CV
C.V.M.M. Vorage
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
The training process of machine learning models for self-driving applications suffers from bottlenecks during loading and processing of LiDAR point clouds with large storage complexity.
Many studies aim to remedy this problem from an implementation perspective by developing efficient data loading and processing pipelines.
This study, on the other hand, explores an alternative approach by augmenting data representations to achieve lower storage complexity known as point cloud compression.
A broad analysis is presented on novel point cloud compression codecs using tensor decomposition methods.
Several point cloud representations and tensor decomposition methods are considered over a range of hyperparameter choices and compression values.
In order to assess the performance of the presented codecs: the compression rate, quality of the reconstruction, and time complexity is compared to the octree-based baseline model: TMC13.
Compared to the baseline model, the performance of the presented tensor decomposition-based codecs falls short. One of the presented codecs does notably outperform the others. This codec uses synthetic tensorization followed by sorting using z-location and decomposition using the TT-SVD algorithm.
Sorting by z-value isolates the ground plane, which is a dominant low-rank feature, which can effectively be decomposed using the TT-SVD algorithm yielding adequate results.
Several limitations of the presented tensor decomposition-based codecs are: the omission of bitwise compression on the factor matrices, and the trade-off between bitwise precision and truncation due to tensor decomposition.
Future work could improve in these areas along with considering the use of different heuristics and optimizing the tensor network topology. ...
Many studies aim to remedy this problem from an implementation perspective by developing efficient data loading and processing pipelines.
This study, on the other hand, explores an alternative approach by augmenting data representations to achieve lower storage complexity known as point cloud compression.
A broad analysis is presented on novel point cloud compression codecs using tensor decomposition methods.
Several point cloud representations and tensor decomposition methods are considered over a range of hyperparameter choices and compression values.
In order to assess the performance of the presented codecs: the compression rate, quality of the reconstruction, and time complexity is compared to the octree-based baseline model: TMC13.
Compared to the baseline model, the performance of the presented tensor decomposition-based codecs falls short. One of the presented codecs does notably outperform the others. This codec uses synthetic tensorization followed by sorting using z-location and decomposition using the TT-SVD algorithm.
Sorting by z-value isolates the ground plane, which is a dominant low-rank feature, which can effectively be decomposed using the TT-SVD algorithm yielding adequate results.
Several limitations of the presented tensor decomposition-based codecs are: the omission of bitwise compression on the factor matrices, and the trade-off between bitwise precision and truncation due to tensor decomposition.
Future work could improve in these areas along with considering the use of different heuristics and optimizing the tensor network topology. ...
The training process of machine learning models for self-driving applications suffers from bottlenecks during loading and processing of LiDAR point clouds with large storage complexity.
Many studies aim to remedy this problem from an implementation perspective by developing efficient data loading and processing pipelines.
This study, on the other hand, explores an alternative approach by augmenting data representations to achieve lower storage complexity known as point cloud compression.
A broad analysis is presented on novel point cloud compression codecs using tensor decomposition methods.
Several point cloud representations and tensor decomposition methods are considered over a range of hyperparameter choices and compression values.
In order to assess the performance of the presented codecs: the compression rate, quality of the reconstruction, and time complexity is compared to the octree-based baseline model: TMC13.
Compared to the baseline model, the performance of the presented tensor decomposition-based codecs falls short. One of the presented codecs does notably outperform the others. This codec uses synthetic tensorization followed by sorting using z-location and decomposition using the TT-SVD algorithm.
Sorting by z-value isolates the ground plane, which is a dominant low-rank feature, which can effectively be decomposed using the TT-SVD algorithm yielding adequate results.
Several limitations of the presented tensor decomposition-based codecs are: the omission of bitwise compression on the factor matrices, and the trade-off between bitwise precision and truncation due to tensor decomposition.
Future work could improve in these areas along with considering the use of different heuristics and optimizing the tensor network topology.
Many studies aim to remedy this problem from an implementation perspective by developing efficient data loading and processing pipelines.
This study, on the other hand, explores an alternative approach by augmenting data representations to achieve lower storage complexity known as point cloud compression.
A broad analysis is presented on novel point cloud compression codecs using tensor decomposition methods.
Several point cloud representations and tensor decomposition methods are considered over a range of hyperparameter choices and compression values.
In order to assess the performance of the presented codecs: the compression rate, quality of the reconstruction, and time complexity is compared to the octree-based baseline model: TMC13.
Compared to the baseline model, the performance of the presented tensor decomposition-based codecs falls short. One of the presented codecs does notably outperform the others. This codec uses synthetic tensorization followed by sorting using z-location and decomposition using the TT-SVD algorithm.
Sorting by z-value isolates the ground plane, which is a dominant low-rank feature, which can effectively be decomposed using the TT-SVD algorithm yielding adequate results.
Several limitations of the presented tensor decomposition-based codecs are: the omission of bitwise compression on the factor matrices, and the trade-off between bitwise precision and truncation due to tensor decomposition.
Future work could improve in these areas along with considering the use of different heuristics and optimizing the tensor network topology.
Bachelor thesis
(2021)
-
G.A.E. Douma, T.Y. Lim, G.A.M. van Rijen, C.V.M.M. Vorage, N. van Wering, C. Hutters
This research paper describes the design and implementation of a Model Predictive Controller, using economic engineering principles, on a model of the US economy. The purpose of the Model Predictive Controller is to mimic the US
government policy by maximizing the Net Domestic Product. The Model Predictive Controller is integrated with a bond graph model which is modeled based on macroeconomic principles and used to simulate the US economy. In all cases, the Model Predictive Controller was able to successfully stabilize the US economy, while maximizing the Net Domestic Product e.g. the economic output of the economy. The model described in this paper provides a promising new way of generating more accurate prospects of future market movements. ...
government policy by maximizing the Net Domestic Product. The Model Predictive Controller is integrated with a bond graph model which is modeled based on macroeconomic principles and used to simulate the US economy. In all cases, the Model Predictive Controller was able to successfully stabilize the US economy, while maximizing the Net Domestic Product e.g. the economic output of the economy. The model described in this paper provides a promising new way of generating more accurate prospects of future market movements. ...
This research paper describes the design and implementation of a Model Predictive Controller, using economic engineering principles, on a model of the US economy. The purpose of the Model Predictive Controller is to mimic the US
government policy by maximizing the Net Domestic Product. The Model Predictive Controller is integrated with a bond graph model which is modeled based on macroeconomic principles and used to simulate the US economy. In all cases, the Model Predictive Controller was able to successfully stabilize the US economy, while maximizing the Net Domestic Product e.g. the economic output of the economy. The model described in this paper provides a promising new way of generating more accurate prospects of future market movements.
government policy by maximizing the Net Domestic Product. The Model Predictive Controller is integrated with a bond graph model which is modeled based on macroeconomic principles and used to simulate the US economy. In all cases, the Model Predictive Controller was able to successfully stabilize the US economy, while maximizing the Net Domestic Product e.g. the economic output of the economy. The model described in this paper provides a promising new way of generating more accurate prospects of future market movements.