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 Videos

A practical algorithm for learning scene information from monocular video.

Lin Zhu1, Jie Zhou, Jingyan Song

  • 1Automation Department of Tsinghua University, Beijing, P.R.China.

Optics Express
|June 11, 2008
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

Polyunsaturated fatty acids promote the expansion of myeloid-derived suppressor cells by activating the JAK/STAT3 pathway.

European journal of immunology·2013
Same author

RAD51 gene is associated with advanced age-related macular degeneration in Chinese population.

Clinical biochemistry·2013
Same author

Immunization against recombinant GnRH-I alters ultrastructure of gonadotropin cell in an experimental boar model.

Reproductive biology and endocrinology : RB&E·2013
Same author

Multi-class constrained normalized cut with hard, soft, unary and pairwise priors and its applications to object segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2013
Same author

Comparison of genomic and amino acid sequences of eight Japanese encephalitis virus isolates from bats.

Archives of virology·2013
Same author

Regulation of dendritic cell differentiation in bone marrow during emergency myelopoiesis.

Journal of immunology (Baltimore, Md. : 1950)·2013
Same journal

Long-term stabilization of intensity-difference squeezing from four-wave mixing in rubidium vapor.

Optics express·2026
Same journal

Robust 3D topography measurement of large-range high-aspect-ratio structures based on dual-domain statistical filtering in SD-OCT.

Optics express·2026
Same journal

Broadband transmissive terahertz metasurface for simultaneous quad-mode OAM multiplexing.

Optics express·2026
Same journal

Leveraging two-dimensional materials for high-sensitivity optical sensors: quasi-bound states in the continuum within hybrid metasurfaces.

Optics express·2026
Same journal

Resolution investigation for dual-spherical-wave optical scanning holographic microscopy: methods and performance.

Optics express·2026
Same journal

Robustness of parallel subnetwork-filtered diffractive deep neural networks.

Optics express·2026
See all related articles

This study introduces a practical algorithm for estimating scene information from monocular video, crucial for applications like surveillance and map building. The method effectively determines ground properties and relative depth using a novel Pedestrian-Scene Map.

Area of Science:

  • Computer Vision
  • Robotics
  • Geospatial Analysis

Background:

  • Estimating scene information (ground/non-ground regions, relative depth, unevenness) is vital for applications like video surveillance and map building.
  • Existing methods often rely on impractical assumptions, limiting their real-world applicability.
  • A practical approach is needed for unconstrained environments using monocular video.

Purpose of the Study:

  • To propose a practical algorithm for estimating scene information from monocular video.
  • To overcome limitations of previous methods that require specific, hard-to-satisfy assumptions.
  • To enable accurate scene understanding for applications like surveillance and mapping.

Main Methods:

  • Development of a novel Pedestrian-Scene Map (PS Map) by integrating pedestrian detection results over time.

Related Experiment Videos

  • The PS Map characterizes scene properties by learning average pedestrian width and occurrence probability at different locations.
  • Utilizing the PS Map to measure relative ground depth, identify ground/non-ground regions, and assess ground unevenness.

    • Main Results:

    • The proposed algorithm effectively estimates critical scene information using monocular video.
    • Experimental results demonstrate the method's robustness with stationary, uncalibrated cameras in unconstrained environments.
    • The PS Map provides a reliable basis for deriving ground properties and scene geometry.

    Conclusions:

    • The developed algorithm offers a practical solution for scene information estimation in monocular video.
    • The Pedestrian-Scene Map is an effective tool for understanding ground characteristics and scene layout.
    • The method shows significant potential for enhancing applications in video surveillance, autonomous navigation, and map building.