├── README.md └── images ├── dataset_structure.png ├── gt_und.png ├── gt_uni.png ├── sensors.png ├── und.png ├── und_slam.png ├── uni.png ├── uni_1_thumbnail.png ├── uni_2_thumbnail.png ├── uni_3_thumbnail.png └── uni_slam.png /README.md: -------------------------------------------------------------------------------- 1 | # MIN3D 2 | [![DOI:10.1007/s41064-023-00260-0](https://img.shields.io/badge/DOI-10.1007/s41064--023--00260--0-ADA99E.svg)](https://doi.org/10.1007/s41064-023-00260-0) 3 | [![Static Badge](https://img.shields.io/badge/83117-cd8b00?label=AZON2&labelColor=0e1d42&link=http%3A%2F%2Fzasobynauki.pl%2Fzasoby%2F83117)](http://zasobynauki.pl/zasoby/83117) 4 | 5 | 6 |
7 | 8 | 9 | 10 | 11 |
12 | 13 | ## MultI-seNsor 3D mapping with an unmanned ground vehicle for mining applications 14 | 15 | #### Robotic dataset for developing mobile mapping solutions for challenging, GNSS-denied and subterranean environments 16 | ### Authors 17 | Paweł Trybała, Jarosław Szrek, Fabio Remondino, Paulina Kujawa, Jacek Wodecki, Jan Blachowski, Radosław Zimroz 18 | 19 | ## Abstract 20 | The research potential in the field of mobile mapping technologies, particularly for specific applications, is hindered by several constraints. These include the need for costly hardware to collect data (possibly with automation using mobile platforms such as robots or drones), limited access to target sites with specific environmental conditions, and the establishment of a ground truth model for evaluating developed solutions. To address these challenges, the utilization of open datasets presents a viable solution. However, the availability of datasets that encompass truly demanding mixed indoor-outdoor and subterranean conditions is currently limited. To alleviate this issue, we propose the MIN3D dataset (MultI-seNsor 3D mapping with an unmanned ground vehicle for mining applications). This dataset was gathered using a wheeled mobile robot in two distinct locations: (i) textureless dark corridors within a university campus and (ii) tunnels of an underground site in Walim (Poland). It comprises around 150 GB of raw data, including images captured by multiple co-calibrated monocular and stereo cameras, a thermal camera, 2 LiDARs, and 3 inertial measurement units. Reliable ground truth point clouds were obtained using a survey-grade terrestrial laser scanner. By openly sharing this dataset, we aim to support the efforts of the scientific community in developing robust methods for navigation and mapping in challenging underground conditions. In the paper, we describe the collected data and provide an initial accuracy assessment of some visual- and LiDAR-based simultaneous localization and mapping (SLAM) algorithms for selected sequences. Encountered problems, open research questions and areas that could benefit from utilizing our dataset are discussed. 21 | 22 | ## Main Contributions: 23 | - Challenging scenes in indoor and underground conditions, targeting typical issues of subterranean environments: variable illumination, featureless or textureless areas, repeating or complex geometry. 24 | - Simultaneously acquired data with many sensors (cameras, LiDAR scanners, IMUs) on a single robotic platform. 25 | - High-quality reference point clouds, acquired with a survey-grade Terrestrial Laser Scanner. 26 | 27 | ## Related papers 28 | Trybała, P., Szrek, J., Remondino, F. et al. MIN3D Dataset: MultI-seNsor 3D Mapping with an Unmanned Ground Vehicle. PFG (2023). 29 | 30 | Trybała, P., Szrek, J., Remondino, F. et al. CALIBRATION OF A MULTI-SENSOR WHEELED ROBOT FOR THE 3D MAPPING OF UNDERGROUND MINING TUNNELS. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-2/W2-2022, 135–142 (2022). 31 | 32 | If you use our work, please cite: 33 | ```bibtex 34 | @article{Trybala2023MIN3D, 35 | title = {MIN3D Dataset: MultI-seNsor 3D Mapping with an Unmanned Ground Vehicle}, 36 | ISSN = {2512-2819}, 37 | url = {http://dx.doi.org/10.1007/s41064-023-00260-0}, 38 | DOI = {10.1007/s41064-023-00260-0}, 39 | journal = {PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science}, 40 | publisher = {Springer Science and Business Media LLC}, 41 | author = {Trybała, Paweł and Szrek, Jarosław and Remondino, Fabio and Kujawa, Paulina and Wodecki, Jacek and Blachowski, Jan and Zimroz, Radosław}, 42 | year = {2023}, 43 | month = oct 44 | } 45 | 46 | @article{Trybala2022calibration, 47 | title = {CALIBRATION OF A MULTI-SENSOR WHEELED ROBOT FOR THE 3D MAPPING OF UNDERGROUND MINING TUNNELS}, 48 | volume = {XLVIII-2/W2-2022}, 49 | ISSN = {2194-9034}, 50 | url = {http://dx.doi.org/10.5194/isprs-archives-XLVIII-2-W2-2022-135-2022}, 51 | DOI = {10.5194/isprs-archives-xlviii-2-w2-2022-135-2022}, 52 | journal = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences}, 53 | publisher = {Copernicus GmbH}, 54 | author = {Trybała, P. and Szrek, J. and Remondino, F. and Wodecki, J. and Zimroz, R.}, 55 | year = {2022}, 56 | month = dec, 57 | pages = {135–142} 58 | } 59 | ``` 60 | 61 | # Dataset 62 | 63 | ## Sensor Setup 64 |
