Skip to content

Commit

Permalink
Update formatting.
Browse files Browse the repository at this point in the history
  • Loading branch information
@wjbeksi
wjbeksi committed Dec 23, 2023
1 parent f3833e2 commit 803dcf3
Showing 1 changed file with 84 additions and 88 deletions.
172 changes: 84 additions & 88 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -46,29 +46,31 @@ <h1 class="title is-1 publication-title">NTrack: A Multiple-Object Tracker and D

<div class="is-size-5 publication-university">
<span class="author-block">The University of Texas at Arlington</span>
</div>

<div class="is-size-5 publication-lab">
<span class="author-block"><a href="https://rvl.uta.edu">Robotic Vision Laboratory</span>
</div>

<div class="column has-text-centered">
<div class="publication-links">

<!-- Preprint link -->
<!-- Paper link -->
<span class="link-block">
<a href="https://arxiv.org/pdf/2312.10922.pdf" class="external-link button is-normal is-rounded is-dark">
<a href="https://ieeexplore.ieee.org/document/10367844" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="ai ai-arxiv"></i>
<i class="fas fa-file-pdf"></i>
</span>
<span>Preprint</span>
<span>Paper</span>
</a>
</span>

<!-- Paper link -->
<!-- Preprint link -->
<span class="link-block">
<a href="https://ieeexplore.ieee.org/document/10367844" class="external-link button is-normal is-rounded is-dark">
<a href="https://arxiv.org/pdf/2312.10922.pdf" class="external-link button is-normal is-rounded is-dark">
<span class="icon">
<i class="fas fa-file-pdf"></i>
<i class="ai ai-arxiv"></i>
</span>
<span>Paper</span>
<span>Preprint</span>
</a>
</span>

