The video is about a robust particle filter based method, which estimates and tracks the posture of a hydraulic crane by using only low-cost equipment, namely, a 2D laser scanner, two short magnetically attached metal tubes as targets, and an angle sensor. In contrast to the previous works employing laser scanners, we do not use the full shape of the crane to estimate the crane posture, but instead, we use only two small targets in the field of view of the laser scanner. Thus, a large share of the range data is applicable to other purposes, e.g., to map the surrounding environment. We test the proposed methods in a challenging forest environment and we show that the particle filter is able to estimate the posture of the hydraulic crane efficiently and reliably in the presence of occlusion and obstructions in the laser scanner data.
The video contains 5 tests. Here is the outline of the video:
0:22 Test A
8:57 Test A results
9:01 Test B
11:42 Test B results
11:47 Test C
16:16 Test C results
16:21 Test D
40:04 Test D results
40:08 Test E
43:34 Test E results
The work is done with Aalto University and Finnish Geospatial Research Institute by Heikki Hyyti, Ville V. Lehtola and Arto Visala.
Strategic Research Council at the Academy of Finland is acknowledged for financial support of project "Competence-Based Growth Through Integrated Disruptive Technologies of 3D Digitalization, Robotics, Geospatial Information and Image Processing/Computing – Point Cloud Ecosystem" (project decision number 293389). See more details at [ Ссылка ]
