search

NVIDIA-AI-IOT / deepstream-occupancy-analytics

This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to build real-time occupancy analytics applications for smart buildings, hospitals, retail, etc. The application is based on deepstream-test5 sample application.
MIT License
221 stars 73 forks source link

kafka message #32

Open vuminhduc97 opened 3 years ago

vuminhduc97 commented 3 years ago

I fixed mgsconv.txt

[analytics0]

enable=1 id=0

description=Vehicle Detection and License Plate Recognition

source=rtsp0 version=1.0 [analytics1] enable=1 id=1

description=Vehicle Detection and License Plate Recognition 1

source=rtsp1 version=1.0

but kafka topic only show [analytics0]

"messageid" : "69995786-a460-4e56-afaa-f12d3dc29d2b", "mdsversion" : "1.0", "@timestamp" : "2021-06-30T07:34:07.107Z", "analyticsModule" : { "RF" : 1.0, "Entry" : 0.0, "Exit" : 0.0, "id" : "0", "description" : "", "source" : "rtsp0", "version" : "1.0", "confidence" : 0.0

while osd still show both 2 analytics sources in screen

mjhuria commented 3 years ago

could you please send the config file to test on?

vuminhduc97 commented 3 years ago

My config files below: test5_config_file_src_infer_tlt.txt

dstest5_msgconv_sample_config.txt

config_nvdsanalytics.txt

cfg_kafka.txt