Dilated Evolving Attentive Spatial-Frequency Network

Seeing the Unseen: 
Wifi-based 2D Human Pose Estimation via Dilated Evolving Attentive Spatial-Frequency Network

• Architecture

• Dataset

• Usage

• Visulization

• Result

• Reference

Architecture

Dataset

GPE			SPE
# Person	Number	Url	Action	Number	Url
1	12,884	https://reurl.cc/EzXD8R	Walk	78,852	https://reurl.cc/OqEL9D
2	18,879	https://reurl.cc/ygmX1a	Wave	77,431	https://reurl.cc/Z71vGQ
3	27,694	https://reurl.cc/e8Wa5W	Jump	40,670	https://reurl.cc/j5RYNM
>=4	28,178	https://reurl.cc/m9ZXd7	Run	41,238	https://reurl.cc/EzXL3m
Cross Period	X	X	Cross Period	X	https://reurl.cc/ld4mZq
Total	87,635	X	Total	238,191	X

Usage

Install

$ git clone https://github.com/DEASFN/DEASFN.git

Setup

• create the virtual enciorment

$ cd DEASFN/
$ python3 -m venv env

• activate the virtual environment

$ source env/bin/activate

• install the necessary packages

$ pip install -r requirements.txt

If there are errors about gdown package, you can ignore them.

Download the dataset

• Download SPE or GPE dataset

$ chmod +x download_SPE.sh     or     $ chmod +x download_GPE.sh     
$ ./download_SPE.sh     or     $ ./download_GPE.sh

When you find the download has exited, you need to press ctrl+c to terminate the sh file by yourself.

If errors occur, you can download by yourself using the links provided above.

Please make sure that all four zipfiles in DEASFN/dataset/SPE or DEASFN/dataset/GPE.

• unzip the dataset ( You can substitute GPE for SPE)

$ cd DEASFN/dataset/SPE
$ chmod +x SPE.sh
$ ./SPE.sh

Train

You can adjust the training parameters in config/args.py

$ python3 TrainDeasfn.py--dataset=SPE     or     $ python3 TrainDeasfn.py --dataset=GPE

Test

You can adjust the testing parameters in config/args.py

$ python3 TestDeasfn.py --dataset=SPE     or     $ python3 TestDeasfn.py --dataset=GPE

Visulization

Comparative visualization of DEASFN and two models (PIW[2] and WiSPPN[1])

Some positive cases of DEASFN on our two benchmarks

Comparative GIF images of DEASFN and two models (PIW[2] and WiSPPN[1]) for each action

	DEASFN	PIW	WiSPPN
Walk
Wave
Jump
Run

Comparative visualization of DEASFN and camera-based method(Openpose)

From this comparison, we can easily observe that DEASFN is better than the camera-based method in dark environment. Under poor illumination, Openpose is likely to loss some keypoints, such as wrist, ankle, and so forth. However, DEASFN can correctly return all keypoints.

DEASFN	Openpose

Result

PCK curve of each model:

PCK of DEASFN on each joint:

• Comparisons on the proposed benchmarks:

Metric	Benchmark	WiSPPN[1]	PIW[2]	DEASFN
MPJPE	SPE	44.16	78.88	37.34
	GPE	X	119.60	44.14
PCK@20	SPE	21.86%	32.96%	50.05%
	GPE	X	27.64%	43.98%

• Comparative results against other methods on our SPE benchmark (PCK@20):

Action	WiSPPN	PIW	DEASFN
Walk	23.58%	39.87%	61.14%
Wave	25.92%	33.06%	45.81%
Run	22.12%	37.91%	58.11%
Jump	15.82%	20.99%	35.15%

• Comparative results against other methods on our GPE benchmark (PCK@20):

# Person	PIW	DEASFN
1-person	53.37%	72.65%
2-person	49.31%	65.39%
3-person	19.54%	34.75%
>=4 person	22.66%	39.12%

• Ablation study on our SPE benchmark:

Model	Architecture	PCK@20
1	SFN	44.99%
2	ASFN	45.95%
3	DEASFN, D=1	48.08%
4	DEASFN, D=3 (Proposed)	50.05%
5	DEASFN, D=5	45.95%

Reference

• [1] Fei Wang, Stanislav Panev, Ziyi Dai, Jinsong Han, and Dong Huang. 2019. Can wifi estimate person pose?arXiv preprint arXiv:1904.00277(2019).
• [2] Fei Wang, Sanping Zhou, Stanislav Panev, Jinsong Han, and Dong Huang. 2019.Person-in-WiFi: Fine-grained person perception using WiFi. InProceedings of theIEEE International Conference on Computer Vision. 5452–5461.