Upcoming with FW 7.10 and CM 6.20, Camera Trainer is a licensable Intelligent Video Analytics module that allows uses to define objects of intereste and train their own detectors for them based on examples of target objects and non-target objects. In contrast to the moving objects detected in general by IVA 7.10, Camera Trainer allows detection of both moving and non-moving objects, separates and immediately classifies them. Training can be done both on live video as well as on recordings available through the respective camera. The resulting detectors can be down- and uploaded for distribution to other cameras.
The attached fact sheet lists the cameras that support Camera Trainer. The attached technical note describes in-depth what Camera Trainer is, how it works, what to use it for and what not, and how to configure it. The configuration is also shown in the following how-to videos:
Setup Camera Trainer
Configure Camera Trainer Task
Backup Camera Trainer Configuration - Method 1
Backup Camera Trainer Configuration - Method 2
Setup VCA Masking