===== Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery Datasets =====
for the RA-L 2019 publication:
Margarita Grinvald, Fadri Furrer, Tonci Novkovic, Jen Jen Chung, Cesar Cadena, Roland Siegwart, Juan Nieto, "Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery", //IEEE Robotics and Automation Letters//, 2019. [[https://arxiv.org/pdf/1903.00268.pdf|pdf]]
{{ ::mobmi00.png?direct&600 |Semantic instance-aware map of office floor}}
=== Datasets ===
Here is the output of $ rosbag info for the sequence 231 from the SceneNN dataset bag:
path: scenenn_231.bag
version: 2.0
duration: 3:06s (186s)
start: Jan 01 1970 01:00:00.03 (0.03)
end: Jan 01 1970 01:03:06.35 (186.35)
size: 7.9 GB
messages: 27495
compression: none [5500/5500 chunks]
types: sensor_msgs/CameraInfo [c9a58c1b0b154e0e6da7578cb991d214]
sensor_msgs/Image [060021388200f6f0f447d0fcd9c64743]
tf/tfMessage [94810edda583a504dfda3829e70d7eec]
topics: /camera/depth/camera_info 5499 msgs : sensor_msgs/CameraInfo
/camera/depth/image_raw 5499 msgs : sensor_msgs/Image
/camera/rgb/camera_info 5499 msgs : sensor_msgs/CameraInfo
/camera/rgb/image_raw 5499 msgs : sensor_msgs/Image
/tf 5499 msgs : tf/tfMessage
Following is the rosbag information about the office floor sequence captured with two Primesense cameras for the online robotic mapping experiment:
path: asl_office_floor.bag
version: 2.0
duration: 5:12s (312s)
start: Feb 14 2019 17:18:42.10 (1550161122.10)
end: Feb 14 2019 17:23:54.84 (1550161434.84)
size: 6.3 GB
messages: 118782
compression: none [6223/6223 chunks]
types: sensor_msgs/CameraInfo [c9a58c1b0b154e0e6da7578cb991d214]
sensor_msgs/Image [060021388200f6f0f447d0fcd9c64743]
tf2_msgs/TFMessage [94810edda583a504dfda3829e70d7eec]
topics: /ps_front/depth_registered/camera_info 1555 msgs : sensor_msgs/CameraInfo
/ps_front/depth_registered/image_raw 1555 msgs : sensor_msgs/Image
/ps_front/rgb/camera_info 1556 msgs : sensor_msgs/CameraInfo
/ps_front/rgb/image_raw 1556 msgs : sensor_msgs/Image
/ps_table/depth_registered/camera_info 1555 msgs : sensor_msgs/CameraInfo
/ps_table/depth_registered/image_raw 1555 msgs : sensor_msgs/Image
/ps_table/rgb/camera_info 1556 msgs : sensor_msgs/CameraInfo
/ps_table/rgb/image_raw 1556 msgs : sensor_msgs/Image
/tf 106338 msgs : tf2_msgs/TFMessage (2 connections)
=== Download Links ===
[[http://robotics.ethz.ch/~asl-datasets/RAL-2019-voxblox-plusplus/scenenn_231/scenenn_231.bag|scenenn_231.bag]] -- 7.9 GB -- sequence 231 from the SceneNN dataset as RGB-D rosbag.
[[http://robotics.ethz.ch/~asl-datasets/RAL-2019-voxblox-plusplus/office_floor/asl_office_floor.bag|asl_office_floor.bag]] -- 6.3 GB -- office floor sequence captured for the online robotic mapping experiment.