Building the baseline model

In this section, we will be looking at the coding part. You can refer to the code given at this GitHub link: https://github.com/jalajthanaki/Real_time_object_detection/tree/master/base_line_model.

First, download the project from the given link and install OpenCV, as per the information given earlier in this chapter. When you download this project folder, there is a pre-trained MobileNet SSD that has been implemented using the caffe library, but here, we are using the pre-trained binary model. We are using OpenCV for loading the pre-trained model as well as streaming the video feeds from the webcam.

In the code, first, we specify the libraries that we need to import and define the command-line arguments that will be used to run the script. We need to provide the parameter file and the pre-trained model. The name of the parameter file is MobileNetSSD_deploy.prototxt.txt and the filename for the pre-trained model is MobileNetSSD_deploy.caffemodel. We have also defined...