| 1. |
- Andrée, Martin, et al.
(author)
-
BIM and 3D property visualisation
- 2018
-
In: FIG Congress 2018.
-
Conference paper (other academic/artistic)abstract
- The concept of 3D property has only existed a short period of time in Sweden, being introduced in 2004 and expanded in 2009 by the addition of condominium (apartment) ownership. It is therefore a rather new form of land management, and the demand for 3D property formation has not been as high as initially expected. There is however an increased interest in 3D property and ownership apartments today, also as being part of the nation’s geospatial infrastructure together with related 3D information for e.g. buildings, utility networks and other features. An effective management of 3D property is depending on, among other things, visualization, representation and storage of 3D real property data, such as legal boundaries and real property rights. There are at present a number of ongoing 3D development and research projects focusing on visualization and standardization of 3D cadastral boundaries. They are part of the national "Smart Built Environment" development and research program, which includes the use of BIM in the (future) 3D property formation process with focus on visualization of 3D real property and condominiums, and specification of requirements and evaluation of 3D digital real property information created and managed in the processes.This paper presents the preliminary results of the working group on visualization of 3D boundaries in the project "Smart planning, construction and management processes throughout the life cycle". The aim is to test the results produced in the project "Information for planning, real property formation and building permission", working group "BIM for 3D property formation." The purpose of this working group is to set the requirements for and evaluate the test bed for 3D property information. The focus is on visualization of 3D property and ownership apartments. The proposed model for digitization and visualization of 3D property formation will be tested in a test bed environment. A pilot case from the Stockholm area is then used in the test bed to see how it could work in practice.The expected outcome is recommendations for the exchange of documentation and other digital information in 3D processes, the visualization of legal boundaries for stakeholders, registration of legal 3D objects in the Swedish national real property register and how to communicate 3D models to right holders/stakeholders for 3D property and condominiums and the property market, as well as suggestions for a homogeneous, effective and digital flow of 3D information to be used by actors and other stakeholders in the property formation, planning and building processes.
|
|
| 2. |
- Andrée, Martin, et al.
(author)
-
Slutrapport för projektet Smart planering för byggande : Delprojekt 3 - BIM som informationsstöd för 3D fastighetsbildning
- 2018
-
Reports (other academic/artistic)abstract
- Samhällsbyggnadsprocessen behöver utvecklas och bli smartare, öppnare och mer effektiv för ett ökat bostadsbyggande. En digitalisering av samhällsbyggnadsprocessen kan ge ett effektivare samarbete mellan kommun, fastighetsägare, byggherrar, medborgare, näringsliv och myndigheter.Vid bildande av tredimensionellt avgränsade fastigheter eller fastighetsutrymmen (3D-fastigheter) behöver gränsernas läge redovisas både verbalt och i kartor och ritningar, detsamma gäller berörda rättigheter. Det är idag ofta svårt att korrekt redovisa en 3D-volym med enbart dagens pappersritningar och även svårt att läsa en registerkarta i 2D med fastigheter och rättigheter beslutade i 3D. Beslutsunderlagen i fastighetsbildnings-processen behöver bli mer enhetliga och entydiga samt fastighetsinformationen behöver bli återanvändningsbar i hela samhällsbyggnadsprocessen.I detta projekt har vi studerat informationsbehovet i de olika tidpunkterna under fastighetsbildningsprocessen för 3D-fastigheter med fokus på vem som är ansvarig för att tillhandahålla informationsunderlag för att identifiera krav på utformning av 3D-modeller (t.ex BIM) och 3D-stöd för fastighetsbildning.Internationellt finns det ett stort intresse och många frågeställningar gällande samspelet mellan BIM och Fastighetsinformation; det är däremot ganska få fall som har identifierats där man har arbetat praktiskt med BIM i relation till redovisning av 3D-fastigheter.Projektethar även tittat på behov av visualisering och tillhandahållande av fastighetsinformation i 3D, hur informationen bör utformas för att kunna tolkas korrekt samt nyttjas vidare av andra aktörer i samhällsbyggnadsprocessen.Slutsatsen i projektetär att en framtida arbetsmodell där man i samband med myndighetsutövningen för fastighetsbildning samverkar med stöd av BIM och geografisk information i ärendehandläggningen kan ge stora effekter på både myndighetens effektivitet och i ärendeutövningen och för förståelsen av fastighetbildningsbeslutet hos samtliga intressenter i processen. För att det arbete som genomförts i denna utredning skall få genomslag i den dagliga verksamheten rekommenderar vibland annatatt de statliga och kommunala lantmäterimyndigheterna arbetar vidare med att utveckla arbetsprocessen och rekommendationerna för 3D-fastighetsbildning baserat på resultatet från detta projekt och redan i dagens modell efterfrågar att man i handläggningsprocessen kan arbeta BIM-baserat även om kommande beslutshandlingar under en övergångsperiod fortfarande kommer att vara baserade på ritningsbilagor i 2D.
|
|
| 3. |
|
|
| 4. |
- Aslani, Mohammad, et al.
