Complex Urban Scenes Research Articles

UAVid: A semantic segmentation dataset for UAV imagery

Semantic segmentation has been one of the leading research interests in computer vision recently. It serves as a perception foundation for many fields, such as robotics and autonomous driving. The fast development of semantic segmentation attributes enormously to the large scale datasets, especially for the deep learning related methods. There already exist several semantic segmentation datasets for comparison among semantic segmentation methods in complex urban scenes, such as the Cityscapes and CamVid datasets, where the side views of the objects are captured with a camera mounted on the driving car. There also exist semantic labeling datasets for the airborne images and the satellite images, where the nadir views of the objects are captured. However, only a few datasets capture urban scenes from an oblique Unmanned Aerial Vehicle (UAV) perspective, where both of the top view and the side view of the objects can be observed, providing more information for object recognition. In this paper, we introduce our UAVid dataset, a new high-resolution UAV semantic segmentation dataset as a complement, which brings new challenges, including large scale variation, moving object recognition and temporal consistency preservation. Our UAV dataset consists of 30 video sequences capturing high-resolution images in oblique views. In total, 300 images have been densely labeled with 8 classes for the semantic labeling task. We have provided several deep learning baseline methods with pre-training, among which the proposed Multi-Scale-Dilation net performs the best via multi-scale feature extraction, reaching a mean intersection-over-union (IoU) score around 50%. We have also explored the influence of spatial-temporal regularization for sequence data by leveraging on feature space optimization (FSO) and 3D conditional random field (CRF). Our UAVid website and the labeling tool have been published online (https://uavid.nl/).

Heuristic sample learning for complex urban scenes: Application to urban functional-zone mapping with VHR images and POI data

Urban functional zones are basic units of urban planning and resource allocation, and contribute to a wide range of urban studies and investigations. Existing studies on functional-zone mapping with very-high-resolution (VHR) satellite images focused much on feature representations and classification techniques, but ignored zone sampling which however was fundamental to automatic zone classifications. Functional-zone sampling is much complicated and can hardly be resolved by classical sampling methods, as functional zones are complex urban scenes which consist of heterogeneous land covers and have highly abstract categories. To resolve the issue, this study presents a novel sampling paradigm, i.e., heuristic sample learning (HSL). It first proposes a sparse topic model to select representative functional zones, then uses deep forest to select confusing zones, and finally embraces Chinese restaurant process to label these selected zones. The presented method collects both representative and confusing zone samples and identifies their categories accurately, which makes the functional-zone classification process robust and the classification results accurate. Experiments conducted in Beijing indicate that HSL is effective and efficient for functional-zone sampling and classifications. Compared to traditional manual sampling, HSL reduces the time cost by 55% and improves the classification accuracy by 11.3% on average; furthermore, HSL can reduce the variation in sampling and classification results caused by different proficiency of operators. Accordingly, HSL significantly contributes to functional-zone mapping and plays an important role in urban studies.

CSPC-Dataset: New LiDAR Point Cloud Dataset and Benchmark for Large-Scale Scene Semantic Segmentation

Large-scale point clouds scanned by light detection and ranging (lidar) sensors provide detailed geometric characteristics of scenes due to the provision of 3D structural data. The semantic segmentation of large-scale point clouds is a crucial step for an in-depth understanding of complex scenes. Of late, although a large number of point cloud semantic segmentation algorithms have been proposed, semantic segmentation methods are still far from being satisfactory in terms of precision and accuracy of large-scale point clouds. For machine learning (ML) and deep learning (DL) methodologies, the semantic segmentation is largely influenced by the quality of training sets and methods themselves. Therefore, we construct a new point cloud dataset, namely CSPC-Dataset (Complex Scene Point Cloud Dataset) for large-scale scene semantic segmentation. CSPC-Dataset point clouds are acquired by a wearable laser mobile mapping robot. It covers five complex urban and rural scenes and mainly includes six types of objects, i.e., ground, car, building, vegetation, bridge, and pole. It provides large-scale outdoor scenes with color information, which has advantages such as the scene more complete, point density relatively uniform, diversity and complexity of objects and the high discrepancy between different scenes. Based on the CSPC-Dataset, we construct a new benchmark, which includes approximately 68 million points with explicit semantic labels. To extend the dataset into a wide range of applications, this paper provides the semantic segmentation results and comparative analysis of 7 baseline methods based on CSPC-Dataset. In the experiment part, three groups of experiments are conducted for benchmarking, which offers an effective way to make comparisons with different point-labeling algorithms. The labeling results have shown that the highest Intersection over Union (IoU) of pole, ground, building, car, vegetation, and bridge for all benchmarks is 36.0%, 97.8%, 93.7%, 65.6%, 92.0%, and 69.6%.

