Salient Object Detection Toward Singlepixel Imaging

• doi: 10.1109/TCSVT.2023.3283705
• title: Salient Object Detection Toward Single-Pixel Imaging
• publisher: IEEE
• isbn:
• issn: 1558-2205
• rank: 3497
• access_type: LOCKED
• content_type: Journals
• abstract: Replacing CCD and CMOS image sensors in conventional cameras with digital micromirror devices (DMD), single-pixel cameras low-costly shot images by capturing compressed measurements and computation. However, the compressed measurements lack explicit spatial information, causing difficulties for high-level tasks such as salient object detection (SOD) that are usually designed to have visual inputs. To address the issue, we propose a single-pixel imaging-based SOD network called SPISODNet that enables predicting saliency maps directly from compressed measurements with high accuracy. Specifically, we first design an underlying feature inversion module (UFIM) to capture the underlying scene information, and then develop a context-aware flow (CAF) consisting of a feature focus module (FFM), three bidirectional attention modules (BAMs), and a spatial information-induced attention module (SIAM) to acquire and polish saliency predictions. Extensive experiments demonstrate that our method achieves superior performance for single-pixel imaging-based SOD.
• article_number: 10145417
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10145417
• html_url: https://ieeexplore.ieee.org/document/10145417/
• abstract_url: https://ieeexplore.ieee.org/document/10145417/
• publication_title: IEEE Transactions on Circuits and Systems for Video Technology
• conference_location:
• conference_dates:
• publication_number: 76
• is_number: 10382161
• publication_year: 2024
• publication_date: Jan. 2024
• start_page: 235
• end_page: 247
• citing_paper_count: 1
• citing_patent_count: 0
• download_count: 780
• insert_date: 20230607
• index_terms:
  • ieee_terms:
    • Image reconstruction
    • Feature extraction
    • Image coding
    • Image edge detection
    • Cameras
    • Object detection
    • Context awareness
  • author_terms:
    • Single-pixel imaging
    • salient object detection
    • underlying feature inversion
    • context-aware mechanism
    • hierarchical feature fusion
  • dynamic_index_terms:
    • Salient Object
    • Salient Object Detection
    • Single-pixel Imaging
    • Spatial Information
    • Attention Module
    • Spatial Module
    • Spatial Attention
    • Saliency Map
    • Spatial Attention Module
    • Compressive Measurements
    • Digital Micromirror Device
    • Loss Function
    • Loss-of-function
    • Convolutional Layers
    • Image Reconstruction
    • Iterative Reconstruction
    • Tomographic Reconstruction
    • Attention Mechanism
    • Multi-head Attention
    • Image Information
    • Precision And Recall
    • Semantic Information
    • Top-down Approach
    • Top-down Model
    • Convolution Operation
    • Adjacent Features
    • RGB Images
    • Computer Image
    • Image Calculator
    • Precision-recall Curve
    • Semantic Segmentation
    • Ghost Imaging
    • Element-wise Multiplication
    • Compression Ratio
    • Feature Fusion
    • Convolution Kernel
• authors:
  • Author Name: Huihui Yue
    Affiliation: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
    Author URL: https://ieeexplore.ieee.org/author/37089228832
    ID: 37089228832
    Order: 1
    Author Affiliations:
    • School of Electrical and Information Engineering, Tianjin University, Tianjin, China
  • Author Name: Jichang Guo
    Affiliation: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
    Author URL: https://ieeexplore.ieee.org/author/37277254300
    ID: 37277254300
    Order: 2
    Author Affiliations:
    • School of Electrical and Information Engineering, Tianjin University, Tianjin, China
    • Shanghai Artificial Intelligence Laboratory, Shanghai, China
  • Author Name: Xiangjun Yin
    Affiliation: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
    Author URL: https://ieeexplore.ieee.org/author/37089426962
    ID: 37089426962
    Order: 3
    Author Affiliations:
    • School of Electrical and Information Engineering, Tianjin University, Tianjin, China
  • Author Name: Yi Zhang
    Affiliation: School of Electrical and Information Engineering, Tianjin University, Tianjin, China
    Author URL: https://ieeexplore.ieee.org/author/37090012150
    ID: 37090012150
    Order: 4
    Author Affiliations:
    • School of Electrical and Information Engineering, Tianjin University, Tianjin, China
  • Author Name: Bihan Wen
    Affiliation: School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore
    Author URL: https://ieeexplore.ieee.org/author/37085343251
    ID: 37085343251
    Order: 5
    Author Affiliations:
    • School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore
  • Author Name: Chongyi Li
    Affiliation: School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore
    Author URL: https://ieeexplore.ieee.org/author/37085795979
    ID: 37085795979
    Order: 6
    Author Affiliations:
    • School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore

Image Sensor

• sensor_type: CMOS
• resolution: Not explicitly stated
• dynamic_range: Not explicitly stated
• pixel_size: Not explicitly stated
• dark_current: Not explicitly stated

Optical Data

• focal_length: Not explicitly stated
• aperture: Not explicitly stated
• field_of_view: Not explicitly stated
• distortion: Not explicitly stated

Performance Metrics

• frame_rate: Not explicitly stated
• signal_to_noise_ratio: Not explicitly stated
• sensitivity: Not explicitly stated
• shutter_speed: Not explicitly stated
• power_consumption: Not explicitly stated
• noise: Not explicitly stated

Applications & Benefits

• cell_imaging: Not explicitly stated
• benefits: Enable digital imaging in a variety of applications such as smartphones, medical devices, and automotive systems.

Supporting Organizations

• supported_by: Not explicitly stated

Manuscript Details

• publication_date: Jan. 2024

Relevancy Score

• score: 5
• missing_fields:
  • resolution
  • dynamic_range
  • pixel_size
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • frame_rate
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • power_consumption
  • noise
  • cell_imaging
  • supported_by

Processed JSON Filename

request_9f33160c-c625-48c8-b195-f74076911d32-salient_object_detection_toward_singlepixel_imaging.json