This repository provides a basic starting point for computer vision projects using C++. The main objective is to practice using the OpenCV library for computer vision tasks and to understand the underlying concepts.
- Motivation
- Pre-requisite
- Installation
- Usage
- Future Improvement
- Contact
- License
I created this repository to understand computer vision and its applications better. By working on practical examples and hands-on projects, I aimed to build a strong foundation in computer vision concepts. I've included code and various experimental techniques to encourage continuous learning and skill development. My main goal for the future is to build a computer vision project that can understand a scene and find meaning from a short video clip of 2 to 5 seconds.
- Operating System: Ubuntu 20.04 or future version
- Libraries: Opencv (4.11.1), make (4.3), cpp (11.4.0)
Should have understanding of cpp programming and makefile to compile cpp codes. You can learn image formats like jpeg, png etc from you tube. Also conceptual understanding of video compression technique like mpeg, avi etc.
Please check specific version for installation which mentioned above, otherwise program will not compile.
Instruction for compiling and running program already provided in README file of every folder.
- Expand the repository with more practical labs and small programs to cover additional computer vision topics.
- Port the existing C++ code to Python for ease of use and accessibility.
- Enhance project features:
- Integrate YOLO pre-trained models or custom-trained models to improve object detection accuracy.
- Implement parallel processing using pthreads or CUDA to enhance performance.
- Add support for multiple image and video formats.
Distributed under the GPL License.