Outdoor_DEEC_withRamp_Segmentation

<p>Shown here is a bag with 148 seconds of recording outside the DEEC of the University of Coimbra (UC), where the robot has the opportunity to climb a small ramp. The bag contains data captured by an RGB-D camera (D435i), a stereo camera (Mynt Eye S1030), wheel odometry (given by the Pioner P3-DX), and a 2D LiDAR (Hokuyo URG-04L). The IMU data from both cameras was also recorded. Alongside this bag is another containing the semantic segmentation generated by the PSPNet network, from the Cityscapes dataset. The alpha has a opacity of 255.</p> <p>The transformations are defined as follows (approximately):</p> <p>&nbsp; &nbsp; RGB-D camera: 0.18 0.005 0.71 0 -0.0872 0 base_link realsense_link<br>&nbsp; &nbsp; Mynt Eye camera: 0.205 0.0 0.63 -1.57 0 -1.72 base_link mynteye_link<br><br>It should be noted that the laser transformations have already been recorded on the bag. The segmented images are in BGR format.&nbsp;<br>The ground truth (GT) was generated using RTAB-Map, combining odometry data from various sensors in a fusion module. While it is considered highly accurate, it may still contain some associated errors.</p>