Tool/software:
Hi,
I am testing IWRL6432BOOST people tracking demo with ceil-mount scenario.
So far the result is not good enough as expected.
Here is the CFG I'm testing right now.
I copy the CFG from People Tracking demo for IWRL6432BOOST, modified the sensor position, boundaries, and tracking parameter (original one cause a lot of ghost object).
sensorStop 0 channelCfg 7 3 0 chirpComnCfg 16 0 0 128 4 28 3 chirpTimingCfg 6 32 0 40 60 frameCfg 2 0 200 64 100 0 antGeometryCfg 0 0 1 1 0 2 0 1 1 2 0 3 2.418 2.418 guiMonitor 2 3 0 0 0 1 0 0 1 0 0 sigProcChainCfg 16 8 3 2 8 8 1 0.3 cfarCfg 2 8 4 3 0 8.0 0 0.5 0 1 0 0 aoaFovCfg -60 60 -40 40 rangeSelCfg 0.1 4 clutterRemoval 1 compRangeBiasAndRxChanPhase 0.0 1.00000 0.00000 -1.00000 0.00000 1.00000 0.00000 -1.00000 0.00000 1.00000 0.00000 -1.00000 0.00000 adcDataSource 0 adc_data_0001_CtestAdc6Ant.bin adcLogging 0 lowPowerCfg 0 factoryCalibCfg 1 0 40 0 0x1ff000 boundaryBox -3 3 -2 2.5 -0.5 3 sensorPosition 0 0 2.8 0 90 staticBoundaryBox -2.5 2.5 -1.5 2.3 0 2.5 gatingParam 3 2 2 2 4 stateParam 3 50 100 100 5 300 allocationParam 10 12 0.1 2 0.5 20 maxAcceleration 0.4 0.4 0.1 trackingCfg 1 2 100 6 61.4 191.8 100 presenceBoundaryBox -3 3 -2 2.5 -0.5 3 baudRate 1250000 sensorStart 0 0 0 0
When I'm searching the solution to fine tune the CFG, I notice that in the Overhead 3D People Tracking User Guide, it provides different CFGs for Wall-mount and Ceil-mount scenarios and describes that they need different way of estimating the angle of each detected dynamic point (3D_people_tracking_detection_layer_tuning_guide.pdf).
I am curious about if IWRL6432BOOST required same adjustment and if TI provides reference CFG for Ceil-mount for testing?
