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

Search research articles

Related Experiment Video

Updated: Mar 29, 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

A Method for Industrial Smoke Video Semantic Segmentation Using DeffNet with Inter-Frame Adaptive Variable Step Size

Jiantao Yang¹, Hui Liu¹

¹Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China.

Sensors (Basel, Switzerland)

|March 28, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Response of Tomicus yunnanensis (Coleoptera: Scolytinae) to infested and uninfested Pinus yunnanensis bolts.

Journal of economic entomology·2010

Same author

Construction of novel tumor necrosis factor-alpha mutants with reduced toxicity and higher cytotoxicity on human tumor cells.

Science in China. Series C, Life sciences·2010

Same author

Impact of MSW landfill on the environmental contamination of phthalate esters.

Waste management (New York, N.Y.)·2010

Same author

[Comparison of Cj1136, Cj1138 and Cj1139 genes among Campylobacter jejuni strains].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2010

Same author

Alveolar stability under different combinations of positive end-expiratory pressure and tidal volume: alveolar microscopy in isolated injured rat lungs.

Chinese medical journal·2010

Same author

[Research on permeability of landfill's body in primary compression].

Huan jing ke xue= Huanjing kexue·2010

This study introduces an adaptive frame selection algorithm using fuzzy logic to improve industrial smoke video segmentation. The method optimizes temporal processing for better accuracy and speed in DeffNet.

Area of Science:

Computer Vision
Artificial Intelligence
Image Processing

Background:

Segmenting non-rigid objects like industrial smoke in videos is challenging due to complex appearance variations and irregular deformations.
Effective utilization of temporal information is crucial but difficult to achieve with current methods.
Existing DeffNet models require enhancement for precise industrial smoke segmentation.

Purpose of the Study:

To develop a novel adaptive frame selection algorithm for industrial smoke video segmentation.
To dynamically optimize the temporal processing step size within the DeffNet framework.
To enhance the efficiency and accuracy of non-rigid object segmentation in industrial settings.

Main Methods:

Implemented a fuzzy logic control system to dynamically adjust the temporal processing step size.

Keywords:

DeffNet LR-ASPP adaptivity fuzzy control non-rigid deformation smoke segmentation

Related Experiment Videos

Last Updated: Mar 29, 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

Utilized Structural Similarity Index (SSIM) and Normalized Cross-Correlation (NCC) to quantify inter-frame variations.

Designed a five-rule fuzzy system with Gaussian membership functions shaped by K-means clustering.

Main Results:

Achieved a segmentation performance of 84.27% Intersection over Union (IoU).
Maintained a high inference speed of 39.71 Frames Per Second (FPS).
Demonstrated seamless integration of the lightweight algorithm as a front-end module for DeffNet.

Conclusions:

The proposed adaptive frame selection algorithm significantly improves DeffNet's industrial smoke video segmentation performance.
The method offers an efficient, scene-specific solution for temporal modeling in non-rigid object segmentation.
This approach provides a practical enhancement for real-time industrial smoke monitoring systems.