Expand Down Expand Up @@ -156,36 +158,34 @@ <h1 class="title is-1 publication-title">NTrack: A Multiple-Object Tracker and D
<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="columns is-centered">
<!-- Abstract -->
<div class="column is-full-width">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
In agriculture, automating the accurate tracking of fruits,
vegetables, and fiber is a very tough problem. The issue becomes
extremely challenging in dynamic field environments. Yet, this
information is critical for making day-to-day agricultural
decisions, assisting breeding programs, and much more. To tackle
this dilemma, we introduce <strong>NTrack</strong>, a novel
multiple object tracking framework based on the linear
relationship between the locations of <em>neighboring</em>
tracks. <strong>NTrack</strong> computes dense optical flow and
utilizes particle filtering to guide each tracker.
Correspondences between detections and tracks are found through
data association via direct observations and indirect cues, which
are then combined to obtain an updated observation. Our modular
multiple object tracking system is independent of the underlying
detection method, thus allowing for the interchangeable use of
any off-the-shelf object detector. We show the efficacy of our
approach on the task of tracking and counting infield cotton
bolls. Experimental results show that our system exceeds
contemporary tracking and cotton boll-based counting methods by a
large margin. Furthermore, we publicly release the
<em>first</em> annotated cotton boll video dataset to the
research community.
</p>
</div>
<!-- Abstract -->
<div class="column is-full-width">
<h2 class="title is-3">Abstract</h2>
<div class="content has-text-justified">
<p>
In agriculture, automating the accurate tracking of fruits,
vegetables, and fiber is a very tough problem. The issue becomes
extremely challenging in dynamic field environments. Yet, this
information is critical for making day-to-day agricultural
decisions, assisting breeding programs, and much more. To tackle
this dilemma, we introduce <strong>NTrack</strong>, a novel
multiple object tracking framework based on the linear
relationship between the locations of <em>neighboring</em>
tracks. <strong>NTrack</strong> computes dense optical flow and
utilizes particle filtering to guide each tracker.
Correspondences between detections and tracks are found through
data association via direct observations and indirect cues, which
are then combined to obtain an updated observation. Our modular
multiple object tracking system is independent of the underlying
detection method, thus allowing for the interchangeable use of
any off-the-shelf object detector. We show the efficacy of our
approach on the task of tracking and counting infield cotton
bolls. Experimental results show that our system exceeds
contemporary tracking and cotton boll-based counting methods by a
large margin. Furthermore, we publicly release the
<em>first</em> annotated cotton boll video dataset to the
research community.
</p>
</div>
</div>
</div>
Expand All @@ -195,28 +195,26 @@ <h2 class="title is-3">Abstract</h2>
<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="columns is-centered">
<!-- Dataset -->
<div class="column is-full-width">
<h2 class="title is-3">Dataset</h2>
<div class="content has-text-justified">
<p>
The <strong>TexCot22</strong> dataset is a set of cotton crop
video sequences for training and testing multi-object tracking
methods. Each tracking sequence is 10 to 20 seconds in length.
The dataset contains of a total of 30 sequences of which 17 are
for training and the remaining 13 are for testing. The video
sequences were captured at 4K resolution and at distinct frame
rates (e.g., 10, 15, 30). There are typically 2 to 10 cotton
bolls per cluster. The average width and height of an annotated
bounding box is approximately 230 x 210 pixels. To make the
dataset robust to environmental conditions, we recorded the field
videos at separate times of day to account for varying lighting
conditions. In total, there are roughly 30 x 300 frames with
150,000 labeled instances. On average there are 70 unique cotton
bolls in each sequence.
</p>
</div>
<!-- Dataset -->
<div class="column is-full-width">
<h2 class="title is-3">Dataset</h2>
<div class="content has-text-justified">
<p>
The <strong>TexCot22</strong> dataset is a set of cotton crop
video sequences for training and testing multi-object tracking
methods. Each tracking sequence is 10 to 20 seconds in length.
The dataset contains of a total of 30 sequences of which 17 are
for training and the remaining 13 are for testing. The video
sequences were captured at 4K resolution and at distinct frame
rates (e.g., 10, 15, 30). There are typically 2 to 10 cotton
bolls per cluster. The average width and height of an annotated
bounding box is approximately 230 x 210 pixels. To make the
dataset robust to environmental conditions, we recorded the field
videos at separate times of day to account for varying lighting
conditions. In total, there are roughly 30 x 300 frames with
150,000 labeled instances. On average there are 70 unique cotton
bolls in each sequence.
</p>
</div>
</div>
</div>
Expand All @@ -226,33 +224,31 @@ <h2 class="title is-3">Dataset</h2>
<section class="section">
<div class="container is-max-desktop">
<div class="columns is-centered">
<div class="columns is-centered">
<!-- Citation -->
<div class="column is-full-width">
<h2 class="title is-3">Citation</h2>
<div class="content has-text-justified">
<p>
If you find this project useful, then please consider citing both
our paper and dataset.
</p>
<pre><code>@article{muzaddid2023ntrack,
title={NTrack: A Multiple-Object Tracker and Dataset for Infield Cotton Boll Counting},
author={Al Muzaddid, Md Ahmed and Beksi, William J},
journal={IEEE Transactions on Automation Science and Engineering},
volume={},
pages={},
doi={},
year={2023}
}</code></pre>
<pre><code>@misc{texcot22tdr,
title={TexCot22},
author={Al Muzaddid, Md Ahmed and Beksi, William J},
publisher={Texas Data Repository},
url={},
doi={},
year={2023}
}</code></pre>
</div>
<!-- Citation -->
<div class="column is-full-width">
<h2 class="title is-3">Citation</h2>
<div class="content has-text-justified">
<p>
If you find this project useful, then please consider citing both
our paper and dataset.
</p>
<pre><code>@article{muzaddid2023ntrack,
title={NTrack: A Multiple-Object Tracker and Dataset for Infield Cotton Boll Counting},
author={Al Muzaddid, Md Ahmed and Beksi, William J},
journal={IEEE Transactions on Automation Science and Engineering},
volume={},
pages={},
doi={},
year={2023}
}</code></pre>
<pre><code>@misc{texcot22tdr,
title={TexCot22},
author={Al Muzaddid, Md Ahmed and Beksi, William J},
publisher={Texas Data Repository},
url={},
doi={},
year={2023}
}</code></pre>
</div>
</div>
</div>
Expand Down

0 comments on commit 803dcf3

Please sign in to comment.