GS
G.M. Smitskamp
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
No-Reference Point Cloud Quality Assessment
Feature Relevance Assessment for No-Reference Quality Assessment of 3D Point Cloud Data
The need to capture environments and objects in 3 dimensions to produce a high quality digital representation is proving to be useful in many applications in the world, where there is an increasing dependence on digital spaces. Point Clouds are a data type to represent 3D objects and scenes. During the processing of the point cloud data, undesired changes to the point cloud can be introduced or information can get lost. Automatic detection and classifying of the quality of a point cloud is needed, to regulate this data type for use in 3D environments, and speed up the processing of point cloud objects in real-time applications.
In this thesis, we look into the problem of no-reference point cloud quality assessment. Full-reference quality metrics compare a distorted point cloud with its original, while no-reference or blind metrics only look at a single point cloud. This task is more challenging than full-reference, as there is less direct information available to work with. We approach the challenge of how the perceptual quality of a point cloud can be estimated when a high-quality reference point cloud is not available, by analyzing if any point cloud properties correlate with the perceptual quality.
We try to find point cloud properties that are effective to use in a model to predict a user given quality score. We select multiple local properties to transform into global descriptors, by taking multiple statistical attributes of the data on all the points to combine into scalars. We analyze the created global descriptors to find linear correlations with the quality score, and found many features that to some measure linearly correlate with some distortion types. With the selected global descriptors, we use Support Vector Regression to find the fitting of the features to the quality score. Varying performances are achieved by training the models on different data subsets, and different fitting kernel functions.
The results show some distortions on unknown objects are properly predictable using fitted weights on this distortion. However, a single defining quality descriptor is not yet found. While the results show potential, our model is not robust and fast enough to perform a reliable assessment of quality in a real-time environment. We are just at the beginning of exploring no-reference quality assessment, and while the current methods are not yet appliable in real-time scenarios, future work can fill many knowledge gaps to reach this goal. ...
In this thesis, we look into the problem of no-reference point cloud quality assessment. Full-reference quality metrics compare a distorted point cloud with its original, while no-reference or blind metrics only look at a single point cloud. This task is more challenging than full-reference, as there is less direct information available to work with. We approach the challenge of how the perceptual quality of a point cloud can be estimated when a high-quality reference point cloud is not available, by analyzing if any point cloud properties correlate with the perceptual quality.
We try to find point cloud properties that are effective to use in a model to predict a user given quality score. We select multiple local properties to transform into global descriptors, by taking multiple statistical attributes of the data on all the points to combine into scalars. We analyze the created global descriptors to find linear correlations with the quality score, and found many features that to some measure linearly correlate with some distortion types. With the selected global descriptors, we use Support Vector Regression to find the fitting of the features to the quality score. Varying performances are achieved by training the models on different data subsets, and different fitting kernel functions.
The results show some distortions on unknown objects are properly predictable using fitted weights on this distortion. However, a single defining quality descriptor is not yet found. While the results show potential, our model is not robust and fast enough to perform a reliable assessment of quality in a real-time environment. We are just at the beginning of exploring no-reference quality assessment, and while the current methods are not yet appliable in real-time scenarios, future work can fill many knowledge gaps to reach this goal. ...
The need to capture environments and objects in 3 dimensions to produce a high quality digital representation is proving to be useful in many applications in the world, where there is an increasing dependence on digital spaces. Point Clouds are a data type to represent 3D objects and scenes. During the processing of the point cloud data, undesired changes to the point cloud can be introduced or information can get lost. Automatic detection and classifying of the quality of a point cloud is needed, to regulate this data type for use in 3D environments, and speed up the processing of point cloud objects in real-time applications.
In this thesis, we look into the problem of no-reference point cloud quality assessment. Full-reference quality metrics compare a distorted point cloud with its original, while no-reference or blind metrics only look at a single point cloud. This task is more challenging than full-reference, as there is less direct information available to work with. We approach the challenge of how the perceptual quality of a point cloud can be estimated when a high-quality reference point cloud is not available, by analyzing if any point cloud properties correlate with the perceptual quality.
We try to find point cloud properties that are effective to use in a model to predict a user given quality score. We select multiple local properties to transform into global descriptors, by taking multiple statistical attributes of the data on all the points to combine into scalars. We analyze the created global descriptors to find linear correlations with the quality score, and found many features that to some measure linearly correlate with some distortion types. With the selected global descriptors, we use Support Vector Regression to find the fitting of the features to the quality score. Varying performances are achieved by training the models on different data subsets, and different fitting kernel functions.
