Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Advancing solar and wind penetration in China through energy complementarity.

Nature·2026
Same author

Morphology-Dependent Percolation and Conductive Network Formation in Polymer Nanocomposites with Multi-Shaped Nanofillers.

Nanomaterials (Basel, Switzerland)·2026
Same author

Optimized LiDAR target for benchmarking depth measurement accuracy.

Optics express·2025
Same author

Ultralow-complexity fiber nonlinearity compensation based on gradient-driven pruned Kolmogorov-Arnold network.

Optics letters·2025
Same author

Wave-Aware Weakly Supervised Histopathological Tissue Segmentation With Cross-Scale Logits Distillation.

IEEE transactions on medical imaging·2025
Same author

Identification of signature genes and subtypes for heart failure diagnosis based on machine learning.

Frontiers in cardiovascular medicine·2025

Related Experiment Video

Updated: Aug 15, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

478

Adaptive SVM-based pixel accumulation technique for a SPAD-based lidar system.

Chuanchuan Yang, Hualong Zhang

    Applied Optics
    |January 6, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces an adaptive Support Vector Machine (SVM) technique for Single-Photon Avalanche Diode (SPAD) lidar, significantly enhancing depth image accuracy. The method effectively distinguishes targets from backgrounds, reducing errors by up to 61%.

    More Related Videos

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
    06:25

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

    Published on: February 12, 2014

    8.5K
    Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station
    05:57

    Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station

    Published on: April 1, 2020

    8.1K

    Related Experiment Videos

    Last Updated: Aug 15, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    478
    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform
    06:25

    Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

    Published on: February 12, 2014

    8.5K
    Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station
    05:57

    Characterization of SiN Integrated Optical Phased Arrays on a Wafer-Scale Test Station

    Published on: April 1, 2020

    8.1K

    Area of Science:

    • Photonics and Optical Sensing
    • Machine Learning in Imaging
    • Computer Vision

    Background:

    • Single-Photon Avalanche Diode (SPAD) flash lidar systems generate depth images.
    • Depth image accuracy is often limited by noise and target/background differentiation.
    • Existing methods may struggle with dynamic changes in target features and environmental conditions.

    Purpose of the Study:

    • To propose an adaptive Support Vector Machine (SVM)-based pixel accumulation technique for SPAD flash lidar.
    • To improve the accuracy of depth images by effectively distinguishing targets from backgrounds.
    • To enhance the real-time adaptability and practicability of depth image processing.

    Main Methods:

    • An adaptive incremental SVM classifier is developed to differentiate target and background pixels, preventing boundary blur.
    • Pixels belonging to the same target are selectively accumulated.
    • Neighboring pixel results are accumulated to reduce noisy photon influence and derive accurate laser signal peak positions from SPAD detector histograms.
    • The SVM model is trained using a compact data subset for efficient online updates.

    Main Results:

    • The proposed adaptive pixel accumulation technique significantly reduces the mean squared error (MSE) of depth images.
    • MSE was reduced by 61% compared to raw images.
    • MSE was reduced by 44% compared to a static SVM-based method, particularly when the target is moving.

    Conclusions:

    • The adaptive SVM-based pixel accumulation technique offers a robust solution for enhancing SPAD lidar depth image accuracy.
    • The method's ability to update online to changing target features and light conditions improves its practical applicability.
    • This approach effectively mitigates noise and improves target-background discrimination in dynamic scenarios.