LDPNet: A Lightweight Densely Connected Pyramid Network for Real-Time Semantic Segmentation

A deep convolutional neural network has been widely used in image semantic segmentation in recent years, its deployment on mobile terminals, however is limited by its high computational costs. Given the slow inference speed and large memory usage of deep convolutional neural networks, we propose a lightweight and densely connected pyramid network (LDPNet) for real-time semantic segmentation. Firstly, a densely connected atrous pyramid (DCAP) module is constructed in the encoding process to extract multi-scale context information for forwarding propagation, strengthen the reuse of features, and offset the spatial information lost in the down-sampling process of the feature map. Secondly, a cross-fusion (CF) module embedded in each other during the decoding process is proposed, which uses high-level semantic features to effectively guide the fusion of low-level spatial details while strengthening context information. Our network is tested on two complex urban road scene data sets. Among them, experiments on the Cityscapes data set show that our structure has 87 frames per second (FPS) on a single NVIDIA GTX1080Ti GPU. The Mean Intersection over Union (mIoU) reaches 71.1%, and the parameter is only 0.8M. Compared with the existing similar networks, the new system achieves a state-of-the-art trade-off between efficiency and accuracy.

Advances in urban information extraction from high-resolution remote sensing imagery

The study of urban area is one of the hottest research topics in the field of remote sensing. With the accumulation of high-resolution (HR) remote sensing data and emerging of new satellite sensors, HR observation of urban areas has become increasingly possible, which provides us with more elaborate urban information. However, the strong heterogeneity in the spectral and spatial domain of HR imagery brings great challenges to urban remote sensing. In recent years, numerous approaches were proposed to deal with HR image interpretation over complex urban scenes, including a series of features from low level to high level, as well as state-of-the-art methods depicting not only the urban extent, but also the intra-urban variations. In this paper, we aim to summarize the major advances in HR urban remote sensing from the aspects of feature representation and information extraction. Moreover, the future trends are discussed from the perspectives of methodology, urban structure and pattern characterization, big data challenge, and global mapping.

LSwarm: Efficient Collision Avoidance for Large Swarms With Coverage Constraints in Complex Urban Scenes

In this letter, we address the problem of collision avoidance for a swarm of UAVs used for continuous surveillance of an urban environment. Our method, LSwarm, efficiently avoids collisions with static obstacles, dynamic obstacles and other agents in three-dimensional urban environments while considering coverage constraints. LSwarm calculates collision avoiding velocities that maximize the conformity of an agent to an optimal path given by a global coverage strategy and ensure sufficient resolution of the coverage data collected by each agent. Our algorithm is formulated based on optimal reciprocal collision avoidance and is scalable with respect to the size of the swarm. We evaluate the coverage performance of LSwarm in realistic simulations of a swarm of quadrotors in complex urban models. In practice, our approach can compute collision avoiding velocities for a swarm composed of tens to hundreds of agents in a few milliseconds on dense urban scenes consisting of tens of buildings.

T24DISSECTING SUB-PHENOTYPES OF BIPOLAR DISORDER USING MULTIPLE POLYGENIC RISK SCORES

Objects are formed by various structures and such structural information is essential for the identification of objects, especially for street facilities presented by mobile laser scanning (MLS) data with abundant details. However, due to the large volume of data, large variations in point density, noise and complexity of scanned scenes, the achievement of effective decomposition of objects into physical meaningful structures remains a challenge issue. And structural information has been rarely considered to improve the accuracy of distinguishing between objects with global or local similarity, such as traffic signs and traffic lights. Therefore, we propose a structural segmentation and classification method for MLS point clouds that is efficient and robust to variations in point density and complex urban scenes. During the segmentation stage, a novel region growing approach and a multi-size supervoxel segmentation algorithm robust to noise and varying density are combined to extract effective local shape descriptors. Structural components with physically meaningful labels are generated via structural labelling and clustering. During the classification stage, we consider the structural information at various scales and locations and encode it into a conditional random-field model for unary and pairwise inferences. High-order potentials are also introduced into the conditional random field to eliminate regional label noise. These high-order potentials are defined upon regions independent of connection relationships and can therefore take effect on isolated nodes. Experiments with two MLS datasets of typical urban scenes in Paris and Hong Kong were used to evaluate the performance of the proposed method. Nine and eleven different object classes were recognized from these two datasets with overall accuracies of 97.13% and 95.79%, respectively, indicating the effectiveness of the proposed method of interpreting complex urban scenes from point clouds with large variations in point density. Compared with previous studies on the Paris dataset, our method was able to recognize more classes and obtained a mean F1-score of 72.70% of seven common classes, being higher than the best of previous results.

