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 Experiment Video

Updated: Apr 15, 2026

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

2.2K

Fast Image-Based Obstacle Detection From Unmanned Surface Vehicles.

Matej Kristan, Vildana Sulíc Kenk, Stanislav Kovacic

    IEEE Transactions on Cybernetics
    |April 4, 2015
    PubMed
    Summary
    This summary is machine-generated.

    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

    eWaSR-An Embedded-Compute-Ready Maritime Obstacle Detection Network.

    Sensors (Basel, Switzerland)·2023
    Same author

    Joint Calibration of a Multimodal Sensor System for Autonomous Vehicles.

    Sensors (Basel, Switzerland)·2023
    Same author

    Learning with Weak Annotations for Robust Maritime Obstacle Detection.

    Sensors (Basel, Switzerland)·2022
    Same author

    A Discriminative Single-Shot Segmentation Network for Visual Object Tracking.

    IEEE transactions on pattern analysis and machine intelligence·2021
    Same author

    WaSR-A Water Segmentation and Refinement Maritime Obstacle Detection Network.

    IEEE transactions on cybernetics·2021
    Same author

    Cognitive Relevance Transform for Population Re-Targeting.

    Sensors (Basel, Switzerland)·2020

    This study introduces a new graphical model for real-time obstacle detection in unmanned surface vehicles (USVs). The method offers fast, continuous image-map estimation for marine environments, improving safety.

    Area of Science:

    • Robotics
    • Computer Vision
    • Marine Engineering

    Background:

    • Unmanned Surface Vehicles (USVs) require robust obstacle detection in diverse marine environments.
    • Challenges include identifying varied obstacles like debris, divers, and shorelines from onboard imagery.
    • Continuous and real-time detection is crucial for safe USV navigation.

    Purpose of the Study:

    • To develop a fast and continuous online obstacle detection method for USVs.
    • To address the challenge of detecting diverse obstacles in real-time from a single video stream.
    • To propose a novel graphical model for unsupervised image-map estimation.

    Main Methods:

    • A new graphical model based on a Markov random field framework is proposed.
    • The model incorporates weak structural constraints reflecting the marine environment's semantic structure.

    More Related Videos

    Quantitatively Measuring In situ Flows using a Self-Contained Underwater Velocimetry Apparatus SCUVA
    09:22

    Quantitatively Measuring In situ Flows using a Self-Contained Underwater Velocimetry Apparatus SCUVA

    Published on: October 31, 2011

    13.6K

    Related Experiment Videos

    Last Updated: Apr 15, 2026

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
    08:47

    Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

    Published on: February 9, 2024

    2.2K
    Quantitatively Measuring In situ Flows using a Self-Contained Underwater Velocimetry Apparatus SCUVA
    09:22

    Quantitatively Measuring In situ Flows using a Self-Contained Underwater Velocimetry Apparatus SCUVA

    Published on: October 31, 2011

    13.6K
  • A highly efficient algorithm enables simultaneous optimization of model parameters and segmentation mask estimation.
  • The approach avoids computationally intensive texture feature extraction.

    • Main Results:

    • The proposed method achieves fast and continuous obstacle detection in real-time.
    • It outperforms existing approaches on a large, challenging marine environment dataset.
    • The algorithm requires a fraction of the computational effort compared to related methods.
    • Demonstrates effective unsupervised segmentation for obstacle identification.

    Conclusions:

    • The developed graphical model provides an efficient solution for real-time obstacle detection in USVs.
    • The approach successfully handles diverse marine obstacles using unsupervised segmentation.
    • This method significantly advances the capability of USVs to navigate safely in complex environments.
    • The proposed technique offers a computationally efficient alternative to traditional feature-based methods.