Direct Step Edge Detection
Project description
Direct Step Edge Follower
DSEF Package
The Direct Step Edge Follower (DSEF) is a edge-following algorithm designed for high-precision edge detection with low computational cost. It employs stepwise directional refinement and kernel-based statistical testing to enhance accuracy, particularly in challenging lighting conditions.
Citation
To cite DSEF in your research, please cite as:
@article{Sivertsen2025DSEF,
author = {Agnar Sivertsen and Fabio A. A. Andrade and Marcos Moura and Carlos A. M. Correia and Mariane R. Petraglia},
title = {Direct Step Edge Follower: a novel edge follower algorithm applied to solar panels inspections with Unmanned Aerial Vehicles},
journal = {Preprint},
year = {2025},
month = {April},
url = {https://www.researchgate.net/publication/390370984_Direct_Step_Edge_Follower_a_novel_edge_follower_algorithm_applied_to_solar_panels_inspections_with_Unmanned_Aerial_Vehicles}
}
Speeds
The DSEF can work in three modes, or speeds, are described in the table below:
| Parameter | Low | Medium | High |
|---|---|---|---|
| $\Delta s$ (EdgeSearch step) | dist ⁄ 80 | dist ⁄ 60 | dist ⁄ 40 |
| $\Delta \ell$ (EdgeFollow step) | diag ⁄ 200 | diag ⁄ 100 | diag ⁄ 50 |
| $\Delta \theta$ (Angle Res.) | $\Omega$ ⁄ 90 | 4 $\Omega$ ⁄ 90 | 10 $\Omega$ ⁄ 90 |
| $N_{\theta}$ (LUT size) | 360 ⁄ $\Delta \theta$ | 360 ⁄ $\Delta \theta$ | 360 ⁄ $\Delta \theta$ |
Where $\mathrm{dist} = \sqrt{(u_{\mathrm{end}}-u_{\mathrm{start}})^2 + (v_{\mathrm{end}}-v_{\mathrm{start}})^2}$ and $\mathrm{diag} = \sqrt{(\mathrm{Width})^2 + (\mathrm{Height})^2}$
Lower speeds have more accuracy, due to the smaller steps, and higher speeds can have less accuracy but are faster.
How to use
The examples of DSEF can be found in the following links:
Simple Implementation of DSEF Search and Follow
Implementation and Comparison between the different Speed Modes in DSEF
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file dsef-0.3.0.tar.gz.
File metadata
- Download URL: dsef-0.3.0.tar.gz
- Upload date:
- Size: 21.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
770ae2723b3e6b18739f17ce7f630519891a9dae83d2aa5572cfcdd892690bbc
|
|
| MD5 |
7ba7a5169d741f988a01d2008cc17ca2
|
|
| BLAKE2b-256 |
b5d70859e24cfbe2dba17a23262bddad14cc08300b8181c2f5fc173d3549b10d
|
File details
Details for the file dsef-0.3.0-py3-none-any.whl.
File metadata
- Download URL: dsef-0.3.0-py3-none-any.whl
- Upload date:
- Size: 22.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3801652c2a2d1bd048ab6cbfc47bf3c4e03bce46d1ac0be552468b3cb3dbb910
|
|
| MD5 |
22361a0e081f20abd98e498a5326ef33
|
|
| BLAKE2b-256 |
3921fdb8ddc6f00abe35936fe25bfc3ce8ec9a58930b3c7b55ad1471e06b4173
|