1+ <!DOCTYPE html>
2+ < html >
3+ < head >
4+ < meta charset ="utf-8 ">
5+ < meta name ="description "
6+ content ="Agricultural Autonomous Driving Dataset from Smart Farming Lab Leipzig University ">
7+ < meta name ="keywords " content ="Agriculture, Autonomous Driving, Dataset, Smart Farming ">
8+ < meta name ="viewport " content ="width=device-width, initial-scale=1 ">
9+ < title > Agricultural Autonomous Driving Dataset</ title >
10+
11+ < link href ="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro "
12+ rel ="stylesheet ">
13+
14+ < link rel ="stylesheet " href ="./static/css/bulma.min.css ">
15+ < link rel ="stylesheet " href ="./static/css/bulma-carousel.min.css ">
16+ < link rel ="stylesheet " href ="./static/css/bulma-slider.min.css ">
17+ < link rel ="stylesheet " href ="./static/css/fontawesome.all.min.css ">
18+ < link rel ="stylesheet "
19+ href ="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css ">
20+ < link rel ="stylesheet " href ="./static/css/index.css ">
21+
22+ < script src ="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js "> </ script >
23+ < script defer src ="./static/js/fontawesome.all.min.js "> </ script >
24+ < script src ="./static/js/bulma-carousel.min.js "> </ script >
25+ < script src ="./static/js/bulma-slider.min.js "> </ script >
26+ < script src ="./static/js/index.js "> </ script >
27+
28+
29+
30+ <!-- Plotly for interactive plots -->
31+ < script src ="https://cdn.plot.ly/plotly-latest.min.js "> </ script >
32+ </ head >
33+ < body >
34+
35+ < section class ="hero ">
36+ < div class ="hero-body ">
37+ < div class ="container is-max-desktop ">
38+ < div class ="columns is-centered ">
39+ < div class ="column has-text-centered ">
40+ < h1 class ="title is-1 publication-title "> Agricultural Autonomous Driving Dataset (Preview)</ h1 >
41+ < div class ="is-size-5 publication-authors ">
42+ < span class ="author-block ">
43+ < a href ="https://research.uni-leipzig.de/smart-farming/#/en " target ="_blank " rel ="noopener "> Smart Farming Lab</ a > </ span >
44+ </ div >
45+
46+ < div class ="is-size-5 publication-authors ">
47+ < span class ="author-block "> Leipzig University</ span >
48+ </ div >
49+
50+ <!-- Logos -->
51+ < div class ="columns is-centered mt-2 ">
52+ < div class ="column is-narrow ">
53+ < img src ="./static/images/567-258-max.png " alt ="Smart Farming Lab " style ="height: 160px; margin: 10px; ">
54+ </ div >
55+ < div class ="column is-narrow ">
56+ < img src ="./static/images/1181-1181-max.png " alt ="Leipzig University " style ="height: 160px; margin: 10px; ">
57+ </ div >
58+ </ div >
59+ </ div >
60+ </ div >
61+ </ div >
62+ </ div >
63+ </ section >
64+ < section class ="section " style ="padding-top: 1.5rem; ">
65+ < div class ="container is-max-desktop ">
66+ <!-- Abstract. -->
67+ < div class ="columns is-centered has-text-centered ">
68+ < div class ="column is-four-fifths ">
69+ < h2 class ="title is-3 "> Abstract</ h2 >
70+ < div class ="content has-text-justified ">
71+ < p >
72+ We present a large (100GB+) comprehensive multi-modal dataset for autonomous driving in agricultural environments,
73+ captured using a sophisticated sensor setup including multiple cameras, LiDAR, GPS, and IMU sensors mounted on a Fendt 728 Variotractor.
74+ </ p >
75+ < p >
76+ The dataset includes synchronized data from:
77+ < strong > 6 cameras</ strong > (rear left/mid/right, side left/right, stereo ZED),
78+ < strong > LiDAR point clouds</ strong > from an Ouster sensor,
79+ < strong > high-precision GPS</ strong > positioning with Novatel OEM7,
80+ and < strong > IMU measurements</ strong > for comprehensive environmental perception.
81+ </ p >
82+ < p >
83+ This dataset is designed to support research in agricultural robotics, autonomous navigation
84+ in unstructured environments, computer vision, environmental mapping and multi-modal sensor fusion.
