Moving Car Recognition and Removal for 3D Urban Modelling Using Oblique Images

With the progress of photogrammetry and computer vision technology, three-dimensional (3D) reconstruction using aerial oblique images has been widely applied in urban modelling and smart city applications. However, state-of-the-art image-based automatic 3D reconstruction methods cannot effectively handle the unavoidable geometric deformation and incorrect texture mapping problems caused by moving cars in a city. This paper proposes a method to address this situation and prevent the influence of moving cars on 3D modelling by recognizing moving cars and combining the recognition results with a photogrammetric 3D modelling procedure. Through car detection using a deep learning method and multiview geometry constraints, we can analyse the state of a car’s movement and apply a proper preprocessing method to the geometrically model generation and texture mapping steps of 3D reconstruction pipelines. First, we apply the traditional Mask R-CNN object detection method to detect cars from oblique images. Then, a detected car and its corresponding image patch calculated by the geometry constraints in the other view images are used to identify the moving state of the car. Finally, the geometry and texture information corresponding to the moving car will be processed according to its moving state. Experiments on three different urban datasets demonstrate that the proposed method is effective in recognizing and removing moving cars and can repair the geometric deformation and error texture mapping problems caused by moving cars. In addition, the methods proposed in this paper can be applied to eliminate other moving objects in 3D modelling applications.

More dense but less walkable: the impact of macroscale walkability indicators on recent designs of emirati neighborhoods

With the aim to enhance sustainability in general including walkability, the recent urban forms of the designs of the Emirati neighborhoods have been denser and more compact, if compared with the older design models. While there are various guidelines and regulations related to the microscale walkability measures for the urban design of neighborhoods in the Emirates but unfortunately the macroscale walkability measures have not received similar attention. So, to investigate how would these denser and more compact recent neighborhoods designs better perform regarding walkability macroscale measures, the research utilized the urban modelling interface (UMI) walkability simulation tool to calculate the UMI Walkscores of these designs because it considers almost all macroscale factors including both urban morphology and urban planning measures and it also allows for the customization of the types, required catchment distances, and weights of the significance of locally provided amenities. The UMI Walkscores were calculated for the six recent denser and more compact neighborhoods designs and were compared with the UMI Walkscore for a conventionally designed model of urban sprawling neighborhoods. Unexpectedly, it has been found out that urban compactness per se is not a sufficient design measure for enhancing walkability in local neighborhood designs, where much higher compactness and density have achieved disappointing UMI Walkscores. So, it seems that for the recent neighborhoods’ designs, little attention was paid to the impact of the street network connectivity measures of Intersection Density, Block Length and the link-to-nodes ratio, on UMI Walkscores, if compared with the main attention paid to increasing FAR through decreasing plot sizes. Meanwhile, the explicit macroscale urban planning measures including the land-use factors of the types, numbers, and the location of amenities, as well as the implicit factors of their destination and global weights seem to be more influential in enhancing the UMI Walkscores but have been less considered when planning these neighborhoods. So, besides considering well-known macroscale urban morphology aspects of street network connectivity and locational distribution of provided amenities, boosting walkability macroscale measures on the design level requires adopting a set of adequately customized measures including the appropriate values of their global and distribution weights. These walkability design weights should be also resilient and continuously reviewed to satisfy the changing needs of the local communities. Based on its findings, the research proposed a five-actions plan to help boost walkability macroscale measures in the design of local urban communities in the UAE.

Designing an Energy-Resilient Neighbourhood Using an Urban Building Energy Model

A climate resilient city, perforce, has an efficient and robust energy infrastructure that can harvest local energy resources and match energy sources and sinks that vary over space and time. This paper explores the use of an urban building energy model (UBEM) to examine the potential for creating a near-zero carbon neighbourhood in Dublin (Ireland) that is characterised by diverse land-uses and old and new building stock. UBEMs are a relatively new tool that allows the simulation of building energy demand across an urbanised landscape and can account for building layout, including the effects of overshadowing and the potential for facade retrofits and energy generation. In this research, a novel geographic database of buildings is created using archetypes, and the associated information on dimensions, fabric and energy systems is integrated into the Urban Modelling Interface (UMI). The model is used to simulate current and future energy demand based on climate change projections and to test scenarios that apply retrofits to the existing stock and that link proximate land-uses and land-covers. The latter allows a significant decoupling of the neighbourhood from an offsite electricity generation station with a high carbon output. The findings of this paper demonstrate that treating neighbourhoods as single energy entities rather than collections of individual sectors allows the development of bespoke carbon reducing scenarios that are geographically situated. The work shows the value of a neighbourhood-based approach to energy management using UBEMs.

