Official implementation of the paper Do pedestrians pay attention? Eye contact detection for autonomous driving

Related tags

Deep Learninglooking
Overview

Do pedestrians pay attention? Eye contact detection for autonomous driving

Official implementation of the paper Do pedestrians pay attention? Eye contact detection for autonomous driving

alt text

Image taken from : https://jooinn.com/people-walking-on-pedestrian-lane-during-daytime.html . Results obtained with the model trained on JackRabbot, Nuscenes, JAAD and Kitti. The model file is available at models/predictor and can be reused for testing with the predictor.

Abstract

In urban or crowded environments, humans rely on eye contact for fast and efficient communication with nearby people. Autonomous agents also need to detect eye contact to interact with pedestrians and safely navigate around them. In this paper, we focus on eye contact detection in the wild, i.e., real-world scenarios for autonomous vehicles with no control over the environment or the distance of pedestrians. We introduce a model that leverages semantic keypoints to detect eye contact and show that this high-level representation (i) achieves state-of-the-art results on the publicly-available dataset JAAD, and (ii) conveys better generalization properties than leveraging raw images in an end-to-end network. To study domain adaptation, we create LOOK: a large-scale dataset for eye contact detection in the wild, which focuses on diverse and unconstrained scenarios for real-world generalization. The source code and the LOOK dataset are publicly shared towards an open science mission.

Table of contents

Requirements

Use 3.6.9 <= python < 3.9. Run pip3 install -r requirements.txt to get the dependencies

Predictor

Get predictions from our pretrained model using any image with the predictor. The scripts extracts the human keypoints on the fly using OpenPifPaf. The predictor supports eye contact detection using human keypoints only. You need to specify the following arguments in order to run correctly the script:

Parameter Description
--glob Glob expression to be used. Example: .png
--images Path to the input images. If glob is enabled you need the path to the directory where you have the query images
--looking_threshold Threshold to define an eye contact. Default 0.5
--transparency Transparency of the output poses. Default 0.4

Example command:

If you want to reproduce the result of the top image, run:

If you want to run the predictor on a GPU:

python predict.py --images images/people-walking-on-pedestrian-lane-during-daytime-3.jpg

If you want to run the predictor on a CPU:

python predict.py --images images/people-walking-on-pedestrian-lane-during-daytime-3.jpg --device cpu --disable-cuda

Create the datasets for training and evaluation

Please follow the instructions on the folder create_data.

Training your models on LOOK / JAAD / PIE

You have one config file to modify. Do not change the variables name. Check the meaning of each variable to change on the training wiki.

After changing your configuration file, run:

python train.py --file [PATH_TO_CONFIG_FILE]

A sample config file can be found at config_example.ini

Evaluate your trained models

Check the meaning of each variable to change on the evaluation wiki.

After changing your configuration file, run:

python evaluate.py --file [PATH_TO_CONFIG_FILE]

A sample config file can be found at config_example.ini

Annotate new images

Check out the folder annotator in order to run our annotator to annotate new instances for the task.

Credits

Credits to OpenPifPaf for the pose detection part, and JRDB, Nuscenes and Kitti datasets for the images.

Cite our work

If you use our work for your research please cite us :)

@misc{belkada2021pedestrians,
      title={Do Pedestrians Pay Attention? Eye Contact Detection in the Wild}, 
      author={Younes Belkada and Lorenzo Bertoni and Romain Caristan and Taylor Mordan and Alexandre Alahi},
      year={2021},
      eprint={2112.04212},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
Owner
VITA lab at EPFL
Visual Intelligence for Transportation
VITA lab at EPFL
A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

Convolutional Neural Network (CNN). This repository contains a source code of a deep learning network built with TensorFlow and Keras to classify gend

Pawel Dziemiach 1 Dec 19, 2021
Repository for the paper "Online Domain Adaptation for Occupancy Mapping", RSS 2020

RSS 2020 - Online Domain Adaptation for Occupancy Mapping Repository for the paper "Online Domain Adaptation for Occupancy Mapping", Robotics: Science

