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

No custom msgconv config file #37

Closed Foglia-m closed 3 years ago

Foglia-m commented 3 years ago

Hi, I don't think you provide the dstest5_msgconv_sample_config.txt file you used in the example as there is no such element as entry and exit when I run your example: the file provided in the repo can't be the same as the one that creates the displayed logs in the gif ( no entry / exit and count such as those displayed in your example). My logs look like the following: "messageid" : "d61a8342-c60c-43d9-9fbb-c62b1fe2a749", "mdsversion" : "1.0", "@timestamp" : "1970-01-01T00:00:00.000Z", "place" : { "id" : "0", "name" : "HWY_20_AND_LOCUST__EBA", "type" : "intersection/road", "location" : { "lat" : 30.32, "lon" : -40.549999999999997, "alt" : 100.0 }, "entrance" : { "name" : "C_127_158", "lane" : "Lane 1", "level" : "P1", "coordinate" : { "x" : 1.0, "y" : 2.0, "z" : 3.0 } } }, "sensor" : { "id" : "HWY_20_AND_LOCUST__EBA__4_11_2018_4_59_59_508_AM_UTC-07_00", "type" : "Camera", "description" : "Aisle Camera", "location" : { "lat" : 45.293701446999997, "lon" : -75.830391449900006, "alt" : 48.155747933800001 }, "coordinate" : { "x" : 5.2000000000000002, "y" : 10.1, "z" : 11.199999999999999 } }, "analyticsModule" : { "id" : "XYZ", "description" : "", "source" : "OpenALR", "version" : "1.0" },

Can you give me a bit more insight on that difference if there are elements I didn't understand? Thank you

monjha commented 3 years ago

Hi Foglia,

Did you update the bin file: libnvds_msgconv.so?

Foglia-m commented 3 years ago

Hi, Thank you for the quick answer, do you mean I should change the /opt/nvidia/deepstream/deepstream-5.1/sources/libs/nvmsgconv/ lib, ie changing the makefile and recompile? I don't see where the original libnvds_msgconv.so is in the code (without this repo), I'm running deepstream on a x86 using the docker 5.1 triton image.

monjha commented 3 years ago

Hi,

No, you don't have to recompile anything. We already provided the lib in the repo. Original libnvds_msgconv.so is at /opt/nvidia/deepstream/deepstream-@DS_VERSION/lib/libnvds_msgconv.so with https://github.com/NVIDIA-AI-IOT/deepstream-occupancy-analytics/tree/master/bin/x86 Thanks!

Foglia-m commented 3 years ago

Ok thank you so much, you guys did such a great job, I can thank you enough.