(author)
-
A fast instance selection method for support vector machines in building extraction
- 2020
-
In: Applied Soft Computing. - : Elsevier BV. - 1568-4946 .- 1872-9681. ; 97
-
Journal article (peer-reviewed)abstract
- Training support vector machines (SVMs) for pixel-based feature extraction purposes from aerial images requires selecting representative pixels (instances) as a training dataset. In this research, locality-sensitive hashing (LSH) is adopted for developing a new instance selection method which is referred to as DR.LSH. The intuition of DR.LSH rests on rapidly finding similar and redundant training samples and excluding them from the original dataset. The simple idea of this method alongside its linear computational complexity make it expeditious in coping with massive training data (millions of pixels). DR.LSH is benchmarked against two recently proposed methods on a dataset for building extraction with 23,750,000 samples obtained from the fusion of aerial images and point clouds. The results reveal that DR.LSH outperforms them in terms of both preservation rate and maintaining the generalization ability (classification loss). The source code of DR.LSH can be found in https://github.com/mohaslani/DR.LSH.
|
|
| 5. |
- Aslani, Mohammad, et al.
(author)
-
A Spatially Detailed Approach to the Assessment of Rooftop Solar Energy Potential based on LiDAR Data
- 2022
-
In: Proceedings of the 8th International Conference on Geographical Information Systems Theory, Applications and Management - GISTAM. - Setúbal : ScitePress. - 9789897585715 ; , s. 56-63
-
Conference paper (peer-reviewed)abstract
- Rooftop solar energy has long been regarded as a promising solution to cities’ growing energy demand and environmental problems. A reliable estimate of rooftop solar energy facilitates the deployment of photovoltaics and helps formulate renewable-related policies. This reliable estimate underpins the necessity of accurately pinpointing the areas utilizable for mounting photovoltaics. The size, shape, and superstructures of rooftops as well as shadow effects are the important factors that have a considerable impact on utilizable areas. In this study, the utilizable areas and solar energy potential of rooftops are estimated by considering the mentioned factors using a three-step methodology. The first step involves training PointNet++, a deep network for object detection in point clouds, to recognize rooftops in LiDAR data. Second, planar segments of rooftops are extracted using clustering. Finally, areas that receive sufficient solar irradiation, have an appropriate size, and fulfill photovoltaic installation requirements are identified using morphological operations and predefined thresholds. The obtained results show high accuracy for rooftop extraction (93%) and plane segmentation (99%). Moreover, the spatially detailed analysis indicates that 17% of rooftop areas are usable for photovoltaics.
|
|
| 6. |
- Aslani, Mohammad, et al.
(author)
-
Automatic identification of utilizable rooftop areas in digital surface models for photovoltaics potential assessment
- 2022
-
In: Applied Energy. - : Elsevier. - 0306-2619 .- 1872-9118. ; 306
-
Journal article (peer-reviewed)abstract
- The considerable potential of rooftop photovoltaics (RPVs) for alleviating the high energy demand of cities has made them a proven technology in local energy networks. Identification of rooftop areas suitable for installing RPVs is of importance for energy planning. Having these suitable areas referred to as utilizable areas greatly assists in a reliable estimate of RPVs energy production. Within such a context, this research aims to propose a spatially detailed methodology that involves (a) automatic extraction of buildings footprint, (b) automatic segmentation of roof faces, and (c) automatic identification of utilizable areas of roof faces for solar infrastructure installation. Specifically, the innovations of this work are a new method for roof face segmentation and a new method for the identification of utilizable rooftop areas. The proposed methodology only requires digital surface models (DSMs) as input, and it is independent of other auxiliary spatial data to become more functional. A part of downtown Gothenburg composed of vegetation and high-rise buildings with complex shapes was selected to demonstrate the methodology performance. According to the experimental results, the proposed methodology has a high success rate in building extraction (about 95% correctness and completeness) and roof face segmentation (about 85% completeness and correctness). Additionally, the results suggest that the effects of roof occlusions and roof superstructures are satisfactorily considered in the identification of utilizable rooftop areas. Thus, the methodology is practically effective and relevant for the detailed RPVs assessments in arbitrary urban regions where only DSMs are accessible.
