Tomasz Lewicki

1. PR #31 adds an optional external blackbody measurement. That improves the accuracy dramatically. 2. Now I display much more comprehensive info about the facial temperature (avg+max+90th percentile), not just...

Yes, it is intended to work on Nvidia Jetson and MIPI-CSI cameras.

Hi @jzx-gooner ! Right now this repo focuses on working with physical cameras. It is possible to connect: - v4l2 sources (for example: logitech C270 webcam) - CSI sources (for...

Are you running the exact same code in https://github.com/NVIDIA-AI-IOT/jetson-stereo-depth/blob/master/depth_pipeline_python/depth_vpi.py or did you modify it somehow? Is it possible that you're overriding the `Camera` class somewhere?

I will try to reproduce that error today in hardware. What JetPack version are you running?

Hi @js1972, thanks for the interest in the project 🙂 Yes, you could possibly use `jetmulticam` to deploy your own TensorRT model, or a pre-trained model from [Nvidia NGC](https://ngc.nvidia.com/catalog/models) with...

@js1972, by defining the pipeline as follows: ```python pipeline = CameraPipelineDNN( cameras=[0, 1, 2, 3, 4, 5, 6, 7], models=[PeopleNet.GPU], save_video=True, save_video_folder="/home/nx/logs/videos" ) ``` on Xavier AGX, you will achieve...

Interesting question, @aafaqin. I assume you're interested in running [detectnet](https://docs.nvidia.com/metropolis/TLT/tlt-user-guide/text/object_detection/detectnet_v2.html) with mobilenet V2 backbone? Similarly as in [jetson-inference](https://github.com/dusty-nv/jetson-inference/blob/master/c/detectNet.cpp) repository? Currently this is not implemented, but feel free to open a...

@aafaqin in general, you could also implement that functionality yourself by: - Downloading [pre-trained model](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/pretrained_detectnet_v2) from TAO - Adding a new module to [jetmulticam.models](https://github.com/NVIDIA-AI-IOT/jetson-multicamera-pipelines/tree/main/jetmulticam/models)

@js1972 As far as the two other modules are concerned, I have to admit I never used them. I'd have to take a look into their API in DS docs...