RISEdb: A Novel Indoor Localization Dataset
Sanchez Belenguer, Carlos; Wolfart, Erik; Casado Coscollá, Álvaro; Sequeira, Vitor
Joint Research Centre (Ispra) - European Commission
25th International Conference on Pattern Recognition (ICPR2020), Milano 10-15 January 2021

CONTACT:
carlos.sanchez-belenguer@ec.europa.eu

ABSTRACT:
In this paper we introduce a novel public dataset for developing and benchmarking indoor localization systems. We have selected and 3D mapped a set of representative indoor environments including a large office building, a conference room, a workshop, an exhibition area and a restaurant. Our acquisition pipeline is based on a portable LiDAR SLAM backpack to map the buildings and to accurately track the pose of the user as it moves freely inside them. We introduce the calibration procedures that enable us to acquire and geo-reference live data coming from different independent sensors rigidly attached to the backpack. This has allowed us to collect long sequences of spherical and stereo images, together with all the sensor readings coming from a consumer smartphone and locate them inside the map with centimetre accuracy. The dataset addresses many of the limitations of existing indoor localization datasets regarding the scale and diversity of the mapped buildings; the number of acquired sequences under varying conditions; the accuracy of the ground-truth trajectory; the availability of a detailed 3D model and the availability of different sensor types. It enables the benchmarking of existing and the development of new indoor localization approaches, in particular for deep learning based systems that require large amounts of labeled training data.

DATASET STRUCTURE:
In the root level there is a folder for each different building.

Each building contains a map.7z file, with the following files:
 - map-xcm.ply: a 3D point cloud in PLY format sampled at "x" centimetres of the building that defines the reference frame (world) in which 3D poses are expressed.
 - blueprints.png: a 2D top-view of the building in PNG format.
 - blueprints.json: world coordinates of the center/corners of the image and the scale (metres/pixel)

Each building contains a sub-folder for each acquisition with 3 files:
 - phone.tar: geo-referenced/timestamped smartphone data in the format described in the document sensors.pdf
 - spherical.tar: geo-referenced/timestamped spherical images in jpg format and equi-rectangular projection. The info.txt file specifies, for each image, the pose of the camera (in the world reference frame defined by the map) and the time in which the image was acquired (all sensor timestamps are in the same time reference frame).
  - zed.tar: geo-referenced/timestamped stereo images in png format. The info.txt file contains the following data:
	* Camera matrix for each of the two cameras (left - right)
	* Lens distortion coefficients for each camera
	* Extrinsic calibration between the two cameras (assuming the left camera in the origin)
	* For each pair of images:
		+ The pose of the left camera and the time in which the image was acquired (all sensor timestamps are in the same time reference frame).
		+ The readings of the IMU when the image was acquired.
		+ The readings of the magnetometer when the image was acquired.
		+ The reading of the barometer when the image was acquired