|
|
| 7. |
- Aslani, Mohammad
(author)
-
Computational and spatial analyses of rooftops for urban solar energy planning
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- In cities where land availability is limited, rooftop photovoltaic panels (RPVs) offer high potential for satisfying concentrated urban energy demand by using only rooftop areas. However, accurate estimation of RPVs potential in relation to their spatial distribution is indispensable for successful energy planning. Classification, plane segmentation, and spatial analysis are three important aspects in this context. Classification enables extracting rooftops and allows for estimating solar energy potential based on existing training samples. Plane segmentation helps to characterize rooftops by extracting their planar patches. Additionally, spatial analyses enable the identification of rooftop utilizable areas for placing RPVs. This dissertation aims to address some issues associated with these three aspects, particularly (a) training support vector machines (SVMs) in large datasets, (b) plane segmentation of rooftops, and (c) identification of utilizable areas for RPVs. SVMs are among the most potent classifiers and have a solid theoretical foundation. However, they have high time complexity in their training phase, making them inapplicable in large datasets. Two new instance selection methods were proposed to accelerate the training phase of SVMs. The methods are based on locality-sensitive hashing and are capable of handling large datasets. As an application, they were incorporated into a rooftop extraction procedure, followed by plane segmentation. Plane segmentation of rooftops for the purpose of solar energy potential estimation should have a low risk of overlooking superstructures, which play an essential role in the placement of RPVs. Two new methods for plane segmentation in high-resolution digital surface models were thus developed. They have an acceptable level of accuracy and can successfully extract planar segments by considering superstructures. Not all areas of planar segments are utilizable for mounting RPVs, and some factors may further limit their useability. Two spatial methods for identifying RPV-utilizable areas were developed in this realm. They scrutinize extracted planar segments by considering panel installation regulations, solar irradiation, roof geometry, and occlusion, which are necessary for a realistic assessment of RPVs potential. All six proposed methods in this thesis were thoroughly evaluated, and the experimental results show that they can successfully achieve the objectives for which they were designed.
|
|
| 8. |
- Aslani, Mohammad, et al.
(author)
-
Continuous residual reinforcement learning for traffic signal control optimization
- 2018
-
In: Canadian journal of civil engineering (Print). - : NRC Research Press. - 0315-1468 .- 1208-6029. ; 45:8, s. 690-702
-
Journal article (peer-reviewed)abstract
- Traffic signal control can be naturally regarded as a reinforcement learning problem. Unfortunately, it is one of the most difficult classes of reinforcement learning problems owing to its large state space. A straightforward approach to address this challenge is to control traffic signals based on continuous reinforcement learning. Although they have been successful in traffic signal control, they may become unstable and fail to converge to near-optimal solutions. We develop adaptive traffic signal controllers based on continuous residual reinforcement learning (CRL-TSC) that is more stable. The effect of three feature functions is empirically investigated in a microscopic traffic simulation. Furthermore, the effects of departing streets, more actions, and the use of the spatial distribution of the vehicles on the performance of CRL-TSCs are assessed. The results show that the best setup of the CRL-TSC leads to saving average travel time by 15% in comparison to an optimized fixed-time controller.
|
|
| 9. |
- Aslani, Mohammad, et al.
(author)
-
Developing adaptive traffic signal control by actor-critic and direct exploration methods
- 2019
-
In: Proceedings of the Institution of Civil Engineers. - : Thomas Telford. - 0965-092X .- 1751-7710. ; 172:5, s. 289-298
-
Journal article (peer-reviewed)abstract
- Designing efficient traffic signal controllers has always been an important concern in traffic engineering. This is owing to the complex and uncertain nature of traffic environments. Within such a context, reinforcement learning has been one of the most successful methods owing to its adaptability and its online learning ability. Reinforcement learning provides traffic signals with the ability automatically to determine the ideal behaviour for achieving their objective (alleviating traffic congestion). In fact, traffic signals based on reinforcement learning are able to learn and react flexibly to different traffic situations without the need of a predefined model of the environment. In this research, the actor-critic method is used for adaptive traffic signal control (ATSC-AC). Actor-critic has the advantages of both actor-only and critic-only methods. One of the most important issues in reinforcement learning is the trade-off between exploration of the traffic environment and exploitation of the knowledge already obtained. In order to tackle this challenge, two direct exploration methods are adapted to traffic signal control and compared with two indirect exploration methods. The results reveal that ATSC-ACs based on direct exploration methods have the best performance and they consistently outperform a fixed-time controller, reducing average travel time by 21%.
|
|
| 10. |
- Aslani, Mohammad, et al.
(author)
-
Efficient and decision boundary aware instance selection for support vector machines
- 2021
-
In: Information Sciences. - : Elsevier. - 0020-0255 .- 1872-6291. ; 577, s. 579-598
-
Journal article (peer-reviewed)abstract
- Support vector machines (SVMs) are powerful classifiers that have high computational complexity in the training phase, which can limit their applicability to large datasets. An effective approach to address this limitation is to select a small subset of the most representative training samples such that desirable results can be obtained. In this study, a novel instance selection method called border point extraction based on locality-sensitive hashing (BPLSH) is designed. BPLSH preserves instances that are near the decision boundaries and eliminates nonessential ones. The performance of BPLSH is benchmarked against four approaches on different classification problems. The experimental results indicate that BPLSH outperforms the other methods in terms of classification accuracy, preservation rate, and execution time. The source code of BPLSH can be found in https://github.com/mohaslani/BPLSH.
|
|
