I am planning to develop a monocular visual odometry system. Is there any indoor dataset available to the public, along with the ground truth, on which I can test my approach?
Note: I am already aware of the KITTI Vision Benchmark Suite which provides stereo data for outdoor vehicles.
If anyone has access to the datasets used in the following paper [SVO14], it would be even more great: http://rpg.ifi.uzh.ch/docs/ICRA14_Forster.pdf
This is another more recent one, based on the paper A Photometrically Calibrated Benchmark For Monocular Visual Odometry by Engel et al:
http://vision.in.tum.de/data/datasets/mono-dataset
This gives both indoor and outdoor scenes, with calibration (or the corresponding sequences so you can calibrate yourself). I haven't tested it fully myself but it seems a rather complete dataset.
http://vision.in.tum.de/data/datasets/rgbd-dataset
This is a set of recordings for the Kinect and Asus Xtion pro, which are all indoors (in offices and a hangar). It comes with precise ground truth from a motion capturing system.
The data is available as ROS bag files, but also as a tarball with png images with a text file for the trajectory.
There are also some scripts to benchmark your results against the ground truth.
I found a monocular dataset captured from a Micro Aerial Vehicle (MAV), and it has been been made available here: http://projects.asl.ethz.ch/sfly/org/doku.php?id=mav%20datasets
In case the url stops worksing in the future, I am adding the name of the publication that came along with this dataset: "A Benchmarking Tool for MAV Visual Pose Estimation" Int. Conf. Control, Automation, Robotics and Vision Singapore, 7-10th December 2010
I am not sure if there are monocular odometry datasets there, (I think it is mostly for standard 2D laser based SLAM), but you should check out radish.
