Search research articles

Related Concept Videos

Gestalt Principles of Perception

Gestalt Principles of Perception

Gestalt principles provide a framework for understanding how humans perceive objects as unified wholes within their context. These principles are essential in explaining the cognitive processes that make sense of complex visual stimuli by organizing them into coherent groups. One fundamental principle is proximity, which posits that objects located close to each other are perceived as a collective group. For instance, when dots are positioned near one another, the visual system interprets them...

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

Home
Three-dimensional Instance Segmentation Using The Generalized Hough Transform And The Adaptive N-shifted Shuffle Attention.

Home
Three-dimensional Instance Segmentation Using The Generalized Hough Transform And The Adaptive N-shifted Shuffle Attention.

Related Experiment Video

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Three-Dimensional Instance Segmentation Using the Generalized Hough Transform and the Adaptive n-Shifted Shuffle

Desire Burume Mulindwa¹, Shengzhi Du¹, Qingxue Liu²

¹Department of Electrical Engineering, Tshwane University of Technology, Pretoria 0001, South Africa.

Sensors (Basel, Switzerland)

|November 27, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

This study introduces an adaptive n-shifted shuffle (ANSS) attention mechanism with Generalized Hough Transform (GHT) for advanced 3D instance segmentation. The novel approach significantly improves object detection in complex indoor scenes, outperforming existing methods.

Keywords:

3D instance segmentation activation functions attention mechanisms generalized Hough transform

More Related Videos

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Related Experiment Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Area of Science:

Computer Vision
Robotics
Artificial Intelligence

Background:

3D instance segmentation is crucial for applications like autonomous driving and robotics.
Traditional methods struggle with complex indoor scenes, occlusions, and object orientations.
Robust 3D instance segmentation is needed for real-world applications.

Purpose of the Study:

To develop a novel model for robust 3D instance segmentation in indoor scenes.
To address limitations of traditional methods in handling occlusions and complex environments.
To improve the accuracy and reliability of 3D object detection and segmentation.

Main Methods:

Integration of a new adaptive n-shifted shuffle (ANSS) attention mechanism with the Generalized Hough Transform (GHT).

Utilizing an n-shifted sigmoid activation function to enhance feature focus.

Employing a learnable shuffling pattern for spatial feature rearrangement to capture fine-grained details.

Leveraging GHT for robust object localization and detection under noise and occlusion.

Main Results:

The proposed method demonstrates superior performance on the Stanford 3D Indoor Spaces Dataset (S3DIS).
Achieved state-of-the-art results in mean Intersection over Union (IoU) and overall accuracy.
Showcased enhanced ability to capture object boundaries and fine-grained details.
Validated robustness in localizing objects despite heavy noise and partial occlusions.

Conclusions:

The integration of ANSS and GHT provides a robust solution for 3D instance segmentation.
The model shows significant potential for practical deployment in real-world scenarios.
The adaptive attention mechanism effectively handles complex indoor scene challenges.