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

Convolution Properties I01:20

Convolution Properties I

120
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
120
Convolution Properties II01:17

Convolution Properties II

147
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
147
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

210
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
210
Deconvolution01:20

Deconvolution

116
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
116
Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

479
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.
479
Vector Operations01:20

Vector Operations

1.1K
Vectors are physical quantities that have both magnitude and direction. The vector operations include addition, subtraction, and scalar multiplication.
A vector multiplied by a scalar value is called scalar multiplication. The result obtained is a new vector with a different magnitude. If the scalar is positive, the direction of the vector remains the same, but if it is negative, the direction of the vector is reversed. For example, the product of the mass and velocity yields the momentum.
1.1K

You might also read

Related Articles

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

Sort by
Same author

Noninvasive multimodal photoacoustic-ultrasound imaging for dynamic assessment of placental hypoxia and perfusion in preeclampsia.

Photoacoustics·2026
Same author

CD4<sup>+</sup>CD25<sup>+</sup> regulatory T cells circumstantially initiate transplant rejection through CXCL15/neutrophil axis.

Communications biology·2026
Same author

A Hand-Held Digital Printer for On-Site Fabrication of Micro/Nano Composite Dressings.

ACS applied materials & interfaces·2026
Same author

Excess nitric oxide alters cellular pH to restrict salicylic acid movement and systemic immunity.

Science advances·2026
Same author

Exosome-Coated Boron-Containing Evodiamine Derivative Triggered by Pathology-Specific Reactive Oxygen Species Targets Myofibroblasts to Ameliorate Hypertrophic Scarring.

ACS applied materials & interfaces·2026
Same author

High Humidity Exacerbates Psoriasiform Skin Disease Relapse by Increasing Tissue-Resident Memory T Cells via Altering Skin Microbiota.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Related Experiment Video

Updated: May 14, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

322

PreCM: The Padding-Based Rotation Equivariant Convolution Mode for Semantic Segmentation.

Xinyu Xu, Huazhen Liu, Tao Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 18, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel rotation equivariant convolution framework (PreCM) to improve semantic segmentation accuracy in computer vision tasks with arbitrary imaging angles. The new method enhances feature extraction, leading to significant improvements in Intersection over Union (IOU) across various datasets.

    More Related Videos

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
    08:27

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

    Published on: January 5, 2024

    907
    Quantifying Intermembrane Distances with Serial Image Dilations
    07:45

    Quantifying Intermembrane Distances with Serial Image Dilations

    Published on: September 28, 2018

    6.3K

    Related Experiment Videos

    Last Updated: May 14, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    322
    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
    08:27

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

    Published on: January 5, 2024

    907
    Quantifying Intermembrane Distances with Serial Image Dilations
    07:45

    Quantifying Intermembrane Distances with Serial Image Dilations

    Published on: September 28, 2018

    6.3K

    Area of Science:

    • Computer Vision
    • Image Processing
    • Deep Learning

    Background:

    • Semantic segmentation is crucial in computer vision, but current deep learning models struggle with arbitrary imaging angles.
    • Lack of rotation equivariance in Convolutional Neural Networks (CNNs) hinders effective feature extraction from objects with diverse orientations.

    Purpose of the Study:

    • To develop a universal convolution-group framework that incorporates rotation equivariance for semantic segmentation.
    • To introduce a novel padding-based rotation equivariant convolution mode (PreCM) as a versatile replacement component for existing convolutions.

    Main Methods:

    • Constructed a universal convolution-group framework to enhance utilization of orientation information.
    • Designed a padding-based rotation equivariant convolution mode (PreCM) compatible with multi-scale images and various convolution types.
    • Proposed a new evaluation metric, Rotation Difference (RD), to assess the impact of image rotation.

    Main Results:

    • PreCM-based semantic segmentation networks showed improved average Intersection over Union (IOU) ranging from 4.53% to 10.63% compared to original versions under random angle rotation.
    • Average Rotation Difference (RD) values decreased across experiments, indicating enhanced robustness to orientation variations.
    • Experiments were conducted on Satellite Images of Water Bodies, DRIVE, and Floodnet datasets, integrating PreCM into six existing semantic segmentation networks.

    Conclusions:

    • The proposed PreCM framework effectively equips semantic segmentation networks with rotation equivariance, significantly improving performance on datasets with arbitrary imaging angles.
    • PreCM serves as a flexible and effective replacement for standard convolutions, enhancing feature extraction and model robustness.
    • The study provides a novel solution for handling orientation variations in semantic segmentation, with potential applications in remote sensing and medical imaging.