Related Experiment Video
Updated: Jan 25, 2026
07:49
Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
Published on: November 26, 2019
8.5K
Building Corner Detection in Aerial Images with Fully Convolutional Networks
Weigang Song1,2, Baojiang Zhong3,4, Xun Sun5,6
1School of Computer Science and Technology, Soochow University, Suzhou 215006, China. m1273152693h@163.com.
Sensors (Basel, Switzerland)
|April 26, 2019
Summary
This study introduces a new method for detecting building corners in aerial images using fully convolutional networks (FCNs). The approach significantly improves accuracy over existing corner detectors for city modeling and geo-localization tasks.
Area of Science:
- Computer Vision
- Remote Sensing
- Artificial Intelligence
Background:
- Generic corner detectors struggle with aerial imagery, failing to differentiate building corners from other features like trees and shadows.
- Fully convolutional networks (FCNs) have shown promise in semantic image segmentation for object recognition.
Purpose of the Study:
- To develop an improved method for detecting building corners in aerial images.
- To enhance the accuracy of building corner detection for applications like city modeling and geo-localization.
Main Methods:
- A DeepLab model with improved FCNs and fully-connected conditional random fields (CRFs) was trained end-to-end for building region segmentation.
- Morphological opening operations were applied to refine segmentation accuracy.
- A scale-space detector was used to identify corner points on building contour curves.
Main Results:
- The proposed approach achieved an F-measure of 0.83 on the test image set.
- The method significantly outperformed existing state-of-the-art corner detectors.
Conclusions:
- The FCN-based approach effectively detects building corners in aerial images.
- This method offers a substantial improvement for structural information extraction in aerial imagery.
Related Concept Videos
01:17Convolution Properties II
583
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...
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...
583
01:20Convolution Properties I
571
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:
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:
571
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
02:26Protein Networks
2.8K
2.8K
02:18Network Covalent Solids
16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K
01:27Movement Joints in Buildings
340
Movement joints in buildings are essential design elements that accommodate inevitable motions caused by various factors such as temperature changes, moisture content variations, and structural deflections. These motions, if not considered in design and construction, can lead to unsightly or dangerous damage. Movement joints are incorporated in different forms to manage these stresses and allow materials to move without causing distress.
The simplest type of movement joints, working joints, are...
The simplest type of movement joints, working joints, are...
340