Viktor Remeli | Budapest University of Technology and Economics (original) (raw)
My primary focus is the verification of deep learning algorithms applied in autonomous vehicles. Other areas of work: developing new DNN-based raw sensor fusion architectures; solving transportation-related combinatorial optimization problems.
Supervisors: András Rövid and Zsolt Szalay
less
Uploads
Papers by Viktor Remeli
IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI 2019), 2019
The paper focuses on the problem of raw data fusion in neural networks based 3D object detection ... more The paper focuses on the problem of raw data
fusion in neural networks based 3D object detection architectures.
Here we consider the case of autonomous driving with data
from camera and LiDAR sensors. Understanding the vehicle
surroundings is a crucial task in autonomous driving since any
subsequent action taken is strongly dependent on it. In this
paper we present an alternative method of fusing camera image
information with LiDAR poinclouds at a close to raw level of
abstraction. Our results suggest that our approach improves
the average precision of 3D bounding box detection of cyclists
(and possibly other objects) in sparse point clouds compared to
the baseline architecture without low-level fusion. The proposed
approach has been evaluated on the KITTI dataset containing
driving scenes with corresponding camera and LiDAR data. The
long-term goal of our research is to develop a neural network
architecture for environment perception that fuses multi-sensor
data at the earliest stages possible, thus leveraging the full benefits
of possible inter-sensor synergies.
IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI 2019), 2019
The paper focuses on the problem of raw data fusion in neural networks based 3D object detection ... more The paper focuses on the problem of raw data
fusion in neural networks based 3D object detection architectures.
Here we consider the case of autonomous driving with data
from camera and LiDAR sensors. Understanding the vehicle
surroundings is a crucial task in autonomous driving since any
subsequent action taken is strongly dependent on it. In this
paper we present an alternative method of fusing camera image
information with LiDAR poinclouds at a close to raw level of
abstraction. Our results suggest that our approach improves
the average precision of 3D bounding box detection of cyclists
(and possibly other objects) in sparse point clouds compared to
the baseline architecture without low-level fusion. The proposed
approach has been evaluated on the KITTI dataset containing
driving scenes with corresponding camera and LiDAR data. The
long-term goal of our research is to develop a neural network
architecture for environment perception that fuses multi-sensor
data at the earliest stages possible, thus leveraging the full benefits
of possible inter-sensor synergies.