https://github.com/againstentropy/nlos-track
Official codes of CVPR 2023 Paper | Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
https://github.com/againstentropy/nlos-track
cnn deep-learning non-line-of-sight pytorch rnn tracking
Last synced: over 1 year ago
JSON representation
Official codes of CVPR 2023 Paper | Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking
- Host: GitHub
- URL: https://github.com/againstentropy/nlos-track
- Owner: AgainstEntropy
- Created: 2023-03-19T09:48:29.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-10-31T19:49:45.000Z (over 2 years ago)
- Last Synced: 2025-03-16T18:21:26.376Z (over 1 year ago)
- Topics: cnn, deep-learning, non-line-of-sight, pytorch, rnn, tracking
- Language: Python
- Homepage: https://againstentropy.github.io/NLOS-Track/
- Size: 37.8 MB
- Stars: 20
- Watchers: 1
- Forks: 4
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# NLOS Tracking
[](https://againstentropy.github.io/NLOS-Track/)
[](https://arxiv.org/abs/2303.11791)
[](https://www.kaggle.com/datasets/againstentropy1/nlos-track)
Official codes of CVPR 2023 [Paper](https://arxiv.org/abs/2303.11791) | _Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking_
## Prepreation
### Environment
Create a new environment and install dependencies with `requirement.txt`:
```shell
conda create -n NLOS_Tracking
conda activate NLOS_Tracking
conda install --file requirements.txt
```
### Data
The NLOS-Track dataset can be downloaded from [kaggle](https://www.kaggle.com/datasets/againstentropy1/nlos-track).
The file structure in project root should be as follow:
```
project_root
| README.md
| requirements.txt
| train.py
+---data
+---utils
+---configs
| ...
+---dataset
+---render
| +---0000
| | configs.yaml
| | route.mat
| | video_128.npy
| | 001.png
| | 002.png
| | ...
| +---0001
| ...
+---real-shot
+---0000
| route.mat
| video_128.npy
+---0001
...
```
#### Data Loading and Visualization
Follow the code blocks in `data_playground.ipynb` to load and visualize the dataset.
## Usage
### Train
**Before training, fill the missing items in configuration files.**
Create a new configuration file in `./configs` for training:
```shell
python train.py --cfg_file=new_cfg --model_name=PAC_Net
```
or directly use `default.yaml` by default:
```shell
python train.py --model_name=PAC_Net --pretrained -b 64 -lr_b 2.5e-4 --gpu_ids=0,1 --port=8888
```
### Test
Follow the code blocks in `test.ipynb` to test a trained model.
## Citation
```bibtex
@article{wang2023nlosTrack,
author = {Wang, Yihao and Wang, Zhigang and Zhao, Bin and Wang, Dong and Chen, Mulin and Li, Xuelong},
title = {Propagate And Calibrate: Real-time Passive Non-line-of-sight Tracking},
journal = {CVPR},
year = {2023},
}
```