85+ </ p >
86+ </ div >
87+ </ div >
88+ </ div >
89+ <!--/ Abstract. -->
90+
91+ <!-- Dataset Overview -->
92+ < div class ="columns is-centered has-text-centered ">
93+ < div class ="column is-four-fifths ">
94+ < h2 class ="title is-3 "> Dataset Overview</ h2 >
95+ < div class ="content has-text-justified ">
96+ < div class ="columns ">
97+ < div class ="column ">
98+ < h4 > Sensors</ h4 >
99+ < ul >
100+ < li > 6 RGB Cameras (multiple viewpoints)</ li >
101+ < li > Ouster LiDAR (3D point clouds)</ li >
102+ < li > Novatel OEM7 GPS/INS</ li >
103+ < li > High-frequency IMU</ li >
104+ </ ul >
105+ </ div >
106+ < div class ="column ">
107+ < h4 > Data Characteristics</ h4 >
108+ < ul >
109+ < li > Location: Lehr- und Forschungsgut Oberholz der Universität Leipzig</ li >
110+ < li > Seasons: Currently Spring and Summer, will be expanded to include Fall and Winter</ li >
111+ < li > Tasks: Plowing, tilling, will be expanded to include planting, harvesting, and more</ li >
112+ </ ul >
113+ </ div >
114+ </ div >
115+ </ div >
116+ </ div >
117+ </ div >
118+ </ div >
119+ </ section >
120+
121+ < section class ="section ">
122+ < div class ="container is-max-desktop ">
123+
124+ <!-- Camera Views -->
125+ < div class ="columns is-centered ">
126+ < div class ="column is-full-width ">
127+ < h2 class ="title is-3 "> Multi-Camera System</ h2 >
128+ < div class ="content has-text-justified ">
129+ < p >
130+ Our agricultural vehicle is equipped with 6 cameras providing comprehensive 360° coverage
131+ for robust safe perception in farming environments. All cameras are synchronized.
132+ Below they are displayed in a single composite video view extracted from the rosbag data.
133+ </ p >
134+ </ div >
135+
136+ <!-- Synchronized Camera Videos -->
137+ < div class ="columns is-multiline " id ="camera-grid ">
138+ <!-- Synchronized camera videos will be populated here -->
139+ </ div >
140+ </ div >
141+ </ div >
142+
143+ <!-- GPS Trajectory -->
144+ < div class ="columns is-centered ">
145+ < div class ="column is-full-width ">
146+ < h2 class ="title is-3 "> GNSS Trajectory</ h2 >
147+ < div class ="content has-text-justified ">
148+ </ div >
149+
150+ < div id ="gps-live-plot " style ="width: 100%; height: 400px; border: 1px solid #ccc; ">
151+ <!-- Complete GPS trajectory map -->
152+ </ div >
153+ </ div >
154+ </ div >
155+
156+ <!-- LiDAR Registration Visualization -->
157+ < div class ="columns is-centered ">
158+ < div class ="column is-full-width ">
159+ < h2 class ="title is-3 "> Precision LIDAR Point Clouds</ h2 >
160+ < div class ="content has-text-justified ">
161+ < p >
162+ The Ouster OS1 LiDAR (128 scanlines) is mounted < strong > 60° downward-facing at 2m height</ strong > . This enables a high-resolution 3D point cloud of the environment that can be used for precise mapping and localization,
163+ for object detection and classification and as a deterministic safety sensor. Below is a point cloud of the farmyard environment as seen by the LiDAR.
164+ </ p >
165+ </ div >
166+
167+ < div class ="has-text-centered ">
168+ < figure class ="image ">
169+ < img src ="./static/images/lidar_registration.png "
170+ alt ="LiDAR-Camera Registration Visualization "
171+ style ="max-width: 100%; height: auto; border: 1px solid #ccc; border-radius: 8px; ">
172+ </ figure >
173+ < p class ="has-text-grey mt-2 ">
174+ < em > LiDAR registration showing the farmyard of the Lehr- und Forschungsgut Oberholz.</ em >
175+ </ p >
176+ </ div >
177+ </ div >
178+ </ div >
179+ </ div >
180+ </ section >
181+
182+
183+
184+ < footer class ="footer ">
185+ < div class ="container ">
186+ < div class ="content has-text-centered ">
187+ </ div >
188+ < div class ="columns is-centered ">
189+ < div class ="column is-8 ">
190+ < div class ="content ">
191+ < p >
192+ This website is licensed under a < a rel ="license "
193+ href ="http://creativecommons.org/licenses/by-sa/4.0/ "> Creative
194+ Commons Attribution-ShareAlike 4.0 International License</ a > .
195+ </ p >
196+ < p >
197+ Website template borrowed from < a
198+ href ="https://github.com/nerfies/nerfies.github.io "> Nerfies</ a > .
199+ </ p >
200+ </ div >
201+ </ div >
202+ </ div >
203+ </ div >
204+ </ footer >
205+
206+ </ body >
207+ </ html >
0 commit comments