D3GATTEN: Dense 3D geometric features extraction and pose estimation using self-attention

B Kelenyi, L Tamas - IEEE Access, 2023 - ieeexplore.ieee.org
Point-cloud processing for extracting geometric features is difficult due to the highly non-
linear rotation variance and measurement noise corrupting the data. To address these …

Rotation invariant graph neural network for 3d point clouds

A Pop, V Domșa, L Tamas - Remote Sensing, 2023 - mdpi.com
In this paper we propose a novel rotation normalization technique for point cloud processing
using an oriented bounding box. We use this method to create a point cloud annotation tool …

Next best view estimation for volumetric information gain

A Pop, L Tamas - IFAC-PapersOnLine, 2022 - Elsevier
In this work we propose a novel next best view (NBV) generation algorithm for volumetric
information maximization. The primary data source is a Time-of-Flight (ToF) camera and the …

Embedded real-time people detection and tracking with time-of-flight camera

L Tamas, A Cozma - Real-Time Image Processing and Deep …, 2021 - spiedigitallibrary.org
People recognition is a relevant subset of the generic image based recognition task with
many possible application areas such as security, surveillance, human-robot interaction or …

Lessons learned from lightweight CNN based object recognition for mobile robots

AO Fulop, L Tamas - 2018 IEEE International Conference on …, 2018 - ieeexplore.ieee.org
The focus of this paper is on the comparison of multiple neural network frameworks and the
their usage in 2D/3D robot perception applications. Numerous frameworks exists for this task …

Evaluation of PCL's Descriptors for 3D Object Recognition in Cluttered Scene

N Zrira, FZ Ouadiay, M Hannat, EH Bouyakhf… - Proceedings of the 2nd …, 2017 - dl.acm.org
3D point cloud recognition is a challenging problem that is growing fast, especially with the
development of acquisition cameras such as the Kinect that allows the generation of a lot of …

Recognizing behaviors patterns in a micro robot soccer game

D Barrios-Aranibar, PJ Alsina - Fifth International Conference …, 2005 - ieeexplore.ieee.org
Recognizing behaviors is an important step for learning by imitation. Learning by imitation,
in the other hand, is considered as a method to acquire complex behaviors and as a way to …

[PDF][PDF] 3D Object Recognition using Time of Flight Camera with Embedded GPU on Mobile Robots.

B Kelényi, S Molnár, L Tamás - VISIGRAPP (4: VISAPP), 2022 - rocon.utcluj.ro
The main goal of this work is to analyze the most suitable methods for segmenting and
classifying 3D point clouds using embedded GPU for mobile robots. We review the current …

Sorting Objects from a Conveyor Belt Using POMDPs with Multiple-Object Observations and Information-Gain Rewards

AD Mezei, L Tamás, L Buşoniu - Sensors, 2020 - mdpi.com
We consider a robot that must sort objects transported by a conveyor belt into different
classes. Multiple observations must be performed before taking a decision on the class of …

MPI Planar Correction of Pulse Based ToF Cameras

ML Pop, L Tamas - 2022 IEEE International Conference on …, 2022 - ieeexplore.ieee.org
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 …