If necessary, create and configure the NeuroTracker VMDA detection tools on the basis of the Neurotracker object. Select the required neural network file for the neural filter ( 2).įrom the Device drop-down list ( 3), select the device on which the neural filter will operate. To set up a neural filter, do the following:
For example, the neural tracker detects all freight trucks, and the neural filter leaves only those tracks that correspond to trucks with cargo door open. You can use the neural filter to sort out video recordings featuring selected objects and their trajectories. On the captured video frame, sequentially set the nodal points of the area in which the objects will be detected by left-clicking the mouse button ( 3).Click the Surveillance territory button ( 2).Click the Start video button ( 1) to capture a video frame.Set the monitoring area on the video image:Ĭlick the Setup button ( 11). Only stationary objects - an object is considered stationary if during the entire existence of its track it has not shifted by more than 10% of its width or height.Using this parameter may reduce the number of false positives. Only moving objects - an object is considered to be moving if during the entire lifetime of its track it has shifted by more than 10% of its width or height.All objects - moving and stationary objects.From the Process drop-down list ( 10) select which objects should be processed by the neural network:.For example, when a larger car completely overlaps a smaller one. This parameter can be useful in situations where one object in the frame temporarily overlaps another. In the Track hold time (s) field ( 9), specify the time in seconds after which the object track is considered lost.
At the same time, a low value of this parameter can lead to false positives. The higher the value of this parameter, the longer it will take from the object detection moment to the display of its track.
0 kommentar(er)