65 | 66 |
67 | 68 | Sensor/Device|Model|Specification 69 | :--:|:--:|:--: 70 | Basler Stereo | acA1440-220um |2x720x540 px, 15 Hz 71 | Intel RealSense RGB | D455 | 640x480 px, 15 Hz 72 | Intel RealSense Stereo | D455 | 2x640x480 px, 15 Hz 73 | Intel RealSense Depth | D455 | 640x480 px, 15 Hz 74 | FLIR IR | VUE-640 | 640x512 px, 15 Hz 75 | LiDAR#1 | Livox Horizon | 10 Hz, ~20 mm accuracy individual point timestamps 76 | LiDAR#2 | Velodyne VLP-16 | 10 Hz, ~20 mm accuracy, actuated (180° rotation) 77 | IMU#1 | Livox | 6-axis, 200 Hz 78 | IMU#2 | RealSense | 6-axis, 400 Hz 79 | IMU#3 | NGIMU | 6-axis, 20 Hz 80 | GT 3D Scanner | Riegl VZ-400i | ~5 mm accuracy 81 | 82 | Point clouds shared as .ply files 83 | 84 | RGB/IR images as .png files 85 | 86 | Depth maps: .png images, 16bit int - metric depth in millimeters 87 | 88 | IMU data as .csv files 89 | 90 | ## Ground Truth Point Clouds 91 | Acquired with a Riegl VZ-400i TLS and registered with RiScan PRO 92 | 93 |
94 | 95 | 96 |
97 | 98 | 99 | ## Data Sequences 100 | Our dataset consists of 8 sequences in total. 101 | 102 |
103 | 104 |
105 | 106 | ## University dataset 107 | 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | 116 | 117 | 118 | 119 | 120 | 121 | 122 | 123 | 124 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | 134 | 135 | 136 | 137 | 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 147 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | 163 | 164 | 165 | 166 | 167 | 168 | 169 | 170 | 171 | 172 | 173 | 174 | 175 | 176 | 177 | 178 | 179 | 180 | 181 | 182 | 183 | 184 | 185 | 186 | 187 | 188 | 189 | 190 | 191 | 192 | 193 | 194 | 195 | 196 | 197 | 198 | 199 | 200 | 201 | 202 | 203 | 204 | 205 | 206 | 207 | 208 | 209 | 210 | 211 | 212 | 213 | 214 | 215 | 216 | 217 | 218 | 219 | 220 | 221 |
Sequence123
Thumbnail
FeaturesGround floorGround floor-outdoor loopMultiple indoor loops with varying illumination
Size [GB]26.122.118.9
Cameras
Basler stereouni_1_basler_left, uni_1_basler_rightuni_2_basler_left, uni_2_basler_rightuni_3_basler_left, uni_3_basler_right
RGBuni_1_rgbuni_2_rgbuni_3_rgb
RealSense Stereouni_1_realsense_left, uni_1_realsense_rightuni_2_realsense_left, uni_2_realsense_rightuni_3_realsense_left, uni_3_realsense_right
RealSense Depthuni_1_realsense_depthuni_2_realsense_depthuni_3_realsense_depth
RealSense RGBuni_1_realsense_rgbuni_2_realsense_rgbuni_3_realsense_rgb
FLIR IRuni_1_iruni_2_iruni_3_ir
IMUs
Livox internal IMUuni_1_imu_livoxuni_2_imu_livoxuni_3_imu_livox
RealSense IMUuni_1_imu_realsenseuni_2_imu_realsenseuni_3_imu_realsense
NGIMUuni_1_ngimu_accelerations, uni_1_ngimu_euler_anglesuni_2_ngimu_accelerations, uni_2_ngimu_euler_anglesuni_3_ngimu_accelerations, uni_3_ngimu_euler_angles
LiDARs
Velodyne VLP-16uni_1_velodyneuni_2_velodyneuni_3_velodyne
Livoxuni_1_livoxuni_2_livoxuni_3_livox
Ground truth
Riegl VZ-400iuni_1_gtuni_2_gtuni_3_gt
Calibration datacalibration
222 | 223 | ## Underground dataset 224 | 225 | 226 | 227 | 228 | 229 | 230 | 231 | 232 | 233 | 234 | 235 | 236 | 237 | 238 | 239 | 240 | 241 | 242 | 243 | 244 | 245 | 246 | 247 | 248 | 249 | 250 | 251 | 252 | 253 | 254 | 255 | 256 | 257 | 258 | 259 | 260 | 261 | 262 | 263 | 264 | 265 | 266 | 267 | 268 | 269 | 270 | 271 | 272 | 273 | 274 | 275 | 276 | 277 | 278 | 279 | 280 | 281 | 282 | 283 | 284 | 285 | 286 | 287 | 288 | 289 | 290 | 291 | 292 | 293 | 294 | 295 | 296 | 297 | 298 | 299 | 300 | 301 | 302 | 303 | 304 | 305 | 306 | 307 | 308 | 309 | 310 | 311 | 312 | 313 | 314 | 315 | 316 | 317 | 318 | 319 | 320 | 321 | 322 | 323 | 324 | 325 | 326 | 327 | 328 | 329 | 330 | 331 | 332 | 333 | 334 | 335 | 336 | 337 | 338 | 339 | 340 | 341 | 342 | 343 | 344 | 345 | 346 | 347 | 348 | 349 | 350 | 351 | 352 | 353 | 354 | 355 | 356 | 357 |
Sequence12345
