A Novel Approach To Object Detection Under Diverse Illumination Conditions Using Rowwise Exposure Images

• doi: 10.1109/JSEN.2025.3554806
• title: A Novel Approach to Object Detection under Diverse Illumination Conditions using Rowwise Exposure Images
• publisher: IEEE
• isbn:
• issn: 2379-9153
• rank: 859
• access_type: LOCKED
• content_type: Early Access Articles
• abstract: In this study, we present a novel approach to object detection utilizing row-wise exposure (RWE) images to substantially improve object detection performance in low and high illumination conditions. Unlike previous RWE imaging techniques that require row-wise merging for HDR synthesis, our system directly utilizes raw RWE images without post-processing. It enables the proposed object detection algorithm to effectively overcome the limitations of conventional systems in dynamic and variable lighting scenarios. Additionally, we introduce a tailored data augmentation strategy optimized for the unique characteristics of RWE images, enhancing model training and robustness without relying on dedicated RWE datasets. We developed a prototype CMOS image sensor (CIS) with RWE functionality to demonstrate the practical viability of our approach. This prototype was instrumental in validating the system's effectiveness in real-world conditions. The proposed data augmentation method, designed specifically for raw RWE images, enriches the training dataset, enabling models to adapt to various lighting situations and improve their generalization abilities. Our experiments employed widely adopted object detection models, such as YOLOv7 and YOLOv9, along with standard datasets like MS COCO and HDR4RTT, to evaluate model performance under varying illumination coefficients and motion blur intensities. The results showed significant performance improvements over existing object detection methods, especially in challenging illumination conditions and dynamic environments. To ensure reproducibility and allow further validation, we have made our source code available at: https://github.com/eomtaehoon/RWE-YOLO.
• article_number: 10947262
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947262
• html_url: https://ieeexplore.ieee.org/document/10947262/
• abstract_url: https://ieeexplore.ieee.org/document/10947262/
• publication_title: IEEE Sensors Journal
• conference_location:
• conference_dates:
• publication_number: 7361
• is_number: 4427201
• publication_year: 2025
• publication_date:
• start_page: 1
• end_page: 1
• citing_paper_count: 0
• citing_patent_count: 0
• download_count: 0
• insert_date: 20250401
• index_terms:
  • ieee_terms:
    • Object detection
    • Imaging
    • Lighting
    • Machine vision
    • Data augmentation
    • Accuracy
    • Intelligent sensors
    • Detectors
    • Training
    • Prototypes
  • author_terms:
    • Object detection
    • CMOS imager sensor (CIS)
    • row-wise exposure images
    • high dynamic range (HDR)
    • machine vision
    • challenging illumination conditions
  • dynamic_index_terms:
    • Imaging Techniques
    • Image Features
    • Imaging Characteristics
    • Dynamic Range
    • Dynamic Light
    • Dynamic Environment
    • Object Detection
    • Data Augmentation
    • Raw Images
    • Image Sensor
    • Camera Sensor
    • Illumination Conditions
    • Standard Datasets
    • High Dynamic Range
    • Machine Vision
    • Visual Navigation
    • Data Augmentation Methods
    • Dynamic Scenarios
    • Motion Blur
    • Object Detection Model
    • Light Conditions
    • Detection Accuracy
    • Exposure Levels
    • High Dynamic Range Image
    • Accurate Object Detection
    • Low Light Conditions
    • MS COCO Dataset
    • Real-time Object Detection
    • Media Exposure
    • Robust Detection
    • Simple Logic
    • Exposure Conditions
    • Exposure Status
    • One-stage Detectors
• authors:
  • Author Name: Tae-Hoon Eom
    Affiliation: Department of Semiconductor Engineering, Seoul National University of Science and Technology, Gongneung-ro 232, Nowon-gu, Seoul, South Korea
    Author URL: https://ieeexplore.ieee.org/author/729879972743117
    ID: 729879972743117
    Order: 1
    Author Affiliations:
    • Department of Semiconductor Engineering, Seoul National University of Science and Technology, Gongneung-ro 232, Nowon-gu, Seoul, South Korea
  • Author Name: Hyeon-June Kim
    Affiliation: Department of Semiconductor Engineering, Seoul National University of Science and Technology, Gongneung-ro 232, Nowon-gu, Seoul, South Korea
    Author URL: https://ieeexplore.ieee.org/author/37085397854
    ID: 37085397854
    Order: 2
    Author Affiliations:
    • Department of Semiconductor Engineering, Seoul National University of Science and Technology, Gongneung-ro 232, Nowon-gu, Seoul, South Korea

Image Sensor

• sensor_type: CMOS
• resolution: 320x320
• dynamic_range: 70 dB
• 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

• frame_rate: High (exact fps not specified)

Applications & Benefits

• cell_imaging: Not specified
• benefits: Enables digital imaging in various applications such as smartphones, medical devices, and automotive systems.

Supporting Organizations

• supported_by: Seoul National University of Science and Technology

Manuscript Details

• publication_date: 2025-00-00

Relevancy Score

• score: 8
• missing_fields:
  • fill factor
  • quantum efficiency
  • readout speed
  • temporal noise
  • fixed-pattern noise
  • analog-to-digital conversion techniques
  • microlenses
  • on-chip colour filters
  • global or rolling shutters
  • backside illumination

Processed JSON Filename

request_3a769c84-feb0-4f68-91d8-a82b97b7ac9f-a_novel_approach_to_object_detection_under_diverse_illumination_conditions_using_rowwise_exposure_images.json