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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

468
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
468
Gestalt Principles of Perception01:21

Gestalt Principles of Perception

238
Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...
238

You might also read

Related Articles

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

Sort by
Same author

Bioinformatics analysis and clinical validation identify <i>FBXW9</i> as a biomarker in bladder urothelial carcinoma.

Translational andrology and urology·2026
Same author

Mechanisms of Reversible Transition in Emulsions Stabilized by Modified Nanocrystalline Cellulose.

Molecules (Basel, Switzerland)·2026
Same author

A Calcium Silicate-derived Silicate Ion Solution Improves Fat Graft Retention and Promotes Angiogenesis: An Experimental Study.

Aesthetic surgery journal·2026
Same author

Association between becoming a carer in later life and changes in the trajectory of cognitive function: results from the English longitudinal study of ageing.

Age and ageing·2026
Same author

SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition.

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

IBP1 Represses the Migration and Invasion of Hepatocellular Carcinoma Cells by Inhibiting SOCE-dependent Formation of Neutrophil Extracellular Traps by Targeting the Akt Pathway.

Anticancer research·2026
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

Related Experiment Video

Updated: May 12, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

11.7K

Uncertain Object Representation for Image-Based 3D Object Perception.

Qitai Wang, Yuntao Chen, Zhaoxiang Zhang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |May 8, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces an uncertain representation for 3D objects detected from images, addressing inherent localization ambiguity. This probabilistic approach improves both 3D object detection and multi-object tracking accuracy.

    More Related Videos

    Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
    08:04

    Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

    Published on: December 4, 2013

    4.4K
    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
    07:05

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

    Published on: October 27, 2016

    9.1K

    Related Experiment Videos

    Last Updated: May 12, 2025

    Creating Objects and Object Categories for Studying Perception and Perceptual Learning
    14:38

    Creating Objects and Object Categories for Studying Perception and Perceptual Learning

    Published on: November 2, 2012

    11.7K
    Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
    08:04

    Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

    Published on: December 4, 2013

    4.4K
    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
    07:05

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

    Published on: October 27, 2016

    9.1K

    Area of Science:

    • Computer Vision
    • Robotics
    • Artificial Intelligence

    Background:

    • Camera-based 3D object detection struggles with localization uncertainty due to the ill-posed nature of image inputs.
    • Existing methods often oversimplify object representation by using single, certain 3D bounding boxes, neglecting localization ambiguity.

    Purpose of the Study:

    • To develop a novel method for representing 3D objects that accounts for localization uncertainty in camera-based detection and tracking.
    • To improve the accuracy and robustness of 3D object detection and multi-object tracking systems by modeling object location as a probability distribution.

    Main Methods:

    • Proposed an uncertain representation for 3D objects by modeling localization uncertainty during the detection process.
    • Developed a method to gather and suppress redundant predictions to form the uncertain object representation for 3D detection.
    • Generalized the cross-frame association metric for 3D multiple object tracking to handle uncertain object representations, enhancing tracking of unstable localizations.

    Main Results:

    • Achieved significant performance boosts as a plug-in module for camera 3D detectors, including +3.5%/+3.2%/+3.7% NDS on the nuScenes validation set for BEVDet4D/BEVDet4D-Depth/DD3D.
    • Demonstrated a +4.7% NDS improvement for BEVDet4D-Depth on the nuScenes test set.
    • The enhanced tracking method reached 48.2% AMOTA performance and reduced identity switches to 300 on the nuScenes test set.

    Conclusions:

    • The proposed uncertain object representation effectively addresses the inherent localization ambiguity in camera-based 3D perception.
    • This probabilistic approach significantly enhances the performance of both 3D object detection and multi-object tracking systems.
    • The method offers a flexible, plug-in solution that improves existing state-of-the-art models without requiring fundamental architectural changes.