Search research articles

Search research articles

Related Experiment Videos

Orientation in manhattan: equiprojective classes and sequential estimation.

André T Martins¹, Pedro M Q Aguiar, Mário A T Figueiredo

¹Department of Electrical and Computer Engineering, Instituto Superior Técnico, Technical University of Lisbon, 1049-001 Lisboa, Portugal. jah@clix.pt

IEEE Transactions on Pattern Analysis and Machine Intelligence

|May 7, 2005

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

A benchmarking framework and dataset for learning to defer in human-AI decision-making.

Scientific data·2025

Same author

A Measure of Synergy Based on Union Information.

Entropy (Basel, Switzerland)·2024

Same author

Orders between Channels and Implications for Partial Information Decomposition.

Entropy (Basel, Switzerland)·2023

Same author

A classification-based approach to semi-supervised clustering with pairwise constraints.

Neural networks : the official journal of the International Neural Network Society·2020

Same author

External Patch-Based Image Restoration Using Importance Sampling.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019

Same author

A Convergent Image Fusion Algorithm Using Scene-Adapted Gaussian-Mixture-Based Denoising.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2018

Same journal

A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces a novel camera 3D orientation estimation method for urban scenes, bypassing feature correspondences. It leverages the Manhattan World assumption for efficient and accurate camera pose tracking in video sequences.

Area of Science:

Computer Vision
Robotics
3D Reconstruction

Background:

Camera 3D orientation estimation from video often relies on feature correspondences, a computationally intensive bottleneck.
Existing methods struggle with efficiency and robustness in complex urban environments.

Purpose of the Study:

To develop a novel 3D orientation estimation method for urban environments that avoids feature correspondences.
To improve the efficiency and accuracy of camera pose tracking in video sequences.

Main Methods:

Exploiting the Manhattan World (MW) assumption, where scene edges align with three orthogonal directions.
Defining equivalence classes of equiprojective orientations and introducing a small rotation model for smooth camera motion.
Decoupling elevation/twist angle estimation from the compass angle within a probabilistic sequential framework.

Related Experiment Videos

Main Results:

A significant reduction in the search space for orientation estimation.
Demonstrated performance using real-world urban video sequences.
Successful avoidance of the computationally expensive feature correspondence step.

Conclusions:

The proposed method offers an efficient and accurate alternative for 3D camera orientation estimation in urban settings.
The Manhattan World assumption provides a powerful constraint for simplifying the orientation inference problem.
This approach has potential applications in autonomous navigation and augmented reality.