3D Object Recognition using Time of Flight Camera with Embedded GPU on Mobile Robots

Kelényi, Benjamin; Molnár, Szilárd; Tamás, Levente

doi:10.5220/0010972200003124

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our work we propose an efficient end-to-end deep learning approach for the MPI reduction on planar surfaces. We focus on these larger segments in a ToF image as the extraction of these planes stands on the bases for a number of preprocessing tasks in robotics perception applications [3], [6], [11], [19]. Our solution makes use of a multistep planar estimation with classical sample consensus-based approach, which is used for the training of a feature-pyramid network (FPN) based architecture.…”

Section: Introductionmentioning

confidence: 99%

MPI Planar Correction of Pulse Based ToF Cameras

Pop

Tamás

2022

2022 IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR)

View full text Add to dashboard Cite

Time-of-Flight (ToF) cameras are becoming popular in a wide span of areas ranging from consumer-grade electronic devices to safety-critical industrial robots. This is mainly due to their high frame rate, relative good precision and the lowered costs. Although ToF cameras are in continuous development, especially pulse-based variants, they still face different problems, including spurious noise over the points or multipath inference (MPI). The latter can cause deformed surfaces to manifest themselves on curved surfaces instead of planar ones, making standard spatial data preprocessing, such as plane extraction, difficult. In this paper, we focus on the MPI reduction problem using Feature Pyramid Networks (FPN) which allow the mitigation of this type of artifact for pulse-based ToF cameras. With our end-to-end network, we managed to attenuate the MPI effect on planar surfaces using a learning-based method on real ToF data. Both the custom dataset used for our model training as well as the code is available on the author's Github homepage.

show abstract