The results show some distortions on unknown objects are properly predictable using fitted weights on this distortion. However, a single defining quality descriptor is not yet found. While the results show potential, our model is not robust and fast enough to perform a reliable assessment of quality in a real-time environment. We are just at the beginning of exploring no-reference quality assessment, and while the current methods are not yet appliable in real-time scenarios, future work can fill many knowledge gaps to reach this goal.
In this thesis, we look into the problem of no-reference point cloud quality assessment. Full-reference quality metrics compare a distorted point cloud with its original, while no-reference or blind metrics only look at a single point cloud. This task is more challenging than full-reference, as there is less direct information available to work with. We approach the challenge of how the perceptual quality of a point cloud can be estimated when a high-quality reference point cloud is not available, by analyzing if any point cloud properties correlate with the perceptual quality.
We try to find point cloud properties that are effective to use in a model to predict a user given quality score. We select multiple local properties to transform into global descriptors, by taking multiple statistical attributes of the data on all the points to combine into scalars. We analyze the created global descriptors to find linear correlations with the quality score, and found many features that to some measure linearly correlate with some distortion types. With the selected global descriptors, we use Support Vector Regression to find the fitting of the features to the quality score. Varying performances are achieved by training the models on different data subsets, and different fitting kernel functions.
The results show some distortions on unknown objects are properly predictable using fitted weights on this distortion. However, a single defining quality descriptor is not yet found. While the results show potential, our model is not robust and fast enough to perform a reliable assessment of quality in a real-time environment. We are just at the beginning of exploring no-reference quality assessment, and while the current methods are not yet appliable in real-time scenarios, future work can fill many knowledge gaps to reach this goal.
Designing an escape room sensory system
S.C.I.L.E.R.: sensory communication inside live escape rooms
Bachelor thesis
(2020)
-
Issa Hanou, Gwennan Smitskamp, Marijn de Schipper, Jan-Willem Manenschijn, Taico Aerts, Otto Visser, Elvin Isufi
Raccoon Serious Games develops different kinds of gaming experiences, including escape rooms. In an escape room, a group of players, usually between 2 and 20 people, are locked in a room, where they have to find clues and solve puzzles to escape. When such a room is played, there is always an operator, monitoring the progress of the players and keeping an eye on their safety. Modern escape rooms are quite technologically advanced, where all components of the room interact with each other. To run these games, Raccoon Serious Games needs a system which should manage all technical aspects within the room and provide a way for the operator to keep track of the players. Furthermore, the system must be flexible enough to handle many different escape rooms, which are hardcoded in configuration files. To meet these needs of Raccoon Serious Games, a team of three developers has developed a new system, called S.C.I.L.E.R.. In ten weeks, they have created a system from scratch. First, they researched technologies and requirements that would be necessary for the system and afterwards implemented the system based on their findings. S.C.I.L.E.R. allows an operator to monitor a complete escape room. The system connects a user interface to all the devices in the room, which are controlled by the user as well as the configuration of the escape room. This configuration is generated from a JSON configuration file, containing all information for the escape room. The system allows the operator to send hints to the players, control the time and manage their progress through the status of devices in the room and the puzzles they have to solve. It also contains the feeds of cameras in the room to actually see the players. Furthermore, it provides the user with a way to check a configuration file and put it to use. The system will be used by Raccoon Serious Games in the near future for the escape rooms that they will be hosting.
...
Raccoon Serious Games develops different kinds of gaming experiences, including escape rooms. In an escape room, a group of players, usually between 2 and 20 people, are locked in a room, where they have to find clues and solve puzzles to escape. When such a room is played, there is always an operator, monitoring the progress of the players and keeping an eye on their safety. Modern escape rooms are quite technologically advanced, where all components of the room interact with each other. To run these games, Raccoon Serious Games needs a system which should manage all technical aspects within the room and provide a way for the operator to keep track of the players. Furthermore, the system must be flexible enough to handle many different escape rooms, which are hardcoded in configuration files. To meet these needs of Raccoon Serious Games, a team of three developers has developed a new system, called S.C.I.L.E.R.. In ten weeks, they have created a system from scratch. First, they researched technologies and requirements that would be necessary for the system and afterwards implemented the system based on their findings. S.C.I.L.E.R. allows an operator to monitor a complete escape room. The system connects a user interface to all the devices in the room, which are controlled by the user as well as the configuration of the escape room. This configuration is generated from a JSON configuration file, containing all information for the escape room. The system allows the operator to send hints to the players, control the time and manage their progress through the status of devices in the room and the puzzles they have to solve. It also contains the feeds of cameras in the room to actually see the players. Furthermore, it provides the user with a way to check a configuration file and put it to use. The system will be used by Raccoon Serious Games in the near future for the escape rooms that they will be hosting.