Skip to content

Commit

Permalink
update website
Browse files Browse the repository at this point in the history
  • Loading branch information
@atoaiari
atoaiari committed Mar 22, 2024
1 parent f12e168 commit a9e0f76
Show file tree
Hide file tree
Showing 5 changed files with 263 additions and 74 deletions.
313 changes: 240 additions & 73 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,8 @@
More Research
</a>
<div class="navbar-dropdown">
<a class="navbar-item" href="https://intelligolabs.net/blog/">
IntelligoLabs Projects
<a class="navbar-item" href="https://github.com/intelligolabs">
IntelliGOLabs Projects
</a>
</div>
</div>
Expand All @@ -66,74 +66,99 @@
<div class="hero-body">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="column has-text-centered">
<h1 class="title is-1 publication-title">HARPER</h1>
<div class="column has-text-centered is-10">
<h1 class="title is-size-3 publication-subtitle">
3D Human Pose Estimation and Forecasting from the
Robot’s Perspective
</h1>
<h1 class="title is-1 publication-title">
The HARPER Dataset
</h1>
<div class="is-size-5 publication-authors">

<span class="author-block">
<a href="https://">Author A.</a>,
<a href="https://">Andrea Avogaro</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://">Andrea Toaiari</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://">Federico Cunico</a><sup>1</sup>,
</span>
<span class="author-block">
<a href="https://">Xiangmin Xu</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://">Haralambos Dafas</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://">Alessandro Vinciarelli</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://">Emma Li</a><sup>2</sup>,
</span>
<span class="author-block">
and <a href="https://">Marco Cristani</a><sup>1</sup>
</span>
<!-- Add more here -->
</div>

<div class="is-size-5 publication-authors">
<span class="author-block">University of Verona</span>
<div class="is-size-6 publication-authors">
<span class="author-block"><sup>1</sup> Department of Engineering for Innovation Medicine, University of Verona, Italy</span>
</div>
<div class="is-size-6 publication-authors">
<span class="author-block"><sup>2</sup> University of Glasgow, UK</span>
</div>

<span class="tag is-success is-primary is-large">COMING SOON</span>
<!-- <span class="tag is-success is-primary is-large" style="margin-top: 1.0em;">COMING SOON</span> -->

<div class="column has-text-centered">
<div class="publication-links">
<!-- PDF Link. -->
<!-- <span class="link-block">
<a href="https://not-available-yet"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span> -->


<!-- Code Link. -->
<!-- <span class="link-block">
<a href="https://github.com/intelligolabs/HARPER"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code (soon)</span>
</a>
</span> -->

<!-- PDF Link. -->
<!-- <span class="link-block">
<a href="https://not-available-yet"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
</span>
<span>Paper</span>
</a>
</span> -->

<!-- Arxiv Link. -->
<span class="link-block">
<a href="https://arxiv.org/abs/2403.14447" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
</span>
<span>arXiv</span>
</a>
</span>

<!-- Code Link. -->
<span class="link-block">
<a href="https://github.com/intelligolabs/HARPER"
class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fab fa-github"></i>
</span>
<span>Code</span>
</a>
</span>

<!-- Dataset Link. -->
<!-- <span class="link-block">
<a href="https://github.com/google/hypernerf/releases/tag/v0.1" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<svg class="svg-inline--fa fa-images fa-w-18" aria-hidden="true" focusable="false" data-prefix="far" data-icon="images" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" data-fa-i2svg=""><path fill="currentColor" d="M480 416v16c0 26.51-21.49 48-48 48H48c-26.51 0-48-21.49-48-48V176c0-26.51 21.49-48 48-48h16v48H54a6 6 0 0 0-6 6v244a6 6 0 0 0 6 6h372a6 6 0 0 0 6-6v-10h48zm42-336H150a6 6 0 0 0-6 6v244a6 6 0 0 0 6 6h372a6 6 0 0 0 6-6V86a6 6 0 0 0-6-6zm6-48c26.51 0 48 21.49 48 48v256c0 26.51-21.49 48-48 48H144c-26.51 0-48-21.49-48-48V80c0-26.51 21.49-48 48-48h384zM264 144c0 22.091-17.909 40-40 40s-40-17.909-40-40 17.909-40 40-40 40 17.909 40 40zm-72 96l39.515-39.515c4.686-4.686 12.284-4.686 16.971 0L288 240l103.515-103.515c4.686-4.686 12.284-4.686 16.971 0L480 208v80H192v-48z"></path></svg>
</span>
<span>Data</span>
</a>
</span> -->
</div>
</div>
</div>
</div>
</div>
</section>
<!--
<section class="hero teaser">
<div class="container">
<div class="columns is-centered">
<div class="column is-max-desktop">
<div class="content has-text-centered">
<div class="columns is-centered">
<div class="column is-7">
<img class="image is-371x299" src="./static/images/teaser.png" alt="Teaser">
<p>
The HARPER Dataset
</p>
</div>
</div>
</div>
</div>
</div>
</div>
</section> -->



