https://endoloc.netlify.app/

1<!DOCTYPE html>
2<html>
3<head>
4  <meta charset="utf-8">
5<!-- This site is hosted on Netlify. Anyone can build and deploy a site
6     like this one for free: https://netlify.new/?utm_campaign=loops&utm_source=ai-legible&utm_medium=owned&utm_content=comment&utm_id=45b09cca-b3c0-428a-8d3a-fc28e794a0a5
7     Netlify hosting facts for this site: static/SSR served via Netlify Edge. -->
8  <!-- Meta tags for social media banners, these should be filled in appropriatly as they are your "business card" -->
9  <!-- Replace the content tag with appropriate information -->
10  <meta name="description" content="DESCRIPTION META TAG">
11  <meta property="og:title" content="SOCIAL MEDIA TITLE TAG"/>
12  <meta property="og:description" content="SOCIAL MEDIA DESCRIPTION TAG TAG"/>
13  <meta property="og:url" content="URL OF THE WEBSITE"/>
14  <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X630-->
15  <meta property="og:image" content="static/image/your_banner_image.png" />
16  <meta property="og:image:width" content="1200"/>
17  <meta property="og:image:height" content="630"/>
18
19
20  <meta name="twitter:title" content="TWITTER BANNER TITLE META TAG">
21  <meta name="twitter:description" content="TWITTER BANNER DESCRIPTION META TAG">
22  <!-- Path to banner image, should be in the path listed below. Optimal dimenssions are 1200X600-->
23  <meta name="twitter:image" content="static/images/your_twitter_banner_image.png">
24  <meta name="twitter:card" content="summary_large_image">
25  <!-- Keywords for your paper to be indexed by-->
26  <meta name="keywords" content="KEYWORDS SHOULD BE PLACED HERE">
27  <meta name="viewport" content="width=device-width, initial-scale=1">
28
29
30  <title>EndoLoc</title>
31  <link rel="icon" type="image/x-icon" href="static/images/icon.ico">
32  <link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro"
33  rel="stylesheet">
34
35  <link rel="stylesheet" href="static/css/bulma.min.css">
36  <link rel="stylesheet" href="static/css/bulma-carousel.min.css">
37  <link rel="stylesheet" href="static/css/bulma-slider.min.css">
38  <link rel="stylesheet" href="static/css/fontawesome.all.min.css">
39  <link rel="stylesheet"
40  href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
41  <link rel="stylesheet" href="static/css/index.css">
42
43  

