I use the default profile.cfg from mmWave Demo Visualizer (https://www.ti.com/video/5703026974001) for people detection scenario.
In the people counting video (https://www.ti.com/video/5703026974001), the object points detected by radar are so stable/robust.
But I found that the radar detected object points are not stable enough.
* The static people shows up sometimes, and are missing sometimes.
* When people are moving, there are many noisy object points shown.
Here is my profile.cfg:
% *************************************************************** % Created for SDK ver:02.00 % Created using Visualizer ver:2.1.0.3 % Frequency:77 % Platform:xWR16xx % Scene Classifier:best_range_res % Azimuth Resolution(deg):15 % Range Resolution(m):0.044 % Maximum unambiguous Range(m):9.02 % Maximum Radial Velocity(m/s):1 % Radial velocity resolution(m/s):0.13 % Frame Duration(msec):100 % Range Detection Threshold (dB):15 % Doppler Detection Threshold (dB):15 % Range Peak Grouping:enabled % Doppler Peak Grouping:enabled % Static clutter removal:disabled % *************************************************************** sensorStop flushCfg dfeDataOutputMode 1 channelCfg 15 3 0 adcCfg 2 1 adcbufCfg -1 0 0 1 0 profileCfg 0 77 429 7 57.14 0 0 70 1 256 5209 0 0 30 chirpCfg 0 0 0 0 0 0 0 1 chirpCfg 1 1 0 0 0 0 0 2 frameCfg 0 1 16 0 100 1 0 lowPower 0 1 guiMonitor -1 1 1 0 0 0 1 cfarCfg -1 0 0 8 4 4 0 5120 cfarCfg -1 1 0 4 2 3 0 5120 peakGrouping -1 1 1 1 1 255 multiObjBeamForming -1 1 0.5 clutterRemoval -1 0 calibDcRangeSig -1 0 -5 8 256 extendedMaxVelocity -1 0 bpmCfg -1 0 0 1 lvdsStreamCfg -1 0 0 0 nearFieldCfg -1 0 0 0 compRangeBiasAndRxChanPhase 0.0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 1 0 measureRangeBiasAndRxChanPhase 0 1.5 0.2 CQRxSatMonitor 0 3 5 123 0 CQSigImgMonitor 0 127 4 analogMonitor 1 1 sensorStart
Here is the video:
Could you give me some suggestions?
Thanks.