<section class="section">
<div class="container is-max-desktop">
Expand All @@ -143,26 +168,169 @@ <h1 class="title is-1 publication-title">HARPER</h1>
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
We present HARPER
We introduce HARPER, a novel dataset for 3D body pose estimation and forecast in dyadic interactions between users and Spot,
the quadruped robot manufactured by Boston Dynamics. The key-novelty is the focus on the robot’s perspective, i.e.,
on the data captured by the robot’s sensors. These make 3D body pose analysis challenging because being close to the ground
captures humans only partially. The scenario underlying HARPER includes 15 actions, of which 10 involve physical contact between the robot and users.
The Corpus contains not only the recordings of the built-in stereo cameras of Spot, but also those of a 6-camera OptiTrack system
(all recordings are synchronized). This leads to ground-truth skeletal representations with a precision lower than a millimeter.
In addition, the Corpus includes reproducible benchmarks on 3D Human Pose Estimation, Human Pose Forecasting, and Collision Prediction,
all based on publicly available baseline approaches. This enables future HARPER users to rigorously compare their results with
those we provide in this work.
</p>


</div>
</div>
</div>

<!-- Paper video. -->
<!-- <div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<iframe width="560" height="315" src="https://" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
</div>
</div> -->
<!--/ Paper video. -->
</div>
</section>
</div>

<!-- <section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<iframe width="560" height="315" src="https://www.youtube.com/watch?v=ScMzIvxBSi4&ab_channel=BenMarquezTX" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
</div>
</div>
</div>
</div>
</section> -->

<section class="hero is-dark is-small">
<div class="hero-body">
<div class="container has-text-centered">
<div class="column is-three-fifths is-offset-one-fifth">
<h2 class="title is-3">Video</h2>
<div class="publication-video">
<iframe width="560" height="315" src="https://youtube.com/embed/XAQDQ9ClzlM" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
</div>
</div>
</div>
</div>
</section>