FeaturesMain tunnel, forward passMain tunnel, return passLoop closures, complicated trajectoryLost camera problem, loop closuresSide tunnel, less structured
Size [GB]13.210.817.913.922.5
Cameras
Basler stereound_1_basler_left, und_1_basler_rightund_2_basler_left, und_2_basler_rightund_3_basler_left, und_3_basler_rightund_4_basler_left, und_4_basler_rightund_5_basler_left, und_5_basler_right
RGBund_1_rgbund_2_rgbund_3_rgbund_4_rgbund_5_rgb
RealSense Stereound_1_realsense_left, und_1_realsense_rightund_2_realsense_left, und_2_realsense_rightund_3_realsense_left, und_3_realsense_rightund_4_realsense_left, und_4_realsense_rightund_5_realsense_left, und_5_realsense_right
RealSense Depthund_1_realsense_depthund_2_realsense_depthund_3_realsense_depthund_4_realsense_depthund_5_realsense_depth
RealSense RGBund_1_realsense_rgbund_2_realsense_rgbund_3_realsense_rgbund_4_realsense_rgbund_5_realsense_rgb
FLIR IRund_1_irund_2_irund_3_irund_4_irund_5_ir
IMUs
Livox internal IMUund_1_imu_livoxund_2_imu_livoxund_3_imu_livoxund_4_imu_livoxund_5_imu_livox
RealSense IMUund_1_imu_realsenseund_2_imu_realsenseund_3_imu_realsenseund_4_imu_realsenseund_5_imu_realsense
NGIMUund_1_ngimu_accelerations, und_1_ngimu_euler_anglesund_2_ngimu_accelerations, und_2_ngimu_euler_anglesund_3_ngimu_accelerations, und_3_ngimu_euler_anglesund_4_ngimu_accelerations, und_5_ngimu_euler_anglesund_5_ngimu_accelerations, und_5_ngimu_euler_angles
LiDARs
Velodyne VLP-16und_1_velodyneund_2_velodyneund_3_velodyneund_4_velodyneund_5_velodyne
Livoxund_1_livoxund_2_livoxund_3_livoxund_4_livoxund_5_livox
Ground truth
Riegl VZ-400iunderground_gt (save as a .las file)
Calibration data (same as University)calibration
358 | 359 | 360 | ## Acknowledgements 361 | The authors offer special thanks to Walimskie Drifts in Walim (https://sztolnie.pl) for making the facility available for data acquisition. 362 | 363 | ## Funding 364 | This work was partly supported by EIT RawMaterials GmbH within the activities of the AMICOS—Autonomous Monitoring and Control System for Mining Plants—project (Agreement No. 19018) and VOT3D—project (Agreement No. 21119). The work was also partly supported by the FAIR project, Piano Nazionale di Ripresa e Resilienza. 365 | 366 | ## Contact 367 | This dataset is provided for academic purposes. For any inquiries please contact . 368 | 369 | ## License 370 | The data provided here is licensed under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/). 371 | -------------------------------------------------------------------------------- /images/dataset_structure.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/dataset_structure.png -------------------------------------------------------------------------------- /images/gt_und.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/gt_und.png -------------------------------------------------------------------------------- /images/gt_uni.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/gt_uni.png -------------------------------------------------------------------------------- /images/sensors.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/sensors.png -------------------------------------------------------------------------------- /images/und.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/und.png -------------------------------------------------------------------------------- /images/und_slam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/und_slam.png -------------------------------------------------------------------------------- /images/uni.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/uni.png -------------------------------------------------------------------------------- /images/uni_1_thumbnail.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/uni_1_thumbnail.png -------------------------------------------------------------------------------- /images/uni_2_thumbnail.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/uni_2_thumbnail.png -------------------------------------------------------------------------------- /images/uni_3_thumbnail.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/uni_3_thumbnail.png -------------------------------------------------------------------------------- /images/uni_slam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/3DOM-FBK/MIN3D/e9103ae4b407018bfa9c4454bc47be5c14e71948/images/uni_slam.png --------------------------------------------------------------------------------