I run the code related to " Computer Vision Aided Beam Tracking in A real-world mmWave Deployment", I found that the training and testing datasets are built from Scenario 8 of Deepsense 6G, could you elaborate how did you generate the two datasets
I have updated the code in the GitHub repo of this paper ( https://github.com/acyiobs/vision_beam_tracking).
The scripts for generating the datasets can be found in ./data.
- sequence generator.py
- This script separates the scenario 8 data into multiple sequences. Each sequence contains the data where the vehicle passes the base station once.
- Then, it creates the scenario8_series_train.csv and scenario8_series_test.csv for the training and test datasets. The two datasets contain different (non-overlapping) sequences.
- This script further processes scenario8_series_train.csv and scenario8_series_train.csv to generate scenario8_series_bbox_train.csv and scenario8_series_bbox_test.csv.
- These two files are directly used in the training/testing of the neural network model.
- It splits each sequence into (overlapping) sub-sequences of 13 time steps.
- For each time step, it prepares the vehicle bounding box (input visual data) and the beam index (ground truth).
- Each row in scenario8_series_bbox_train/test.csv corresponds to one of these sub-sequences.
To reproduce the data generation, please follow the data preprocessing steps in readme.
appreciate your feedback, thank you very much, hopefully I can get in touch with you via email