Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification

Introduction

This is the implementation of MoCos presented by "Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification".

Environment

Python >= 3.5
Tensorflow-gpu >= 1.14.0
Pytorch >= 1.1.0
Faiss-gpu >= 1.6.3

Here we provide a configuration file to install the extra requirements (if needed):

conda install --file requirements.txt

Note: This file will not install tensorflow/tensorflow-gpu, faiss-gpu, pytroch/torch, please install them according to the cuda version of your graphic cards: Tensorflow, Pytorch. Take cuda 9.0 for example:

conda install faiss-gpu cuda90 -c pytorch
conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=9.0 -c pytorch
conda install tensorflow==1.14
conda install sklearn

Datasets and Models

We provide three already pre-processed datasets (IAS-Lab, BIWI, KGBD) with various sequence lengths (f=4/6/8/10/12) here (pwd: 7je2) and the pre-trained models here (pwd: ymn0). Since we report the average performance of our approach on all datasets, here the provided models may produce better results than the paper.

Please download the pre-processed datasets and model files while unzipping them to Datasets/ and ReID_Models/ folders in the current directory.

Note: The access to the Vislab Multi-view KS20 dataset and large-scale RGB-based gait dataset CASIA-B are available upon request. If you have signed the license agreement and been granted the right to use them, please email us with the signed agreement and we will share the complete pre-processed KS20 and CASIA-B data. The original datasets can be downloaded here: IAS-Lab, BIWI, KGBD, KS20, CASIA-B. We also provide the Preprocess.py for directly transforming original datasets to the formated training and testing data.

Dataset Pre-Processing

To (1) extract 3D skeleton sequences of length f=6 from original datasets and (2) process them in a unified format (.npy) for the model inputs, please simply run the following command:

python Pre-process.py 6

Note: If you hope to preprocess manually (or you can get the already preprocessed data (pwd: 7je2)), please frist download and unzip the original datasets to the current directory with following folder structure:

[Current Directory]
├─ BIWI
│    ├─ Testing
│    │    ├─ Still
│    │    └─ Walking
│    └─ Training
├─ IAS
│    ├─ TestingA
│    ├─ TestingB
│    └─ Training
├─ KGBD
│    └─ kinect gait raw dataset
└─ KS20
     ├─ frontal
     ├─ left_diagonal
     ├─ left_lateral
     ├─ right_diagonal
     └─ right_lateral

After dataset preprocessing, the auto-generated folder structure of datasets is as follows:

Datasets
├─ BIWI
│    └─ 6
│      ├─ test_npy_data
│      │    ├─ Still
│      │    └─ Walking
│      └─ train_npy_data
├─ IAS
│    └─ 6
│      ├─ test_npy_data
│      │    ├─ A
│      │    └─ B
│      └─ train_npy_data
├─ KGBD
│    └─ 6
│      ├─ test_npy_data
│      │    ├─ gallery
│      │    └─ probe
│      └─ train_npy_data
└─ KS20
    └─ 6
      ├─ test_npy_data
      │    ├─ gallery
      │    └─ probe
      └─ train_npy_data

Note: KS20 data need first transforming ".mat" to ".txt". If you are interested in the complete preprocessing of KS20 and CASIA-B, please contact us and we will share. We recommend to directly download the preprocessed data here (pwd: 7je2).

Model Usage

To (1) train MoCos to obtain skeleton representations and (2) validate their effectiveness on the person re-ID task on a specific dataset (probe), please simply run the following command:

python MoCos.py --dataset KS20 --probe probe

# Default options: --dataset KS20 --probe probe --length 6  --gpu 0
# --dataset [IAS, KS20, BIWI, KGBD]
# --probe ['probe' (the only probe for KS20 or KGBD), 'A' (for IAS-A probe), 'B' (for IAS-B probe), 'Walking' (for BIWI-Walking probe), 'Still' (for BIWI-Still probe)] 
# --length [4, 6, 8, 10, 12] 
# --(H, n_heads, L_transfomer, fusion_lambda, prob_s, prob_t, lr, etc.) with default settings for each dataset
# --mode [Train (for training), Eval (for testing)]
# --gpu [0, 1, ...]

Please see MoCos.py for more details.

To print evaluation results (Top-1, Top-5, Top-10 Accuracy, mAP) of the best model saved in default directory (ReID_Models/(Dataset)/(Probe)), run:

python MoCos.py --dataset KS20 --probe probe --mode Eval

Application to Model-Estimated Skeleton Data

Estimate 3D Skeletons from RGB-Based Scenes

To apply our MoCos to person re-ID under the large-scale RGB scenes (CASIA B), we exploit pose estimation methods to extract 3D skeletons from RGB videos of CASIA B as follows:

Step 1: Download CASIA-B Dataset
Step 2: Extract the 2D human body joints by using OpenPose
Step 3: Estimate the 3D human body joints by using 3DHumanPose

We provide already pre-processed skeleton data of CASIA B for single-condition (Nm-Nm, Cl-Cl, Bg-Bg) and cross-condition evaluation (Cl-Nm, Bg-Nm) (f=40/50/60) here (pwd: 07id). Please download the pre-processed datasets into the directory Datasets/.

Usage

To (1) train the MoCos to obtain skeleton representations and (2) validate their effectiveness on the person re-ID task on CASIA B under single-condition and cross-condition settings, please simply run the following command:

python MoCos.py --dataset CAISA_B --probe_type nm.nm --length 40

# --length [40, 50, 60] 
# --probe_type ['nm.nm' (for 'Nm' probe and 'Nm' gallery), 'cl.cl', 'bg.bg', 'cl.nm' (for 'Cl' probe and 'Nm' gallery), 'bg.nm']  
# --(H, n_heads, L_transfomer, fusion_lambda, prob_s, prob_t, lr, etc.) with default settings
# --gpu [0, 1, ...]

Please see MoCos.py for more details.

License

MoCos is released under the MIT License. Our models and codes must only be used for the purpose of research.

Kali-Hac / MoCos