Search research 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

Related Concept Videos

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

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.

You might also read

Related Articles

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

Sort by

Same author

Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks.

Scientific reports·2024

Same author

Real-Time Monocular Skeleton-Based Hand Gesture Recognition Using 3D-Jointsformer.

Sensors (Basel, Switzerland)·2023

Same author

Influence of Biochar and Bio-Oil Loading on the Properties of Epoxy Resin Composites.

Polymers·2023

Same author

Visual Parking Occupancy Detection Using Extended Contextual Image Information via a Multi-Branch Output ConvNeXt Network.

Sensors (Basel, Switzerland)·2023

Same author

A multi-sensor dataset with annotated activities of daily living recorded in a residential setting.

Scientific data·2023

Same author

A fully automatic method for segmentation of soccer playing fields.

Scientific reports·2023

Search research articles

Related Experiment Video

Updated: May 3, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Foreground segmentation in depth imagery using depth and spatial dynamic models for video surveillance applications.

Carlos R del-Blanco¹, Tomás Mantecón², Massimo Camplani³

¹Grupo de Tratamiento de Imágenes, E.T.S.I de Telecomunicación, Universidad Politécnica de Madrid, Avenida Complutense 30, Madrid 28040, Spain. cda@gti.ssr.upm.es.

Sensors (Basel, Switzerland)

|January 29, 2014

Summary

This study introduces a novel foreground segmentation algorithm using a Kinect depth sensor for reliable indoor surveillance. The new method combines background subtraction with a Bayesian network, improving accuracy regardless of lighting conditions.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: May 3, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Computer Vision
Artificial Intelligence
Robotics

Background:

High-quality foreground segmentation is crucial for indoor security and surveillance systems.
Existing methods often struggle with varying illumination conditions.
There is a need for low-cost, illumination-independent segmentation solutions.

Purpose of the Study:

To propose a novel foreground segmentation algorithm using only a Kinect depth sensor.
To achieve robust segmentation independent of indoor illumination.
To enhance the performance of security and surveillance applications.

Main Methods:

A novel algorithm combining Gaussian Mixture Model (GMM)-based background subtraction with a Bayesian network.
Development of a Bayesian network that leverages depth data characteristics.
Introduction of two dynamic models within the Bayesian network: spatial and depth evolution models.
A key contribution is a depth-based dynamic model predicting foreground depth distribution changes.

Main Results:

The proposed algorithm achieves high-quality foreground segmentation.
Segmentation performance is robust across different indoor illumination conditions.
Experimental results on depth-based databases show superior accuracy compared to state-of-the-art methods.

Conclusions:

The novel algorithm effectively addresses the limitations of illumination-dependent segmentation.
The depth-based dynamic model offers a significant advancement over traditional visible imagery approaches.
The system provides a promising low-cost solution for enhanced indoor surveillance and security.