managementunit driven by energy-harvesting photovoltaic (PV) cell is designed to power the CIP and CIM array. The Selfputing chip is fabricated in 180 nm CMOS process and consumes $0.57 \mu \mathrm{~W}$ power at a frame rate of 15 fps with 95.1% accuracy on MNIST dataset, achieving self-powered operation when driven by a PV cell with $1.26 \mu \mathrm{~W}$ harvesting power.
• article_number: 10719556
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10719556
• html_url: https://ieeexplore.ieee.org/document/10719556/
• abstract_url: https://ieeexplore.ieee.org/document/10719556/
• publication_title: 2024 IEEE European Solid-State Electronics Research Conference (ESSERC)
• conference_location: Bruges, Belgium
• conference_dates: 9-12 Sept. 2024
• publication_number: 10719398
• is_number: 10719399
• publication_year: 2024
• publication_date: 9-12 Sept. 2024
• start_page: 585
• end_page: 588
• citing_paper_count: 0
• citing_patent_count: 0
• download_count: 381
• insert_date: 20241023
• index_terms:
  • ieee_terms:
    • Accuracy
    • Array signal processing
    • Microprocessors
    • Power system management
    • Prototypes
    • Computer architecture
    • Vision sensors
    • In-memory computing
    • Feature extraction
    • Visual perception
  • author_terms:
    • Near-zero-power perception
    • energy harvesting
    • processing-in-sensor
    • computing-in-pixel
    • computing-in-memory
  • dynamic_index_terms:
    • Visual Perception
    • Computational Memory
    • Compute-in-memory
    • In-memory Computing
    • Vision Chips
    • Image Classification
    • Solar Cells
    • Photocurrent
    • MNIST Dataset
    • CMOS Process
    • Pixel Array
    • Neural Network
    • Horizontal Plane
    • Horizontal Direction
    • Horizontal Distance
    • Focal Plane
    • Back Focal Plane
    • Adaptive Control
    • Convolution Kernel
    • Image Sensor
    • Camera Sensor
    • Physical World
    • Neural Network Layers
    • Cell Voltage
    • Circuit Implementation
    • Processing Circuit
    • Neural Network Approximation
    • Neural Network Computations
    • Neural Network Estimation
    • 1st Layer
    • Energy Harvesting System
    • Charge Pump
    • Harvest Light Energy
    • Field Of Perception
    • Power Overhead
• isbn_formats:
  • format: Print on Demand(PoD) ISBN, value: 979-8-3503-8814-5, isbnType: New-2005
  • format: USB ISBN, value: 979-8-3503-8812-1, isbnType: New-2005
  • format: Electronic ISBN, value: 979-8-3503-8813-8, isbnType: New-2005
• authors:
  • Author Name: Maimaiti Nazhamaiti
    Affiliation: Tsinghua University, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37088525986
    ID: 37088525986
    Order: 1
    Author Affiliations:
    • Tsinghua University, Beijing, China
  • Author Name: Weihuang Jiang
    Affiliation: Tsinghua University, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/432385960328497
    ID: 432385960328497
    Order: 2
    Author Affiliations:
    • Tsinghua University, Beijing, China
  • Author Name: Haijin Su
    Affiliation: Beijing Jiaotong University, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/109666939357085
    ID: 109666939357085
    Order: 3
    Author Affiliations:
    • Beijing Jiaotong University, Beijing, China
  • Author Name: Xin Hong
    Affiliation: Jinan University, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37593877900
    ID: 37593877900
    Order: 4
    Author Affiliations:
    • Jinan University, Guangzhou, China
  • Author Name: Xiangjun Wang
    Affiliation: Henan University of Science and Technology, Luoyang, China
    Author URL: https://ieeexplore.ieee.org/author/38667935000
    ID: 38667935000
    Order: 5
    Author Affiliations:
    • Henan University of Science and Technology, Luoyang, China
  • Author Name: Yutong Li
    Affiliation: University of Chinese Academy of Sciences, Hangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37088701351
    ID: 37088701351
    Order: 6
    Author Affiliations:
    • University of Chinese Academy of Sciences, Hangzhou, China
  • Author Name: Li Luo
    Affiliation: Beijing Jiaotong University, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37087182945
    ID: 37087182945
    Order: 7
    Author Affiliations:
    • Beijing Jiaotong University, Beijing, China
  • Author Name: Junkai Huang
    Affiliation: Jinan University, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37539965800
    ID: 37539965800
    Order: 8
    Author Affiliations:
    • Jinan University, Guangzhou, China
  • Author Name: Bo Liu
    Affiliation: Henan University of Science and Technology, Luoyang, China
    Author URL: https://ieeexplore.ieee.org/author/37090044793
    ID: 37090044793
    Order: 9
    Author Affiliations:
    • Henan University of Science and Technology, Luoyang, China
  • Author Name: Jinshui Miao
    Affiliation: University of Chinese Academy of Sciences, Hangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089389036
    ID: 37089389036
    Order: 10
    Author Affiliations:
    • University of Chinese Academy of Sciences, Hangzhou, China
  • Author Name: Qi Wei
    Affiliation: Tsinghua University, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37582779500
    ID: 37582779500
    Order: 11
    Author Affiliations:
    • Tsinghua University, Beijing, China
  • Author Name: Fei Qiao
    Affiliation: Tsinghua University, Beijing, China
    Author URL: https://ieeexplore.ieee.org/author/37088482515
    ID: 37088482515
    Order: 12
    Author Affiliations:
    • Tsinghua University, Beijing, China

Image Sensor

• sensor_type: CMOS
• resolution: 32x32
• dynamic_range: Not specified in the text
• pixel_size: Not specified in the text
• dark_current: Not specified in the text

Optical Data

• focal_length: Not specified in the text
• aperture: Not specified in the text
• field_of_view: Not specified in the text
• distortion: Not specified in the text

Performance Metrics

• frame_rate: 15 fps
• signal_to_noise_ratio: Not specified in the text
• sensitivity: Not specified in the text
• shutter_speed: Not specified in the text
• power_consumption: 0.57 µW
• noise: Not specified in the text

Applications & Benefits

• cell_imaging: Not specified in the text
• benefits: Self-powered operation, maintenance-free large-scale vision sensor networks.

Supporting Organizations

• supported_by: National Natural Science Foundation of China under grant No. 92164203, 62334006, and Key Research and Development Program of Xinjiang Uygur Autonomous Region (No.2022B01008-3).

Manuscript Details

• publication_date: 9-12 Sept. 2024

Relevancy Score

• score: 9
• missing_fields:
  • 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_178c6666-1d59-480b-b92a-8d34a499427d-selfputing_a_057_w__15_fps_vision_chip_with_selfpowered_inpixel_computing_and_inmemory_computing_for_visual_perception_on_the_edge.json