Page History

Scene analytics detection tools (VMDA) based on object tracker

Scene analytics detection tools (VMDA) based on object tracker with use of a neural filter and GPU resources

For each track, one image per second is sent to neural network for classification.

• The NVIDIA GeForce GT 730 graphics card is capable of processing up to 70¹ classifications² per second.

• The NVIDIA GeForce GTX 1070 graphics card is capable of processing up to 220³ classifications per second.

• The Intel Neural Compute Stick 1 (movidius I) is capable of processing up to 58 classifications per second⁴.

• The Intel Neural Compute Stick 2 (movidius II) is capable of processing up to 200 classifications per second⁴.

• Several video cards can be used in one system.
• For example, if you need to track 9 persons per second on 10 cameras, then a GeForce GTX 1070 or similar video card is suitable.
• Up to two Intel Neural Compute Stick can be used in one system.

Scene analytics detection tools based on neural tracker with use of CPU resources

The frame rate specified during the Neurotracker object 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.

Scene analytics detection tools based on neural tracker with use of VPU resources

The frame rate specified during the Neurotracker object 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.

1 Mustang-V100-MX8 (Intel HDDL) card processes up to 60 video channels regardless of video resolution.

Multiple Mustang-V100-MX8 (Intel HDDL) cards can be used on the server.

The results are given for a standard size neural network⁵

Scene analytics detection tools based on neural tracker with use of GPU resources

The frame rate specified during the Neurotracker object 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.

1 NVidia Quadro RTX 4000 card, regardless of the codec (H.264, H.265), processes up to 73 channels of 640x360 video with 25 fps; in case of 1920x1080 video with 25 fps, the number of channels depends on the codec: up to 52 channels for H.264, and up to 73 channels for H.265. For details, see GPU performance for Axxon Next detection tools

Multiple NVidia Quadro RTX 4000 cards can be used on the server.

The results are given for a standard size neural network⁵

The results are given for a neural tracker with 1 active sub detection tool Motion in area

Scene analytics detection tools based on neural tracker with use of GPU resources and high-precision neural network

The frame rate specified during the Neurotracker object 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.

1 NVidia Quadro RTX 4000 card, regardless of the codec (H.264, H.265), processes up to 61 channels of 640x360 video with 25 fps; in case of 1920x1080 video with 25 fps, the number of channels depends on the codec: up to 52 channels for H.264, and up to 61 channels for H.265. For details, see GPU performance for Axxon Next detection tools

Multiple NVidia Quadro RTX 4000 cards can be used on the server.

The results are given for a standard size neural network⁵

The results are given for a neural tracker with 1 active sub detection tool Motion in area