48 lines
2.0 KiB
HTML
48 lines
2.0 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<title>
|
|
"Portfolio"
|
|
</title>
|
|
</head>
|
|
|
|
<body bgcolor="#F0F8FF">
|
|
<details>
|
|
<summary>Menu</summary>
|
|
<ul>
|
|
<li><a href="./index.html">Home</a></li>
|
|
<li><a href="./embeded_details.html">Embeded Details</a></li>
|
|
<li><a href="./opencv_details.html">OpenCV Details</a></li>
|
|
<li><a href="./photography_details.html">Photography Details</a></li>
|
|
<li><a href="./table.html">Table with filters (not working yet)</a></li>
|
|
<li><a href="./images/institute.png">Institute</a></li>
|
|
</ul>
|
|
</details>
|
|
<h2 align="center">OpenCV Details</h2>
|
|
<hr width="80%" align="center">
|
|
<p align="center">
|
|
<img src="./images/opencv.png" alt="OpenCV" height="150" align="top">
|
|
as mentioned before i love when programs are able to <i>see</i> things <br>
|
|
my experience with opencv started with simple hight level functions like detectCircle or findContours and
|
|
etc...<br>
|
|
Right now i'm crawling deeper into the library , and the idea of standartisation of parameters between different
|
|
cameras is appealig to me <br>
|
|
so i'm trying to understand how all that works from the math side<br>
|
|
Additionally, I'm exploring Re-Identification (ReId) techniques,
|
|
they are used for recognizing and tracking objects across different camera views or consecutive frames.
|
|
</p>
|
|
<hr width="50%" align="center">
|
|
<p>
|
|
One of many projects I've worked on is <a href="https://github.com/OkunElya/ArucoNGP-MapCreator"
|
|
target="_blank">ArucoNGP-MapCreator</a>.<br>
|
|
The idea was to create a relative map of Aruco markers just from photos of pairs (or more) of them.<br>
|
|
It can also estimate the camera's position in the world relative to a specific marker, using only images
|
|
containing any marker.<br>
|
|
It was also my first deep dive into linear algebra.<br>
|
|
</p>
|
|
|
|
</body>
|
|
|
|
</html> |