43<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>

43
44  

44<script src="https://documentcloud.adobe.com/view-sdk/main.js"></script>

44
45  

45<script defer src="static/js/fontawesome.all.min.js"></script>

45
46  

46<script src="static/js/bulma-carousel.min.js"></script>

46
47  

47<script src="static/js/bulma-slider.min.js"></script>

47
48  

48<script src="static/js/index.js"></script>

48
49</head>
50<body>
51
52
53  <section class="hero">
54    <div class="hero-body">
55      <div class="container is-max-desktop">
56        <div class="columns is-centered">
57          <div class="column has-text-centered">
58            <h1 class="title is-1 publication-title">EndoLoc: Relative Pose Regression Framework with Transformation and Correlation Features for In-vivo Visual Localization of Endoscope</h1>
59            <div class="is-size-5 publication-authors">
60              <!-- Paper authors -->
61              <span class="author-block">
62                <big><b>Liangjing Shao</b><sup>1,2,3,*</sup>,</big></span>
63                <span class="author-block">
64                  <big><b>Benshuang Chen</b><sup>1,2</sup>,</big></span>
65                <span class="author-block">
66                  <big><b>Shuting Zhao</b><sup>1,2</sup>,</big></span>
67                  <span class="author-block">
68                    <big><b>Fuming Yang</b><sup>4</sup>,</big>
69                  </span>
70                  <span class="author-block">
71                    <big><b>Xinrong Chen</b><sup>1,2,#</sup></big>
72                  </span>
73                  </div>
74
75                  <br>
76
77                  <div class="is-size-5 publication-authors">
78                    <span class="author-block">1. College of Biomedical Engineering, Fudan University</span>
79                    <span class="author-block">2. Shanghai Key laboratory of Medical Image Computing and Computer Assisted Intervention</span>
80                    <span class="author-block">3. Department of Electronic Engineering, The Chinese University of Hong Kong</span>
81                    <span class="author-block">4. Department of Neurosurgery, Shanghai General Hospital, Shanghai JiaoTong University School of Medicine</span>
82                    <span class="eql-cntrb"><br>Accepted by <a href="https://ieee-cas.org/publication/tcsvt" style="color: #11563B;">IEEE TCSVT</a></span>
83                    <span class="eql-cntrb"><small><br><sup>#</sup>Corresponding Authors</small></span>
84                    <span class="eql-cntrb"><small><br><sup>*</sup>This work was done when Liangjing was a master student with Fudan University</small></span>
85                  </div>
86
87        </div>
88      </div>
89    </div>
90  </div>
91</section>
92
93
94<!-- Teaser video-->
95<section class="hero teaser">
96  <div class="container is-max-desktop">
97    <div class="hero-body">
98      <video poster="" id="tree" autoplay controls muted loop height="100%">
99        <!-- Your video here -->
100        <source src="static/videos/nasal.mp4"
101        type="video/mp4">
102      </video>
103      <h2 class="subtitle has-text-centered">
104        Demo Videos of Real-time Visual Localization in <b>Nasal Endoscopy</b>
105      </h2>
106    </div>
107  </div>
108  <div class="container is-max-desktop">
109    <div class="hero-body">
110      <video poster="" id="tree" autoplay controls muted loop height="100%">
111        <!-- Your video here -->
112        <source src="static/videos/colon.mp4"
113        type="video/mp4">
114      </video>
115      <h2 class="subtitle has-text-centered">
116        Demo Videos of Real-time Visual Localization in <b>Colonoscopy</b>
117      </h2>
118    </div>
119  </div>
120</section>
121<!-- End teaser video -->
122
123<!-- Paper abstract -->
124<section class="section hero is-light">
125  <div class="container is-max-desktop">
126    <div class="columns is-centered has-text-centered">
127      <div class="column is-four-fifths">
128        <h2 class="title is-3">Abstract</h2>
129        <div class="content has-text-justified">
130          <p>
131            Real-time localization of endoscope is significant for navigation and automation of endoscopic diagnosis and minimally invasive surgery. However, traditional localization based on optical tracking or magnetic tracking is easily influenced by occlusion or electromagnetic medical instruments and is complicated for implementation. Meanwhile, transformation and correlation information in image pairs are still ignored in existing visual localization methods for endoscopy. In this work, a novel relative pose regression framework is proposed to perform relative pose estimation and absolute pose tracking for endoscope based on endoscopic videos. Firstly, scene features and transformation features are respectively extracted from endoscopic observations and the corresponding optical flow by the proposed feature encoder based on gated convolution, which can prevent gradient vanishing when training the encoder from scratch on endoscopic data. Furthermore, A novel correlation module based on cross attention is proposed to extract correlation features from two input images, which can capture more key features in endoscopic frames with more limited vision from local to global. Moreover, a novel pose decoder with upsampling and downsampling on the channel dimension is utilized to extract richer representation from the concatenated feature map for relative transformation vector prediction. The proposed method outperforms the state-of-the-art methods on the datasets from nasal endoscopy and colonoscopy, with less than 3\% localization error on average. The further experiments also demonstrate the efficiency of the proposed method.
132          </p>
133        </div>
134      </div>
135    </div>
136  </div>
137</section>
138<!-- End paper abstract -->
139
140
141<!--BibTex citation -->
142  <section class="section" id="BibTeX">
143    <div class="container is-max-desktop content">
144      <h2 class="title">BibTeX</h2>
145      <pre><code>BibTex Code Here</code></pre>
146    </div>
147</section>
148<!--End BibTex citation -->
149
150<!-- Statcounter tracking code -->
151  
152<!-- You can add a tracker to track page visits by creating an account at statcounter.com -->
153
154    <!-- End of Statcounter Code -->
155
156  </body>
157  </html>