Panoramic Street-Level Imagery in Data-Driven Urban Research: A Comprehensive Global Review of Applications, Techniques, and Practical Considerations

The release of Google Street View in 2007 inspired several new panoramic street-level imagery platforms including Apple Look Around, Bing StreetSide, Baidu Total View, Tencent Street View, Naver Street View, and Yandex Panorama. The ever-increasing global capture of cities in 360° provides considerable new opportunities for data-driven urban research. This paper provides the first comprehensive, state-of-the-art review on the use of street-level imagery for urban analysis in five research areas: built environment and land use; health and wellbeing; natural environment; urban modelling and demographic surveillance; and area quality and reputation. Panoramic street-level imagery provides advantages in comparison to remotely sensed imagery and conventional urban data sources, whether manual, automated, or machine learning data extraction techniques are applied. Key advantages include low-cost, rapid, high-resolution, and wide-scale data capture, enhanced safety through remote presence, and a unique pedestrian/vehicle point of view for analyzing cities at the scale and perspective in which they are experienced. However, several limitations are evident, including limited ability to capture attribute information, unreliability for temporal analyses, limited use for depth and distance analyses, and the role of corporations as image-data gatekeepers. Findings provide detailed insight for those interested in using panoramic street-level imagery for urban research.

3D CONTENT GENERATION USING HYBRID AERIAL SENSOR DATA

In aerial data acquisition a new era started with the introduction of the first real hybrid sensor systems, like the Leica CityMapper-2. Hybrid in this context means the combination of an (oblique) camera system with a topographic LiDAR into an integrated aerial mapping system. By combining these complimentary sub-systems into one system the weaknesses of the one system could be compensated by using the alternative data source. An example is the mapping of low-light urban canyons, where image-based systems mostly produce unreliable results. For an LiDAR sensor the geometrical reconstruction of these areas is straight forward and leads to accurate results. The paper gives a detailed overview over the development and technical characteristics of hybrid sensor systems. The process of data acquisition is discussed and strategies for hybrid urban mapping are proposed. A hybrid sensor alone is just a part of the whole procedure to generate 3D content. As important as the senor itself is the workflow to generate the products. Here again a hybrid approach, with the processing of all datasets in one environment, is discussed. Special attention is paid to the hybrid orientation of the data and the integrated generation of base and enhanced products. The paper is rounded off by the discussion of the advantage of LiDAR data for the 3D Mesh generation for urban modelling.

EEB Project System Integration and Technology Sperimentation Matrix

Today an increasing number of cities are equipping themselves with three-dimensional urban modelling and simulation platforms for energy management to integrate both spatial and semantic data for enabling better decision-making. The work presented in this chapter is the result of the study carried out by Politecnico di Torino within the Energy Efficient Buildings (EEB) project. Collected data on urban and building scale are managed in specialized, independent, and heterogeneous domains such as GIS, BIM, and IoT devices for energy and electrical monitoring. Possible relationships among these datasets in the perspective of system integration have been carried out according to a rich matrix of experimentations. Specific tools, including innovative visualization technologies and web services, are put in place to allow final users to benefit from this data. The infrastructure is intended to establish a common interoperable ground among heterogeneous networks to achieve the goal of smart cities digital twins.

NAS-HRIS: Automatic Design and Architecture Search of Neural Network for Semantic Segmentation in Remote Sensing Images

The segmentation of high-resolution (HR) remote sensing images is very important in modern society, especially in the fields of industry, agriculture and urban modelling. Through the neural network, the machine can effectively and accurately extract the surface feature information. However, using the traditional deep learning methods requires plentiful efforts in order to find a robust architecture. In this paper, we introduce a neural network architecture search (NAS) method, called NAS-HRIS, which can automatically search neural network architecture on the dataset. The proposed method embeds a directed acyclic graph (DAG) into the search space and designs the differentiable searching process, which enables it to learn an end-to-end searching rule by using gradient descent optimization. It uses the Gumbel-Max trick to provide an efficient way when drawing samples from a non-continuous probability distribution, and it improves the efficiency of searching and reduces the memory consumption. Compared with other NAS, NAS-HRIS consumes less GPU memory without reducing the accuracy, which corresponds to a large amount of HR remote sensing imagery data. We have carried out experiments on the WHUBuilding dataset and achieved 90.44% MIoU. In order to fully demonstrate the feasibility of the method, we made a new urban Beijing Building dataset, and conducted experiments on satellite images and non-single source images, achieving better results than SegNet, U-Net and Deeplab v3+ models, while the computational complexity of our network architecture is much smaller.