Giter Site home page Giter Site logo

headposeestimation-whenet's Introduction

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

Yijun Zhou and James Gregson - BMVC2020

Abstract: We present an end-to-end head-pose estimation network designed to predict Euler angles through the full range head yaws from a single RGB image. Existing methods perform well for frontal views but few target head pose from all viewpoints. This has applications in autonomous driving and retail. Our network builds on multi-loss approaches with changes to loss functions and training strategies adapted to wide range estimation. Additionally, we extract ground truth labelings of anterior views from a current panoptic dataset for the first time. The resulting Wide Headpose Estimation Network (WHENet) is the first fine-grained modern method applicable to the full-range of head yaws (hence wide) yet also meets or beats state-of-the-art methods for frontal head pose estimation. Our network is compact and efficient for mobile devices and applications. ArXiv

Demo

We provided two use case of the WHENet, image input and video input in this repo. Please make sure you installed all the requirments before running the demo code by pip install -r requirements.txt. Additionally, please download the YOLOv3 model for head detection and put it under yolo_v3/data.

Image demo

To run WHENet with image input, please put images and bbox.txt under one folder (E.g. Sample/) and just run pthon demo.py.

Format of bbox.txt are showed below:

image_name,x_min y_min x_max y_max
mov_001_007585.jpeg,240 0 304 83

Video/Webcam demo

We used YOLO_v3 in the video demo to get the cropped head image. In order to customize some of the functions we have put the yolo implementation and the pre-trained model in the repo. Hollywood head and Crowdhuman are used to train the head detection YOLO model.

demo_video.py [--video INPUT_VIDEO_PATH] [--snapshot WHENET_MODEL] [--display DISPLAY_OPTION] 
              [--score YOLO_CONFIDENCE_THRESHOLD] [--iou IOU_THRESHOLD] [--gpu GPU#] [--output OUTPUT_VIDEO_PATH]

Please set --video '' for webcam input.

Dependncies

headposeestimation-whenet's People

Contributors

ascendhuawei avatar yijun88 avatar yijunzhou-huawei avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.