<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">The HARPER Dataset</h2>
<div class="content has-text-justified">
<p>
We introduce HARPER, a novel dataset for 3D body pose estimation and forecast in dyadic interactions between users and Spot,
the quadruped robot manufactured by Boston Dynamics. The key-novelty is the focus on the robot’s perspective, i.e.,
on the data captured by the robot’s sensors.
</p>
</div>
<div class="publication-links">
<span class="link-block">
<a href="https://univr-my.sharepoint.com/:f:/g/personal/federico_cunico_univr_it/Esk9qR4fKyFBg05UdXK0YSYBY8JvLHpY2Bis2xyX1pcVWg" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<svg class="svg-inline--fa fa-images fa-w-18" aria-hidden="true" focusable="false" data-prefix="far" data-icon="images" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" data-fa-i2svg=""><path fill="currentColor" d="M480 416v16c0 26.51-21.49 48-48 48H48c-26.51 0-48-21.49-48-48V176c0-26.51 21.49-48 48-48h16v48H54a6 6 0 0 0-6 6v244a6 6 0 0 0 6 6h372a6 6 0 0 0 6-6v-10h48zm42-336H150a6 6 0 0 0-6 6v244a6 6 0 0 0 6 6h372a6 6 0 0 0 6-6V86a6 6 0 0 0-6-6zm6-48c26.51 0 48 21.49 48 48v256c0 26.51-21.49 48-48 48H144c-26.51 0-48-21.49-48-48V80c0-26.51 21.49-48 48-48h384zM264 144c0 22.091-17.909 40-40 40s-40-17.909-40-40 17.909-40 40-40 40 17.909 40 40zm-72 96l39.515-39.515c4.686-4.686 12.284-4.686 16.971 0L288 240l103.515-103.515c4.686-4.686 12.284-4.686 16.971 0L480 208v80H192v-48z"></path></svg>
</span>
<span>OptiTrack Data (120fps)</span>
</a>
</span>
<span class="link-block">
<a href="" class="external-link button is-normal is-rounded is-danger is-light">
<span class="icon">
<svg class="svg-inline--fa fa-images fa-w-18" aria-hidden="true" focusable="false" data-prefix="far" data-icon="images" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" data-fa-i2svg=""><path fill="currentColor" d="M480 416v16c0 26.51-21.49 48-48 48H48c-26.51 0-48-21.49-48-48V176c0-26.51 21.49-48 48-48h16v48H54a6 6 0 0 0-6 6v244a6 6 0 0 0 6 6h372a6 6 0 0 0 6-6v-10h48zm42-336H150a6 6 0 0 0-6 6v244a6 6 0 0 0 6 6h372a6 6 0 0 0 6-6V86a6 6 0 0 0-6-6zm6-48c26.51 0 48 21.49 48 48v256c0 26.51-21.49 48-48 48H144c-26.51 0-48-21.49-48-48V80c0-26.51 21.49-48 48-48h384zM264 144c0 22.091-17.909 40-40 40s-40-17.909-40-40 17.909-40 40-40 40 17.909 40 40zm-72 96l39.515-39.515c4.686-4.686 12.284-4.686 16.971 0L288 240l103.515-103.515c4.686-4.686 12.284-4.686 16.971 0L480 208v80H192v-48z"></path></svg>
</span>
<span>Spot + OptiTrack Data (10fps)</span>
</a>
</span>
</div>
</div>
</div>
<div class="columns is-centered">
<div class="column">
<div class="content feature-list">
<h4>Data</h4>
<ul>
<li>15 different interactions</li>
<li>17 participants</li>
<li>10 actions involve physical contact between the Spot and users</li>
<li>
Recordings of the built-in stereo cameras of Spot
<span class="tag is-rounded is-danger is-light">Coming Soon</span>
</li>
<li>Recordings of a 6-camera OptiTrack system</li>
<li>Ground-truth skeletal representations with a precision lower than a millimeter</li>
</ul>
</div>
<div class="content feature-list">
<h4>Sensors</h4>
<ul>
<li>Spot's stereo cameras (5 Greyscale + Depth and 1 RGB-D)</li>
<li>6-camera OptiTrack system</li>
<li>External RGB Camera</li>
</ul>
</div>
<div class="content feature-list">
<h4>Annotations</h4>
<ul>
<li>Human 21-joint 3D skeletal model</li>
<li>Spot 21-joint 3D skeletal model</li>
<li>
2D keypoints reprojected on the Spot's cameras
<span class="tag is-rounded is-danger is-light">Coming Soon</span>
</li>
<li>
Per-keypoint visibility
<span class="tag is-rounded is-danger is-light">Coming Soon</span>
</li>
</ul>
</div>
</div>
<div class="column">
<img src="static/images/Teaser.png">
</div>
</div>
</section>

<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column">
<h2 class="title is-3">Benchmarks (from the Spot's Perspective)</h2>
<div class="columns">
<div class="column">
<!-- <div class="block">
<img src="static/images/short_blank_placeholder.png">
</div> -->
<div class="block content box">
<h4>3D Human Pose Estimation</h4>
<p>
Estimate the 3D human pose from the robot's perspective (camera + depth).
</p>
</div>
</div>
<div class="column">
<!-- <div class="block">
<img src="static/images/short_blank_placeholder.png">
</div> -->
<div class="block content box">
<h4>Human Pose Forecasting</h4>
<p>
Forecast the future human poses (all the keypoints) from the robot's perspective.
</p>
</div>
</div>
<div class="column">
<!-- <div class="block">
<img src="static/images/short_blank_placeholder.png">
</div> -->
<div class="block content box">
<h4>Collision Prediction</h4>
<p>
Collision estimation between the robot and the human on the forecasted poses.
</p>
</div>
</div>
</div>
</div>
</div>
</div>
</section>

<!-- <section class="section" id="BibTeX">
Expand All @@ -178,7 +346,6 @@ <h2 class="title">BibTeX</h2>
year = {},
pages = {}
}
</code>
</pre>
</div>
Expand All @@ -187,17 +354,17 @@ <h2 class="title">BibTeX</h2>
<footer class="footer">
<div class="container">

<div class="columns is-centered">
<div class="columns is-centered has-text-centered">
<div class="column is-8">
<div class="content">
<div class="content is-size-7">
<p>
This website is licensed under a <a rel="license"
href="http://creativecommons.org/licenses/by-sa/4.0/">Creative
Commons Attribution-ShareAlike 4.0 International License</a>.
</p>
<p>
<a
href="https://github.com/nerfies/nerfies.github.io">Source code</a> of this website (Nerfies)
Website code based on <a
href="https://github.com/nerfies/nerfies.github.io">Nerfies</a>.

</p>
</div>
Expand Down
Loading

0 comments on commit a9e0f76

Please sign in to comment.