Related Experiment Video
Updated: Oct 27, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.1K
Binocular vision supports the development of scene segmentation capabilities: Evidence from a deep learning model
Ross Goutcher1,2, Christian Barrington1,3,4, Paul B Hibbard5,6
1Psychology Division, Faculty of Natural Sciences, University of Stirling, Stirling, UK.
Journal of Vision
|July 21, 2021
Summary
Deep learning models can perform scene segmentation and depth estimation using binocular images. Binocular image arrangement impacts performance, suggesting its importance in visual development and potential applications for perceptual impairments.
Area of Science:
- Computer Vision
- Deep Learning
- Computational Neuroscience
Background:
- Deep learning has advanced machine vision tasks like scene segmentation and depth estimation.
- Binocular vision provides depth cues crucial for visual perception.
Purpose of the Study:
- To develop a novel deep neural network for simultaneous scene segmentation and depth estimation using binocular images.
- To investigate the impact of binocular image arrangement on model performance.
Main Methods:
- A novel deep neural network model was designed for joint scene segmentation and depth estimation.
- The model was trained and evaluated using standard, identical, and swapped left-right binocular image pairs.
Main Results:
- Performance degraded significantly with swapped images, indicating sensitivity to binocular arrangement.
- Segmentation performance remained robust with identical images, surpassing monocular models.
- Binocular image differences were shown to aid depth recovery and enhance monocular segmentation learning.
Conclusions:
- Binocular image disparities are critical for both depth and segmentation information.
- Binocular vision appears to play a significant role in visual development.
- Findings may inform the study and treatment of developmental perceptual impairments.
Related Concept Videos
01:15Depth Perception and Spatial Vision
1.3K
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.
1.3K
01:26Visual System
1.1K
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
1.1K
01:24Vision
57.3K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
57.3K