anisghaoui / humolire

HuMoLiRe is a Pedestrian Dead-Reckoning Particle Filter Map-aided system that leverages human motion likelihood in indoor spaces to estimate their position. This repository is the dataset and software published with its paper.

HuMoLiRe

Example of trajectory

Citation

This dataset and software are related to the following publication in the IEEE Sensors journal. Please cite using the following:

@ARTICLE{ghaouihumolire,
author={Ghaoui, Mohamed Anis and Vincke, Bastien and Reynaud, Roger}, 
journal={IEEE Sensors Journal},   
title={Human Motion Likelihood Representation Map-Aided PDR Particle Filter},  
year={2023},  
volume={23},  
number={1},  
pages={484-494},  
doi={10.1109/JSEN.2022.3222639}}

IEEE page

Introduction

This program runs on python3.8+. It is recommanded to use PyCharm. (it can easily be turned into older version by editing every print(f"{variable=})" call)

Entry point is main.py. generate_figures.py is used to recreate the figures mentionned in the article.

Requirements

requirements.txt lists:

• numpy~=1.21
• matplotlib~=3.3.3
• scipy~=1.5.4
• AHRS~=0.3.0
• imageio~=2.9.0
• tqdm~=4.51.0
• opencv-python~=4.5.1.48

Optional:

• adjustText~=0.7.3 , is used to place the purple numbers automatically
• requests~=2.22.0 , is used to send an SMS when the program is finished

Folder structure:

.
├── data
├── docs
├── humolire
├── map_editor
├── README.md
├── requirements.txt
└── tests

Documentation:

There are many README.MD files in the folders about. The main entry point is main.py. There is a beginning of documentation at read the docs. I don't have much time. If you want to help in documentation, I would be immensely grateful.

Contribution:

• If you have a research question, please reach me by email: [email protected]
• If you have a question about the code, open an issue
• If you wanna help documenting (I lack the time and skills to do that correctly), open an issue. Thank you!

LICENSE

Humolire Dataset and Software by Anis GHAOUI is licensed under a Creative Commons Attribution 4.0 International License.

humolire's Issues

I want to timestamp the coordinate results of DR and Map-Aided DR using the code.

Hello.
First of all, thank you for providing the code and the paper.
I have conducted PDR (Pedestrian Dead Reckoning) using the provided code for test purpose and obtained meaningful results.
I would like to compare the coordinates obtained through DR with those corrected based on the Grid map at the same timestamps.
Therefore, I would like to include timestamps for each coordinate in the code.
From my analysis of the code, it seems that the coordinates obtained through DR are stored in pdr_positions in main.py(line 81),
pdr_positions, total_distance = compute_positions(*perform_pdr(acce, gyro, **kwargs)
and the corrected coordinates based on the Grid map are likely to be found in plot_particles_center within visualize.py(line 121,122).
X = [center.x for center in center_positions] Y = [center.y for center in center_positions]
My questions are as follows:

1. Could you please provide a way to include timestamps for both DR coordinates and Grid map-based corrected coordinates?
2. Alternatively, should I consider that the generated coordinates are estimated at 1-second intervals? I am asking this because there seems to be a parameter for steps per second.

Thank you for reading my message, and I would greatly appreciate your response as it would be immensely helpful to me. Thank you, and have a great day.

ValueError: keyword grid_b is not recognized; valid keywords ar

when i want to run the main.py in the humolire file ,why i can't run it,and its error like this.
ValueError: keyword grid_b is not recognized; valid keywords are ['size', 'width', 'color', 'tickdir', 'pad', 'labelsize', 'labelcolor', 'labelfontfamily', 'zorder', 'gridOn', 'tick1On', 'tick2On', 'label1On', 'label2On', 'length', 'direction', 'left', 'bottom', 'right', 'top', 'labelleft', 'labelbottom', 'labelright', 'labeltop', 'labelrotation', 'grid_agg_filter', 'grid_alpha', 'grid_animated', 'grid_antialiased', 'grid_clip_box', 'grid_clip_on', 'grid_clip_path', 'grid_color', 'grid_dash_capstyle', 'grid_dash_joinstyle', 'grid_dashes', 'grid_data', 'grid_drawstyle', 'grid_figure', 'grid_fillstyle', 'grid_gapcolor', 'grid_gid', 'grid_in_layout', 'grid_label', 'grid_linestyle', 'grid_linewidth', 'grid_marker', 'grid_markeredgecolor', 'grid_markeredgewidth', 'grid_markerfacecolor', 'grid_markerfacecoloralt', 'grid_markersize', 'grid_markevery', 'grid_mouseover', 'grid_path_effects', 'grid_picker', 'grid_pickradius', 'grid_rasterized', 'grid_sketch_params', 'grid_snap', 'grid_solid_capstyle', 'grid_solid_joinstyle', 'grid_transform', 'grid_url', 'grid_visible', 'grid_xdata', 'grid_ydata', 'grid_zorder', 'grid_aa', 'grid_c', 'grid_ds', 'grid_ls', 'grid_lw', 'grid_mec', 'grid_mew', 'grid_mfc', 'grid_mfcalt', 'grid_ms']