Page History

A neurotracker is designed for detecting any objects in a video image and calculating the metadata. The neurotracker operation involves the use of a neural network, which allows to reduce the computation load and improve the quality of the object detection. Any detection tool can be implemented on the basis of the neurotracker. The neurotracker independently receives the necessary tracks, both with moving and with completely motionless (for the whole analysis period) objects. As in all situations related to neuroanalysis, the quality of work and the resource consumption of the neurotracker directly depend on the optimization of the neural network model used.

Before you start setting up the neural filter, you should contact the AxxonSoft technical support and request the model files of the trained neural networks. Technical support specialists will request from you the data needed to prepare the models, and then will provide you with the *.ann and*.txt files for each neurotracker model. These files should be distributed to all servers where it is planned to use the neurotracker.

The following VMDA detection tools can be created on the basis of the neurotracker:

• Neurotracker counter (for periodical events notifying the number of neurotracked objects).
• VMDA detection tools: Line crossing, Motion in the area (any movement, entering the area, exiting the area, appearance in the area, disappearance in the area, stop in the area, staying in the area for more than 10 seconds, abandoned objects)

...

• .