https://github.com/avinash793/object-tracking-software
Implementation of Lucas Kanade Tracking system using six parameter affine model and recursive Gauss-Newton process.
https://github.com/avinash793/object-tracking-software
affine-transformation computer-vision gauss-newton-method lucas-kanade-algorithm lucas-kanade-tracker object-tracking opencv opencv4 python3 tracking-algorithm video-object-tracking
Last synced: 2 months ago
JSON representation
Implementation of Lucas Kanade Tracking system using six parameter affine model and recursive Gauss-Newton process.
- Host: GitHub
- URL: https://github.com/avinash793/object-tracking-software
- Owner: Avinash793
- Created: 2018-02-07T18:11:02.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2024-01-15T08:09:17.000Z (over 1 year ago)
- Last Synced: 2025-03-24T16:11:06.598Z (3 months ago)
- Topics: affine-transformation, computer-vision, gauss-newton-method, lucas-kanade-algorithm, lucas-kanade-tracker, object-tracking, opencv, opencv4, python3, tracking-algorithm, video-object-tracking
- Language: Python
- Homepage:
- Size: 2.78 MB
- Stars: 33
- Watchers: 2
- Forks: 12
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Object Tracking
Track moving object in a given video.
## Requirements
* Numpy >= 1.24.3
* OpenCV >= 4.9.0 (latest as of 2024)
## Description
We have implemented Object Tracking Software which tracks moving object
in a given video. We have implemented in two ways:
1. From scratch using **Lucas Kanade Tracking** algorithm which uses six parameter affine model
and recursive Gauss-Newton algorithm. Implemented the research paper Lucas-Kanade 20 Years On: by
simon Baker (Microsoft Computer vision researcher).
2. using OpenCV library.
Then, We have done the detailed comparative analysis of both implementation which can be found in the attached pdf.
## How To Run
1. Put video in `video/` folder, or you can use provided sample video `slow_traffic.mp4` .
2. Run:
```shell
python3 lucas_kanade_scratch.py
```
or
```shell
python3 lucas_kanade_opencv.py
```
3. Enter video filename along with path like:
```shell
Enter video filename along with path: video/slow_traffic.mp4
```
Enter "0" to use your real time system camera for video.