This tutorial outlines a process developers can follow to create a video analytics plugin for use with Nx Meta products.
The tutorial will not teach the reader how to use neural networks and algorithms for computer vision tasks; instead, it will show developers how to use the Metadata SDK to write a video analytics plugin (which might use third-party neural network frameworks for real-world tasks). The plugin is a C++ shared library.
The plugin created will detect and track people, cats, and dogs.
For object detection, we will use the OpenCV DNN module in conjunction with the pre-trained MobileNet SSD Caffe model. For object tracking, we will use the tbm (tracked by matching) OpenCV module.
The following sections of the tutorial will cover the step-by-step to
- download the source code;
- prepare the workspace;
- start the project using a template;
- load and enable plugin inside VMS Server;
- add an object detector, send object metadata to the Server; and
- add object tracking functionality;
- add analytics event functionality.
Comments
0 comments
Article is closed for comments.