Characteristics of Stereo Imaging using Non-Identical Cameras for Object Detection

The fear from the continuous spreading of the Covid-19 pandemic had put lot of restrictions on the movement of goods around the world. In Egypt, the importing of goods especially electronic products from many countries including China was crucial to the research and educational purposes. The restrictions had stopped the importing of many electronic devices from China including cameras. Object detection and identification were among the hot topics of research in our university which depended mainly on imported cameras. In this paper we tackle the problem of setting up stereo cameras using old non identical cameras to do object detection. The selection of the cameras was not optional since we had to use what we found in our old laptops. OpenCV and Python programming commands were used to set the two cameras to obtain equally clear images as much as possible. A disparity map was then calculated using openCV and its accuracy was then discussed. Accuracy was dependable on the sharpness of the cameras used, Gamma parameter, number of pixels per image and matching algorithm to match the two images obtained using the stereo cameras.