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

Deconvolution

Deconvolution

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...

Reducing Line Loss

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...

You might also read

Related Articles

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

Sort by

Same author

Thymosin Alpha-1 Restores Chemotherapy-Induced Antitumor Immunity by Chaperoning a MicroRNA Ligand of TLR7 in Dendritic Cells.

Cancer research·2026

Same author

PMF-YOLO: a parameter-efficient multi-scale detector for underwater optical imagery under scattering and nonuniform illumination.

Applied optics·2026

Same author

Dual-branch underwater image enhancement network based on fusion of polarization and color information.

Applied optics·2026

Same author

A pH-responsive ultrasmall Fe-kaempferol nanoplatform ameliorates acute kidney injury by enhancing efferocytosis and metabolic reprogramming.

Journal of nanobiotechnology·2026

Same author

A non-complement role for C1R rewires integrin and death-receptor signaling to drive renal cancer metastasis.

Molecular cancer·2026

Same author

GAS5 mediates notch signaling to exacerbate calcium oxalate-induced renal injury through the NF-κB/NLRP3 axis by promoting macrophage polarization.

Cellular and molecular life sciences : CMLS·2026

Same journal

DSPE-ViT: a lightweight vision transformer with dynamic sparse positional encoding for dense small object detection in UAV imagery.

Frontiers in neurorobotics·2026

Same journal

ST-HONet: Spatio-Temporal Hierarchical Network for long-horizon bimanual visuomotor imitation.

Frontiers in neurorobotics·2026

Same journal

ST-HADP: Spatio-Temporal hierarchical attention diffusion policy for long-horizon generalizable bimanual visuomotor imitation.

Frontiers in neurorobotics·2026

Same journal

EQISP: efficient quantized image signal processing with multi-scale pyramid fusion for resource constrained embodied perception.

Frontiers in neurorobotics·2026

Same journal

Research on embodied agent multimodal perception and real-time path planning algorithms for complex unstructured environments.

Frontiers in neurorobotics·2026

Same journal

NL-YOLOv5: a model with a larger receptive field and the ability to globally acquire features.

Frontiers in neurorobotics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A lightweight multi-dimension dynamic convolutional network for real-time semantic segmentation.

Chunyu Zhang¹, Fang Xu², Chengdong Wu¹

¹Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China.

Frontiers in Neurorobotics

|January 2, 2023

Summary

This summary is machine-generated.

This study introduces LMDCNet, a lightweight network for real-time semantic segmentation. It balances accuracy and efficiency for autonomous driving applications using Multidimensional Dynamic Convolution.

Keywords:

dynamic convolution encoder-decoder lightweight network multi-dimension convolution semantic segmentation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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: Aug 15, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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
Deep Learning
Robotics

Background:

Semantic segmentation is crucial for autonomous driving and micro-robots.
Existing methods struggle to balance inference speed, network parameters, and segmentation accuracy.

Purpose of the Study:

To propose a lightweight network for real-time semantic segmentation.
To address the trade-offs between speed, size, and accuracy in semantic segmentation.

Main Methods:

Introduced the lightweight multi-dimensional dynamic convolutional network (LMDCNet).
Core innovation: Multidimensional Dynamic Convolution (MDy-Conv) utilizing attention and factorial convolution.
Designed an asymmetric encoder (MS-DAB) and decoder (SC-FP) for efficient feature utilization and multi-scale fusion.

Main Results:

LMDCNet achieved 73.8 mIoU at 71.2 FPS on Cityscapes and 69.6 mIoU at 92.4 FPS on CamVid.
The network has only 1.05 M parameters and was trained/inferred on a single 1080Ti GPU.
Demonstrated a strong balance between segmentation accuracy and network efficiency.

Conclusions:

LMDCNet effectively addresses the challenges of real-time semantic segmentation.
The proposed MDy-Conv and network architecture offer a promising solution for resource-constrained applications.
Achieved state-of-the-art performance with significantly reduced computational cost.