Gd
G.P. de Jong
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
Automatically deriving 3D representations of buildings is a challenging problem which is at the base of a wide range of applications. The DE-RISC project aims to generate a 3D model of the entire city of Rotterdam in The Netherlands, enabling many of these applications. Generating a 3D model of a building can be done in a variety of ways, of which only few are robust, scalable and generalizable. Recognition and reconstruction of architectural floor plans is such a scalable method long researched in literature.
Although these methods generalized poorly initially, recent breakthroughs in computer vision have allowed for the application of deep learning based approaches. Recent floor plan processing methods have shown promising results on single-unit floor plans. Single-unit floor plans are floor plans of single apartments of relatively low complexity. In contrast, multi-unit floor plans describe entire buildings, and are thus significantly larger and of higher complexity. Applying single-unit floor plan processing methods to multi-unit floor plans is not trivial, and results in insufficient accuracy. These methods can therefore not be applied to an entire city, limiting the scalability and generalizability.
This thesis proposes a novel multi-scale floor plan recognition and reconstruction method designed to transform floor plans of arbitrary size into their 3D representations. As no multi-unit floor plan datasets exists, a novel floor plan dataset MURF is presented based on multi-unit floor plans from buildings in Rotterdam. MURF considers seven boundary and opening semantic classes, each with distinct physical properties. The recognition part of the method relies on an FCN employing multi-scale skip-connections, an attention mechanism, and a multi-task training objective to reinforce the learning of multi-scale features. The reconstruction part refines predictions from the recognition step by applying post-processing, vectorization, and visualization in Blender.
The proposed method is compared to floor plan processing models from literature and general stateof-the-art segmentation models by a quantitative and qualitative evaluation. Experimental results show that the proposed method is significantly outperforms existing floor plan processing methods, and performs best out of general segmentation models. A case study on the EMC in Rotterdam demonstrates the generalizability of the proposed method. ...
Although these methods generalized poorly initially, recent breakthroughs in computer vision have allowed for the application of deep learning based approaches. Recent floor plan processing methods have shown promising results on single-unit floor plans. Single-unit floor plans are floor plans of single apartments of relatively low complexity. In contrast, multi-unit floor plans describe entire buildings, and are thus significantly larger and of higher complexity. Applying single-unit floor plan processing methods to multi-unit floor plans is not trivial, and results in insufficient accuracy. These methods can therefore not be applied to an entire city, limiting the scalability and generalizability.
This thesis proposes a novel multi-scale floor plan recognition and reconstruction method designed to transform floor plans of arbitrary size into their 3D representations. As no multi-unit floor plan datasets exists, a novel floor plan dataset MURF is presented based on multi-unit floor plans from buildings in Rotterdam. MURF considers seven boundary and opening semantic classes, each with distinct physical properties. The recognition part of the method relies on an FCN employing multi-scale skip-connections, an attention mechanism, and a multi-task training objective to reinforce the learning of multi-scale features. The reconstruction part refines predictions from the recognition step by applying post-processing, vectorization, and visualization in Blender.
The proposed method is compared to floor plan processing models from literature and general stateof-the-art segmentation models by a quantitative and qualitative evaluation. Experimental results show that the proposed method is significantly outperforms existing floor plan processing methods, and performs best out of general segmentation models. A case study on the EMC in Rotterdam demonstrates the generalizability of the proposed method. ...
Automatically deriving 3D representations of buildings is a challenging problem which is at the base of a wide range of applications. The DE-RISC project aims to generate a 3D model of the entire city of Rotterdam in The Netherlands, enabling many of these applications. Generating a 3D model of a building can be done in a variety of ways, of which only few are robust, scalable and generalizable. Recognition and reconstruction of architectural floor plans is such a scalable method long researched in literature.
Although these methods generalized poorly initially, recent breakthroughs in computer vision have allowed for the application of deep learning based approaches. Recent floor plan processing methods have shown promising results on single-unit floor plans. Single-unit floor plans are floor plans of single apartments of relatively low complexity. In contrast, multi-unit floor plans describe entire buildings, and are thus significantly larger and of higher complexity. Applying single-unit floor plan processing methods to multi-unit floor plans is not trivial, and results in insufficient accuracy. These methods can therefore not be applied to an entire city, limiting the scalability and generalizability.
This thesis proposes a novel multi-scale floor plan recognition and reconstruction method designed to transform floor plans of arbitrary size into their 3D representations. As no multi-unit floor plan datasets exists, a novel floor plan dataset MURF is presented based on multi-unit floor plans from buildings in Rotterdam. MURF considers seven boundary and opening semantic classes, each with distinct physical properties. The recognition part of the method relies on an FCN employing multi-scale skip-connections, an attention mechanism, and a multi-task training objective to reinforce the learning of multi-scale features. The reconstruction part refines predictions from the recognition step by applying post-processing, vectorization, and visualization in Blender.
