The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems.
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems
The aim of this study is to propose a probabilistic contour determination method on indoor map scan data. Traditional probabilistic contour detection algorithms operate as a kind of decision-making tool by processing the segment between two randomly selected samples in a full dataset. Pure geometric approaches, on the other hand, focus on identical features (corners, landmarks etc.) with a series of labeling operations based on Euclidean distance. Both approaches are commonly used in the literature to recognize a predefined geometric pattern. At the core of this study, a novel segmentation and labelling strategy is performed in a manner that geometrical and probabilistic principles are applied sequentially. In the first stage, the total data segmented with the line splitting strategy is transformed into subsets from which random samples will be selected in the following steps. Samples selected from the new (constrained) subsets provide higher accuracy segmentation. The data set processed in the study are indoor distance measurements obtained from the 2D Light Detection and Ranging (LIDAR) sensor. The detected line segments are one of the most basic features used for indoor positioning and the results of the study can be adapted to indoor positioning systems.