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

Direct Sparse Odometry.

Jakob Engel, Vladlen Koltun, Daniel Cremers

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |April 20, 2017
    PubMed
    Summary
    This summary is machine-generated.

    Direct Sparse Odometry (DSO) offers accurate real-time visual odometry by directly optimizing sparse image features and camera motion. This novel method achieves superior tracking accuracy and robustness without relying on traditional keypoint detectors.

    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

    DynSUP: Dynamic Gaussian Splatting From an Unposed Image Pair.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    SNI-SLAM++: Tightly-Coupled Semantic Neural Implicit SLAM.

    IEEE transactions on pattern analysis and machine intelligence·2025
    Same author

    Learned free-energy functionals from pair-correlation matching for dynamical density functional theory.

    Physical review. E·2025
    Same author

    Auditory Training and Perceptual Assessment of Spasmodic Dysphonia.

    Journal of voice : official journal of the Voice Foundation·2025
    Same author

    The Pulseq-CEST Library: definition of preparations and simulations, example data, and example evaluations.

    Magma (New York, N.Y.)·2025
    Same author

    Reaching the limit in autonomous racing: Optimal control versus reinforcement learning.

    Science robotics·2023
    Same journal

    Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same journal

    Learning Shape Anchors for Holistic Indoor Scene Understanding.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    Area of Science:

    • Computer Vision
    • Robotics
    • Simultaneous Localization and Mapping (SLAM)

    Background:

    • Visual odometry methods estimate camera motion from image sequences.
    • Existing direct methods often rely on smoothness priors, limiting their applicability.
    • Keypoint-based methods can fail in texture-less regions.

    Purpose of the Study:

    • To introduce Direct Sparse Odometry (DSO), a novel visual odometry approach.
    • To achieve real-time, accurate, and robust camera motion estimation.
    • To overcome limitations of existing direct and indirect visual odometry techniques.

    Main Methods:

    • Employs a fully direct probabilistic model minimizing photometric error.
    • Jointly optimizes sparse geometry (inverse depth) and camera motion.

    Related Experiment Videos

  • Achieves real-time performance by evenly sampling pixels and omitting smoothness priors.

    • Main Results:

    • DSO demonstrates significantly higher tracking accuracy compared to state-of-the-art methods.
    • The method exhibits enhanced robustness across diverse real-world scenarios.
    • Effective handling of feature-poor regions due to gradient-based pixel sampling.

    Conclusions:

    • Direct Sparse Odometry provides a robust and accurate solution for real-time visual odometry.
    • The novel formulation enables effective motion estimation even in challenging environments.
    • DSO represents a significant advancement in visual odometry research.