The proposed method is compared to floor plan processing models from literature and general stateof-the-art segmentation models by a quantitative and qualitative evaluation. Experimental results show that the proposed method is significantly outperforms existing floor plan processing methods, and performs best out of general segmentation models. A case study on the EMC in Rotterdam demonstrates the generalizability of the proposed method.
Although these methods generalized poorly initially, recent breakthroughs in computer vision have allowed for the application of deep learning based approaches. Recent floor plan processing methods have shown promising results on single-unit floor plans. Single-unit floor plans are floor plans of single apartments of relatively low complexity. In contrast, multi-unit floor plans describe entire buildings, and are thus significantly larger and of higher complexity. Applying single-unit floor plan processing methods to multi-unit floor plans is not trivial, and results in insufficient accuracy. These methods can therefore not be applied to an entire city, limiting the scalability and generalizability.
This thesis proposes a novel multi-scale floor plan recognition and reconstruction method designed to transform floor plans of arbitrary size into their 3D representations. As no multi-unit floor plan datasets exists, a novel floor plan dataset MURF is presented based on multi-unit floor plans from buildings in Rotterdam. MURF considers seven boundary and opening semantic classes, each with distinct physical properties. The recognition part of the method relies on an FCN employing multi-scale skip-connections, an attention mechanism, and a multi-task training objective to reinforce the learning of multi-scale features. The reconstruction part refines predictions from the recognition step by applying post-processing, vectorization, and visualization in Blender.
The proposed method is compared to floor plan processing models from literature and general stateof-the-art segmentation models by a quantitative and qualitative evaluation. Experimental results show that the proposed method is significantly outperforms existing floor plan processing methods, and performs best out of general segmentation models. A case study on the EMC in Rotterdam demonstrates the generalizability of the proposed method.
The feeling of belongingness, to be a member of a group, is rooted in human evolutionary history. Cooperative behaviour within such groups has since been an important research topic. The evolution of cooperation in the iterated prisoner's dilemma (IPD) has been shown to be an effective tool of simulating and analysing this behaviour. However, it is unclear what the effects of group-based agents on IPD strategies in evolving spatial environments are. This paper investigates how this cooperation emerges by proposing an evolving spatial model that applies a genetic algorithm to its agents, extended to work with three distinct group types. This genetic algorithm makes use of four genetic operators: cloning, crossover, mutation and inversion. The groups considered are kin, clans and their combination. Cooperation is measured by examining (1) populations levels divided into nice, balanced and nasty groups, and (2) average cooperation levels of both strategies and games played per iteration. Experiments for all group types with two reproduction preferences were conducted. Three distinct conclusions can be drawn from the results. First, strategies evolved through domestic reproduction exhibit more cooperation for in-group opponents and more defection for out-group opponents. Second, strategies evolved through wealthy reproduction exhibit the same increase and decrease of cooperation as domestic reproduction, but to a smaller degree. Third, an evolving spatial environment with group-based agents develops subgroups, defined by similar strategies and restricting group-wide cooperation. Thus, agents with cooperative domestic strategies and defective foreign strategies win, and there is a positive correlation between group size and restriction of group-wide cooperation.
...
The feeling of belongingness, to be a member of a group, is rooted in human evolutionary history. Cooperative behaviour within such groups has since been an important research topic. The evolution of cooperation in the iterated prisoner's dilemma (IPD) has been shown to be an effective tool of simulating and analysing this behaviour. However, it is unclear what the effects of group-based agents on IPD strategies in evolving spatial environments are. This paper investigates how this cooperation emerges by proposing an evolving spatial model that applies a genetic algorithm to its agents, extended to work with three distinct group types. This genetic algorithm makes use of four genetic operators: cloning, crossover, mutation and inversion. The groups considered are kin, clans and their combination. Cooperation is measured by examining (1) populations levels divided into nice, balanced and nasty groups, and (2) average cooperation levels of both strategies and games played per iteration. Experiments for all group types with two reproduction preferences were conducted. Three distinct conclusions can be drawn from the results. First, strategies evolved through domestic reproduction exhibit more cooperation for in-group opponents and more defection for out-group opponents. Second, strategies evolved through wealthy reproduction exhibit the same increase and decrease of cooperation as domestic reproduction, but to a smaller degree. Third, an evolving spatial environment with group-based agents develops subgroups, defined by similar strategies and restricting group-wide cooperation. Thus, agents with cooperative domestic strategies and defective foreign strategies win, and there is a positive correlation between group size and restriction of group-wide cooperation.