# Swisslog dataset ## Introduction The dataset is produced within the [Safelog project](http://safelog-project.eu/) and is used for the evaluation of the developed algorithm which estimates the location of humans in the warehouse environments. The localization is based on the fusion of information from stereo visual odometry and distances to the known absolute poses of detected ground-markers. The ground-markers are part of the warehouse environment since they are used for the localization of robots: markers The dataset contains: ### ./calibration/ -> recordings used for obtaining calibration parameters ./recordings/ -> sequences used for the evaluation ./apriltag_map/ -> recordings of the AprilTags in the environment which are used in obtaining the ground truth pose ./ground-markers_coordinates.txt -> global positions of the ground markers with format "ID x y z roll pitch yaw Label", where x, y, z are given in meters and roll, pitch, yaw, the rotations about the x, y, and z axes are given in radians. The information coded in the DataMatrix codes in the center of the marker is ID*10. ./racks_coordinates.txt -> global positions of the racks with format "ID x y z roll pitch yaw Label", similar to the format of `ground-markers_coordinates.txt` with ID begin the information coded in the AprilTag plus 800. ## Recordings The dataset contains 4 recordings made in the Swisslog testing facility. The environment sized 12x13m^2 enclosed with a safety fence contains a dozen metal racks, which is a very close approximation of the real warehouse environment. In the recordings a human worker carried the camera setup on the lower back of the safety vest, while performing expected movements during the warehouse tasks execution. The recordings are in .bag format and contain the following topics: ### /imu -> IMU measurements /stereo/image_raw -> Stereo pair concatenated in one image, left on top of the right image /stereo/left/cam_info -> Parameters of the left stereo pair /stereo/right/cam_info -> Parameters of the right stereo pair /stickers_camera/camera_info -> Monocular camera parameters /stickers_camera/image_raw -> Monocular camera image /tagslam_gt -> Ground truth pose The images of the testing area and the camera setup are provided in the following images: Testing_facility1 cam_setup ## Sensor setup The camera setup contains PercepIn's stereo visual-inertial module _Ironsides_ and the monocular camera _FLIR Chameleon3_ CM3-U3-50S5M-CS. Both the stereo visual-inertial module and the monocular camera are places on the thick aluminum plate which ensures fixed displacement between them. ### Camera parameters computed with the [Kalibr](https://github.com/ethz-asl/kalibr) calibration package ### Intrinsic parameters #### Left Ironsides camera distortion: [-0.3495738611503549 0.09447840177522801 -0.003548925540635458 -0.0005183361735231511] projection: [434.1452047256915 434.1526731396501 314.41908249476535 231.01828250185793] #### Right Ironsides camera distortion: [-0.35218262885972684 0.09598872982061206 -0.003618221373164676 -2.4773535968930765e-05] projection: [421.7022303158664 421.7236264802341 322.3795386612717 234.81809082346203] #### Stickers camera distortion: [-0.05647082111108878 0.34366151497043845 -0.006004431130824592 -0.002859418860702002] projection: [3461.392252592753 3461.1128018631225 1248.4970984850447 980.240992663445] ### Extrinsic parameters #### Left Ironsides to Right Ironsides [ 0.99998852773938 -0.00280355674816 -0.00388387167208 -0.06496780693111 0.00276345619324 0.99994321673329 -0.01029206582459 -0.00030970532878 0.00391250552375 0.01028121484210 0.99993949263037 -0.00025798762955 0.0 0.0 0.0 1.0] #### Left Ironsides to Stickers: [ 0.99947666762682 -0.01684542381458 -0.02761562177618 -0.03189336419586 -0.00466198282412 0.76978048681416 -0.63829167943526 -0.05019896964669 0.03201026063195 0.63808638429028 0.76929910268868 -0.09491616062339 0.0 0.0 0.0 1.0] ### Calibration parameters provided by manufacturer The calibration parameters for PIRVS Ironsides stereo-inertial sensor are provided in _calib_PerceptIn_V1_2162.json_ . ## Ground truth The ground truth is obtained with the [TagSLAM](https://github.com/berndpfrommer/tagslam) algorithm which recorded AprilTags in the environment. AprilTags are placed around the environment. The ground truth pose is computed in distinct areas due to the discontinued estimate of the TagSLAM algorithm. The recordings of AprilTags in the testing facility that are used for obtaining the Apriltags' map, which is afterward used for computing the ground truth, are in the _./apriltag_map_ folder.