Anthony 26 Sep 22, 2022
ML From Scratch

ML from Scratch MACHINE LEARNING TOPICS COVERED - FROM SCRATCH Linear Regression Logistic Regression K Means Clustering K Nearest Neighbours Decision

Tanishq Gautam 66 Nov 02, 2022
XViT - Space-time Mixing Attention for Video Transformer

XViT - Space-time Mixing Attention for Video Transformer This is the official implementation of the XViT paper: @inproceedings{bulat2021space, title

Adrian Bulat 33 Dec 23, 2022
Continual learning with sketched Jacobian approximations

Continual learning with sketched Jacobian approximations This repository contains the code for reproducing figures and results in the paper ``Provable

Machine Learning and Information Processing Laboratory 1 Jun 30, 2022
Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

Continual Reinforcement Learning This repository provides a simple way to run continual reinforcement learning experiments in PyTorch, including evalu

55 Dec 24, 2022
This repository contains small projects related to Neural Networks and Deep Learning in general.

ILearnDeepLearning.py Description People say that nothing develops and teaches you like getting your hands dirty. This repository contains small proje

Piotr Skalski 1.2k Dec 22, 2022
rastrainer is a QGIS plugin to training remote sensing semantic segmentation model based on PaddlePaddle.

rastrainer rastrainer is a QGIS plugin to training remote sensing semantic segmentation model based on PaddlePaddle. UI TODO Init UI. Add Block. Add l

deepbands 5 Mar 04, 2022
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks (SDPoint) This repository contains the cod

Jason Kuen 17 Jul 04, 2022
Pytorch implementation of Nueral Style transfer

Nueral Style Transfer Pytorch implementation of Nueral style transfer algorithm , it is used to apply artistic styles to content images . Content is t

Abhinav 9 Oct 15, 2022
Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision. ICCV 2021.

Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision Download links and PyTorch implementation of "Towers of Ba

Blakey Wu 40 Dec 14, 2022
Unsupervised Learning of Video Representations using LSTMs

Unsupervised Learning of Video Representations using LSTMs Code for paper Unsupervised Learning of Video Representations using LSTMs by Nitish Srivast

Elman Mansimov 341 Dec 20, 2022
Video Frame Interpolation with Transformer (CVPR2022)

VFIformer Official PyTorch implementation of our CVPR2022 paper Video Frame Interpolation with Transformer Dependencies python = 3.8 pytorch = 1.8.0

DV Lab 63 Dec 16, 2022
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Transformers

DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Transformers Authors: Jaemin Cho, Abhay Zala, and Mohit Bansal (

Jaemin Cho 98 Dec 15, 2022
The fundamental package for scientific computing with Python.

NumPy is the fundamental package needed for scientific computing with Python. Website: https://www.numpy.org Documentation: https://numpy.org/doc Mail

NumPy 22.4k Jan 09, 2023
Code for our paper "Multi-scale Guided Attention for Medical Image Segmentation"

Medical Image Segmentation with Guided Attention This repository contains the code of our paper: "'Multi-scale self-guided attention for medical image

Ashish Sinha 394 Dec 28, 2022
3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021)

3DDUNET This is the code for 3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021) Conference Paper Link Dataset We use SMOID dataset

1 Jan 07, 2022
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features

CleanRL (Clean Implementation of RL Algorithms) CleanRL is a Deep Reinforcement Learning library that provides high-quality single-file implementation

Costa Huang 1.8k Jan 01, 2023
Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks.

pyradiomics v3.0.1 Build Status Linux macOS Windows Radiomics feature extraction in Python This is an open-source python package for the extraction of

Artificial Intelligence in Medicine (AIM) Program 842 Dec 28, 2022
NHS AI Lab Skunkworks project: Long Stayer Risk Stratification

NHS AI Lab Skunkworks project: Long Stayer Risk Stratification A pilot project for the NHS AI Lab Skunkworks team, Long Stayer Risk Stratification use

NHSX 21 Nov 14, 2022