Virtual camera is created only using opencv and numpy. It simulates a camera where we can control all its parameters, intrinsic and extrinsic to get a better understanding how each component in the camera projection matrix affects the final image of the object captured by the camera.

This is a fun project I created to motivate computer vision enthusiasts and to highlight the importance of understanding fundamental concepts related to image formation in a camera.

What is a camera calibration, why is it necessary, and how do we compute it?

Lightweight moving object detection method (pedestrians, cyclists, vehicles) which is developed for devices with limited computational power (Beaglebone, Raspberry).

Estimating the fundamental and essential matrices of input stereo images, and then reconstructing the 3d points by triangulation.

Examples of camera calibration, camera parameters visualization

Select regions of interest (ROI) from large-area aerial oblique data to create a small dataset containing the ROI.