TY  - CHAP
A1  - Triputen, Sergey
A1  - Gopal, Atmaraaj
A1  - Weber, Thomas
A1  - Höfert, Christian
A1  - Rätsch, Matthias
A1  - Schreve, Kristiaan
T1  - Methodology to analyze the accuracy of 3D objects reconstructed with collaborative robot based monocular LSD-SLAM
T2  - Advancing the frontier of intelligent autonomous systems : proceedings 2018 International Conference on Intelligent Autonomous Systems (ICoIAS 2018), March 1-3, 2018, Singapore
N2  - SLAM systems are mainly applied for robot navigation while research on feasibility for motion planning with SLAM for tasks like bin-picking, is scarce. Accurate 3D reconstruction of objects and environments is important for planning motion and computing optimal gripper pose to grasp objects. In this work, we propose the methods to analyze the accuracy of a 3D environment reconstructed using a LSD-SLAM system with a monocular camera mounted onto the gripper of a collaborative robot. We discuss and propose a solution to the pose space conversion problem. Finally, we present several criteria to analyze the 3D reconstruction accuracy. These could be used as guidelines to improve the accuracy of 3D reconstructions with monocular LSD-SLAM and other SLAM based solutions.
KW  - 3D reconstruction
KW  - accuracy
KW  - bin-picking
KW  - collaborative robot
KW  - depth estimation
KW  - monocular camera
KW  - LSD-SLAM
KW  - SLAM
KW  - space conversion
Y1  - 2018
SN  - 978-1-5386-6331-8
U6  - http://dx.doi.org/10.1109/ICoIAS.2018.8494109
SP  - 185
EP  - 190
PB  - IEEE
CY  - Piscataway, NJ
ER  - 
TY  - CHAP
A1  - Weber, Thomas
A1  - Triputen, Sergey
A1  - Gopal, Atmaraaj
A1  - Eißler, Steffen
A1  - Höfert, Christian
A1  - Schreve, Kristiaan
A1  - Rätsch, Matthias
ED  - Chalup, Stephan
T1  - Efficient and robust 3D object reconstruction based on monocular SLAM and CNN semantic segmentation
T2  - RoboCup 2019: Robot World Cup XXIII. - (Lecture notes in artificial intelligence ; 11531)
N2  - Various applications implement slam technology, especially in the field of robot navigation. We show the advantage of slam technology for independent 3d object reconstruction. To receive a point cloud of every object of interest void of its environment, we leverage deep learning. We utilize recent cnn deep learning research for accurate semantic segmentation of objects. In this work, we propose two fusion methods for cnn-based semantic segmentation and slam for the 3d reconstruction of objects of interest in order to obtain a more robustness and efficiency. As a major novelty, we introduce a cnn-based masking to focus slam only on feature points belonging to every single object. Noisy, complex or even non-rigid features in the background are filtered out, improving the estimation of the camera pose and the 3d point cloud of each object. Our experiments are constrained to the reconstruction of industrial objects. We present an analysis of the accuracy and performance of each method and compare the two methods describing their pros and cons.
KW  - 3d reconstruction
KW  - slam
KW  - lsd-slam
KW  - monocular camera
KW  - cnn
KW  - semantic segmentation
KW  - bin-picking
KW  - collaborative robot
KW  - depth estimation
Y1  - 2019
U6  - http://dx.doi.org/10.1007/978-3-030-35699-6_27
SP  - 351
EP  - 363
PB  - Springer
CY  - Cham
ER  -