havocfixer/mmmesh

mmmesh's Issues

PC Cloud adaptation to IWR6843ISK-ODS

Hi, thank you so much for your work. Really appreciated :)
I am using IWR6843ISK-ODS with DCA1000EVM to capture .bin file. The antenna pattern in 6834ISK-ODS and 1843BOOST are different and would like your expertise on what changes shall be done in the script to adapt to 6843ISK-ODS for point cloud generation alone.
The antenna pattern and virtual antennas are as shown:
https://drive.google.com/file/d/1bnAqMHeS1rCOPlplNw3qUwXRa7Os5Wmm/view?usp=sharing
Thank you once again.

Why the output dim of CombineModule is 68 not 144?

Hello,
It is a great work! But there is a question about the output dim of CombineModule in your code. It equals 9*6+3+10+1 that is not same as the num 10+144+1+3 =157 in your paper. Why the num of joints is 9? Wish you could answer me.
Thanks!

The dataset

Hi, is there any way I can access the dataset?

Error capturing data from mmWave Radar?

Hi, I am trying to use your code in 1.mmWave_data_generation to capture the real-time data from the AWR1843BOOST radar but every time I try to read data using getFrame() method it gives me readItem as "wait new frame" and itemNum as -2. Can you tell me could be the possible reason for this?
I am using the ubuntu 20.04 subsystem for windows 10 as administrator to run capture.py file.

Thanks!

elevation resolution

I appreciate your great work.
In pc_generate.py, you are trying perform FFT along 4 virtual antennas.
elevation_ant = virtual_ant[2 * num_rx:, :]
However, from the TI website (https://e2e.ti.com/support/sensors-group/sensors/f/sensors-forum/1018413/iwr1843boost-range-elevation-heatmap-processing), they suggest perform FFT along two separate rows of virtual antennas.
Does your method follow the same strategy provided by TI?

the question about capture.py

Thanks for you great work!
The radar type I use is IWR1443. When I run capture.py in step 1-mmWave_data_capture, I can get mmWave radar data successfully and the data is not empty. But it still prints “Packet Lost! Please discard this data.”
How can I deal with this problem?

How to convert joint coordinates SMPL parameters?

Hi,

I am very impressed by your work, I am now trying to capture some data with a similar setting as yours. Converting radar ADC data to PC data is very clear, but I wonder how to convert joint coordinates to SMPL pose parameters.

Thank you a lot.

How can the real-time data collection program work?

I want to ask the author a question. Nothing happens after the capture.py file is run. My steps are as follows: first connect DCA1000EVM and awr1642, and power on, and finally run capture.py, but the bin file I collected is empty. Do I need to configure the parameters with mmstudio software first, and then run capture.py? I tried but it seems to have failed. Can you give the correct steps to run capture.py? Thanks!

bitoperations.lua "No such file or directory"

Hello

Thank you so much for your contributions in this area.

I am however having an issue. I am using mmWave Studio version 2.1.1.0, with IWR1443, and I get the following error when I try to run your lua script:

Any suggestions would be greatly appreciated.

Thank you!

mmWave x,y,z coordinates generation.

Hi, I am just wondering about the piece of code that generates the x,y,z coordinates from the mmwave frames. Appreciate it if you could point that.

Thank you!

Converting mmWave data to .dat format

I was wondering if I was missing a step - I'm working with some of the .bin files that I get from the mmWave generation, and I was wondering how it goes from these .bin files -> .dat files. I see in the pc_generation.py, that a Point Cloud is generated, but I was confused on how it gets to the .dat files in the 3.deep_model/data.py. i.e. convert the radar data to the .dat formats (trans.mcl.20p8a) I'm not sure if I missed a step and any help would be appreciated.

Some questions about data.py in '3.deep_model'

I'm confused about the data.py file,
What are the meanings of the data loaded in trans.mcl.20p8a.dat, pmat.mcl.20p8a.dat, betas.mcl.20p8a.dat, and Genes.mcl.20p8a. dat in lines 13 to 17?
And how to get these data?
I'm not sure if I missed a step and any help would be appreciated.

How to make a dataset that matches this project

Hello! Thank you for this great work, we are currently using our own radar and motion capture equipment to make a dataset for training, we have the following practical problems:

1. How should we correct the deviation of radar and motion capture equipment?
2. The training data in data.py includes trans.mcl.20p8a.dat; pmat.mcl.20p8a.dat; betas.mcl.20p8a.dat What is the specific meaning of these data？And how should we accurately use our equipment to obtain the same data that can match the model interface like your data ？
   Looking forward to your generous answer！

capture.py related questions

mmMesh: Towards 3D Real-Time Dynamic Human Mesh Construction Using Millimeter-Wave

是个非常棒的工作 再次感谢您的开源

在对你工作的学习过程中，我有些问题像向您请教：

1. 成功在mmWaveStudio中执行[DataCaptureDemo_1843new.lua]后 我理解这个是一个不断发送chirp信号的过程 然后可以在ip：192.168.33.30中去取数据 板子相当于服务机 192.168.33.180似乎也是板子的ip地址 您开源的code中好像没有使用他 然后在Ubuntu的客户端去与192.168.33.30建立连接 capture.py中的a.getFrame()则是一直在取数据 并写入到新的bin中（客户端中）
2. 如果在同一台电脑的双系统中可以不用调整网线（连接DCA1000EVM的） 如果是两台电脑的话得把网线DCA1000EVM连接到Ubuntu那台机子上（在run完lua后）
3. 我尝试执行python capture.py 1 得到的time.bin二进制数据有900M这个情况正常吗
4. 这个是我对您项目的一些理解 我打算借鉴您在数据捕获和点云生成工作的设计 所以希望得到您的纠正和指导

What energy in pc_generation.py means?

Can you tell me what energy in pc_generation.py means? Is it reflection intensity? thanks

The point cloud shape stored in .dat file

Thanks for your excellent job! I've read the paper and the code, there are still some questions confuse me. I was wondering is I can use the bin files I get using openradar to skip the step1.mmWave_data_capture, I tried but didn't work. Thus I want to know the point cloud shape stored in /pc.mcl.20p8a.dat file ,so that I could use the point cloud I've got from other method to run the infer_model.py, Thanks a lot!

Data shape in point cloud generation