Types of detection tools for Intellect

Motion Detection (key frames)

Base detection tool activated when the camera is armed.

The detection tool is applicable only for H.264, H.265 codecs. The platform is calculated for decoding by key frames if the GOP=25 (every 25th frame is the key frame).

Service detection tools:

• Focus detection tool.
• Stability detection tool.
• Background change detection tool.
• Blind detection tool.
• Cover detection tool.

The platform is calculated for one service detection tool (any of the listed).

The detection tool is applicable only for H.264, H.265 codecs. The platform is calculated for decoding by key frames if the GOP=25 (every 25th frame is the key frame).

VMDA detection tools based on object trajectory tracker.

VMDA detection tools based on object tracker with use of a neural filter and GPU resources.

VMDA detection tools based on neural tracker as part of Intellect Detector Pack with use of CPU resources.

The frame rate specified during the Neurotracker module configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher.

VMDA detection tools based on neural tracker as part of Intellect Detector Pack with use of VPU resources.

The frame rate specified during the Neurotracker module configuration (the Frames processed per second parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher.

The results are given for a standard size neural network*.

Traffic flows information gathering subsystem based on IntelliVision vehicle detection as part of Auto Intellect software package.

Face detection tool based on the Tevian recognition module as part of Face Intellect software package.

When calculating the platform using this detection tool, only the resources for face detection and their vectorization are taken into account. The load from comparing faces with the reference database is not taken into account, because usually a separate server is provided to perform this function.

Recognizer of railway passenger carriage numbers based on the IntLab module as part of Auto Intellect software package.

1. Optimal resolution is 704*288 OR 640*360 and fps=25. With a higher resolution, the module will not be able to process all frames, which will reduce the quality of operation.
2. Main channel has the same resource consumption as subordinate channel.

1. Optimal resolution is 704*288 OR 640*360 and fps=25. With a higher resolution, the module will not be able to process all frames, which will reduce the quality of operation.
2. Main channel has the same resources consumption as subordinate channel.

People counter detection

People counter detection tool that is a part of Intellect Detector Pack.

Optimal parameters for this detection tool are resolution of 800x600 / 640x360 / 640x480 / 320x240 and FPS in range from 24 to 30. If specified parameters of the video stream do not meet these conditions, then when you select this detection tool the resolution is set to 320x240 and FPS=24.

Fire detection tool (CPU, 0.1fps)

Smoke detection tool (CPU, 0.1fps)

Fire and smoke detection tools based on neural network as part of Intellect Detector Pack with use of CPU resources.

The frame rate specified during the detection tool configuration (the Number of frames for analysis and output parameter) is indicated in brackets. This is the number of fps processed by the module; the frame rate of the incoming video stream is usually higher.