As the target moves from the center of the image, it automatically adjusts the camera’s physical position using pan, tilt or zoom commands until the target is again centered in the camera’s FOV. This typically continues until the target can no longer be detected, a user takes manual control or after a set timeout period.
RELATED: 11 Components of a Secure School Front Entrance
The feature obviously has considerable value in the design of a security system as it acts as a force multiplier, allowing the first responder to react to a situation without the need to also control the camera. It can also prove useful for remote deployments to document activities in and around a facility without the need for operator intervention.
Functionality Can Reside on Camera, Edge Device or Server
One factor to note is that our definition did not refer to where this capability resides within a security solution. You may assume this is a function of the camera and in order to achieve this functionality you would need to procure new cameras. This is not the case. Camera auto follow capability can physically reside in three places: the camera, an edge device or a server.
Each type of implementation has its pros and cons. The good news is you don’t need to design a brand new system or replace all of your existing cameras to acquire this functionality. The use of edge devices and server software allows existing p/t/z cameras to auto-follow as well.
Another subtle but important point to notice in our definition of camera auto follow is the continued reference to “controlling pan, tilt or zoom.” When considering what flavor of camera auto follow you would prefer, it is worthwhile to note that oftentimes the algorithm only controls pan and tilt.
There are good reasons for this, one of which is the fact that the zoom function for many cameras can be slow. This can be due to mechanical limitations, it can also be due to command timing whereby a zoom command may not be able to be executed concurrent with a pan and tilt command.
Whatever the reason, a slow zoom can provide time for the target to move out of the FOV, so when the zoom is complete there is no object to detect. Another complexity of zoom can be the camera’s ability to remain focused during the zoom event. This period of unfocused video can also cause issues with detection, creating the same scenario where the target moves during the zoom action and there is no object present when the zoom action is completed. So what are the ramifications of not having zoom control with camera auto follow capability? In some situations, there may not be any. If you are monitoring a fairly small area there may not be the need to have this zoom feature. The camera can track the object around the general area with a good view of the target.
The downside is eventually the object may move far enough away that it will be too small to be of viewing value or have too few pixels for the algorithm detection software to recognize. As you start to move to more distant ranges, the ability to utilize a camera’s zoom does have significant value. If the intent is for camera auto follow to perform at varying distances, then it is important to ask about zoom capability.
Deployment Scenario: Single Camera vs. Multiple Cameras
Another point that causes common confusion in the realm of camera auto follow is the idea of single or multiple camera follow. Either of these deployments can be further confused by the idea of camera hand off. So it’s come time to further clarify our definition of camera auto follow: The capability to automatically control a p/t/z camera’s pan, tilt or zoom in an attempt to keep a specified object centered in the camera’s FOV, using only the video information provided by that same p/t/z camera.
