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

Deconvolution01:20

Deconvolution

368
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...
368
Convolution Properties II01:17

Convolution Properties II

352
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...
352
Convolution Properties I01:20

Convolution Properties I

318
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:
318
Downsampling01:20

Downsampling

340
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
340
Upsampling01:22

Upsampling

378
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
378
Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

551
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...
551

You might also read

Related Articles

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

Sort by
Same authorSame journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Interpretable scRNA-seq Analysis with Intelligent Gene Selection.

Applied biochemistry and biotechnology·2026
Same author

LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Interacted Planes Reveal 3D Line Mapping.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Rejoining fragmented ancient bamboo slips with physics-driven deep learning.

Nature communications·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Nov 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

735

Unmixing Convolutional Features for Crisp Edge Detection.

Linxi Huan, Nan Xue, Xianwei Zheng

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |May 27, 2021
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a context-aware tracing strategy (CATS) to enhance deep edge detection. CATS improves edge localization accuracy by addressing feature and side mixing in convolutional neural networks.

    More Related Videos

    Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
    07:34

    Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

    Published on: August 22, 2019

    8.2K
    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
    07:15

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

    Published on: July 11, 2025

    914

    Related Experiment Videos

    Last Updated: Nov 4, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

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

    Published on: December 15, 2023

    735
    Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
    07:34

    Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

    Published on: August 22, 2019

    8.2K
    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
    07:15

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

    Published on: July 11, 2025

    914

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Image Processing

    Background:

    • Deep edge detectors often suffer from localization ambiguity due to feature and side mixing in convolutional neural networks.
    • This mixing phenomenon negatively impacts the accuracy of edge classification and the fusion of predictions from different network sides.

    Purpose of the Study:

    • To propose a novel context-aware tracing strategy (CATS) for improving the crisp edge detection capabilities of deep learning models.
    • To address the localization ambiguity in deep edge detectors by mitigating feature and side mixing.

    Main Methods:

    • Developed a context-aware tracing strategy (CATS) comprising two modules: a tracing loss for feature unmixing and a context-aware fusion block for side mixing.
    • The tracing loss facilitates better learning of side edges by tracing boundaries, while the fusion block aggregates complementary edge information.

    Main Results:

    • The proposed CATS significantly enhances localization accuracy when integrated with existing deep edge detectors.
    • Using a VGG16 backbone on the BSDS500 dataset, CATS improved the F-measure (ODS) of RCF and BDCN by 12% and 6% respectively, without morphological non-maximal suppression.

    Conclusions:

    • The context-aware tracing strategy (CATS) is an effective method for improving edge localization in deep edge detection.
    • CATS offers a valuable approach to enhance the performance of modern deep edge detectors, particularly in scenarios requiring precise edge localization.