AN IMPROVED AUTOMATIC POINTWISE SEMANTIC SEGMENTATION OF A 3D URBAN SCENE FROM MOBILE TERRESTRIAL AND AIRBORNE LIDAR POINT CLOUDS: A MACHINE LEARNING APPROACH

Abstract. Automatic semantic segmentation of point clouds observed in a 3D complex urban scene is a challenging issue. Semantic segmentation of urban scenes based on machine learning algorithm requires appropriate features to distinguish objects from mobile terrestrial and airborne LiDAR point clouds in point level. In this paper, we propose a pointwise semantic segmentation method based on our proposed features derived from Difference of Normal and the features “directional height above” that compare height difference between a given point and neighbors in eight directions in addition to the features based on normal estimation. Random forest classifier is chosen to classify points in mobile terrestrial and airborne LiDAR point clouds. The results obtained from our experiments show that the proposed features are effective for semantic segmentation of mobile terrestrial and airborne LiDAR point clouds, especially for vegetation, building and ground classes in an airborne LiDAR point clouds in urban areas.

FUSION OF FEATURE BASED AND DEEP LEARNING METHODS FOR CLASSIFICATION OF MMS POINT CLOUDS

Abstract. This work proposes an approach for semantic classification of an outdoor-scene point cloud acquired with a high precision Mobile Mapping System (MMS), with major goal to contribute to the automatic creation of High Definition (HD) Maps. The automatic point labeling is achieved by utilizing the combination of a feature-based approach for semantic classification of point clouds and a deep learning approach for semantic segmentation of images. Both, point cloud data, as well as the data from a multi-camera system are used for gaining spatial information in an urban scene. Two types of classification applied for this task are: 1) Feature-based approach, in which the point cloud is organized into a supervoxel structure for capturing geometric characteristics of points. Several geometric features are then extracted for appropriate representation of the local geometry, followed by removing the effect of local tendency for each supervoxel to enhance the distinction between similar structures. And lastly, the Random Forests (RF) algorithm is applied in the classification phase, for assigning labels to supervoxels and therefore to points within them. 2) The deep learning approach is employed for semantic segmentation of MMS images of the same scene. To achieve this, an implementation of Pyramid Scene Parsing Network is used. Resulting segmented images with each pixel containing a class label are then projected onto the point cloud, enabling label assignment for each point. At the end, experiment results are presented from a complex urban scene and the performance of this method is evaluated on a manually labeled dataset, for the deep learning and feature-based classification individually, as well as for the result of the labels fusion. The achieved overall accuracy with fusioned output is 0.87 on the final test set, which significantly outperforms the results of individual methods on the same point cloud. The labeled data is published on the TUM-PF Semantic-Labeling-Benchmark.

CONTOUR EXTRACTION OF PLANAR ELEMENTS OF BUILDING FACADES FROM POINT CLOUDS USING GLOBAL GRAPH-BASED CLUSTERING

Abstract. In this work, we present a surface-based method to extract the contours of planar building elements in the urban scene. A bottom-up segmentation method that utilizes global graph-based optimization and supervoxel structure is developed, enabling an automatic and unsupervised segmentation of point clouds. Then, a planarity-based extraction is conducted to segments, and only the planar segments, as well as their neighborhoods, are selected as candidates for the plane fitting. The points of the plane can be identified by the parametric model given by the planarity calculation. Afterward, the boundary points of the extracted plane are extracted by the alpha-shape. Optionally, line segments can be fitted and optimized by the energy minimization with the local graphical model. The experimental results using different datasets reveal that our proposed segmentation methods can be effective and comparable with other method, and the contours of planar building elements can be well extracted from the complex urban scene.

Structural segmentation and classification of mobile laser scanning point clouds with large variations in point density

Objects are formed by various structures and such structural information is essential for the identification of objects, especially for street facilities presented by mobile laser scanning (MLS) data with abundant details. However, due to the large volume of data, large variations in point density, noise and complexity of scanned scenes, the achievement of effective decomposition of objects into physical meaningful structures remains a challenge issue. And structural information has been rarely considered to improve the accuracy of distinguishing between objects with global or local similarity, such as traffic signs and traffic lights. Therefore, we propose a structural segmentation and classification method for MLS point clouds that is efficient and robust to variations in point density and complex urban scenes. During the segmentation stage, a novel region growing approach and a multi-size supervoxel segmentation algorithm robust to noise and varying density are combined to extract effective local shape descriptors. Structural components with physically meaningful labels are generated via structural labelling and clustering. During the classification stage, we consider the structural information at various scales and locations and encode it into a conditional random-field model for unary and pairwise inferences. High-order potentials are also introduced into the conditional random field to eliminate regional label noise. These high-order potentials are defined upon regions independent of connection relationships and can therefore take effect on isolated nodes. Experiments with two MLS datasets of typical urban scenes in Paris and Hong Kong were used to evaluate the performance of the proposed method. Nine and eleven different object classes were recognized from these two datasets with overall accuracies of 97.13% and 95.79%, respectively, indicating the effectiveness of the proposed method of interpreting complex urban scenes from point clouds with large variations in point density. Compared with previous studies on the Paris dataset, our method was able to recognize more classes and obtained a mean F1-score of 72.70% of seven common classes, being higher than the best of previous results.

RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes From High-Resolution Remotely Sensed Images

It is a classical task to automatically extract road networks from very high-resolution (VHR) images in remote sensing. This paper presents a novel method for extracting road networks from VHR remotely sensed images in complex urban scenes. Inspired by image segmentation, edge detection, and object skeleton extraction, we develop a multitask convolutional neural network (CNN), called RoadNet, to simultaneously predict road surfaces, edges, and centerlines, which is the first work in such field. The RoadNet solves seven important issues in this vision problem: 1) automatically learning multiscale and multilevel features [gained by the deeply supervised nets (DSN) providing integrated direct supervision] to cope with the roads in various scenes and scales; 2) holistically training the mentioned tasks in a cascaded end-to-end CNN model; 3) correlating the predictions of road surfaces, edges, and centerlines in a network model to improve the multitask prediction; 4) designing elaborate architecture and loss function, by which the well-trained model produces approximately single-pixel width road edges/centerlines without nonmaximum suppression postprocessing; 5) cropping and bilinear blending to deal with the large VHR images with finite-computing resources; 6) introducing rough and simple user interaction to obtain desired predictions in the challenging regions; and 7) establishing a benchmark data set which consists of a series of VHR remote sensing images with pixelwise annotation. Different from the previous works, we pay more attention to the challenging situations, in which there are lots of shadows and occlusions along the road regions. Experimental results on two benchmark data sets show the superiority of our proposed approaches.

Patch Matching and Dense CRF-Based Co-Refinement for Building Change Detection from Bi-Temporal Aerial Images.

The identification and monitoring of buildings from remotely sensed imagery are of considerable value for urbanization monitoring. Two outstanding issues in the detection of changes in buildings with composite structures and relief displacements are heterogeneous appearances and positional inconsistencies. In this paper, a novel patch-based matching approach is developed using densely connected conditional random field (CRF) optimization to detect building changes from bi-temporal aerial images. First, the bi-temporal aerial images are combined to obtain change information using an object-oriented technique, and then semantic segmentation based on a deep convolutional neural network is used to extract building areas. With the change information and extracted buildings, a graph-cuts-based segmentation algorithm is applied to generate the bi-temporal changed building proposals. Next, in the bi-temporal changed building proposals, corner and edge information are integrated for feature detection through a phase congruency (PC) model, and the structural feature descriptor, called the histogram of orientated PC, is used to perform patch-based roof matching. We determined the final change in buildings by gathering matched roof and bi-temporal changed building proposals using co-refinement based on CRF, which were further classified as “newly built,” “demolished”, or “changed”. Experiments were conducted with two typical datasets covering complex urban scenes with diverse building types. The results confirm the effectiveness and generality of the proposed algorithm, with more than 85% and 90% in overall accuracy and completeness, respectively.

Exploring semantic elements for urban scene recognition: Deep integration of high-resolution imagery and OpenStreetMap (OSM)

Urban scenes refer to city blocks which are basic units of megacities, they play an important role in citizens’ welfare and city management. Remote sensing imagery with largescale coverage and accurate target descriptions, has been regarded as an ideal solution for monitoring the urban environment. However, due to the heterogeneity of remote sensing images, it is difficult to access their geographical content at the object level, let alone understanding urban scenes at the block level. Recently, deep learning-based strategies have been applied to interpret urban scenes with remarkable accuracies. However, the deep neural networks require a substantial number of training samples which are hard to satisfy, especially for high-resolution images. Meanwhile, the crowed-sourced Open Street Map (OSM) data provides rich annotation information about the urban targets but may encounter the problem of insufficient sampling (limited by the places where people can go). As a result, the combination of OSM and remote sensing images for efficient urban scene recognition is urgently needed. In this paper, we present a novel strategy to transfer existing OSM data to high-resolution images for semantic element determination and urban scene understanding. To be specific, the object-based convolutional neural network (OCNN) can be utilized for geographical object detection by feeding it rich semantic elements derived from OSM data. Then, geographical objects are further delineated into their functional labels by integrating points of interest (POIs), which contain rich semantic terms, such as commercial or educational labels. Lastly, the categories of urban scenes are easily acquired from the semantic objects inside. Experimental results indicate that the proposed method has an ability to classify complex urban scenes. The classification accuracies of the Beijing dataset are as high as 91% at the object-level and 88% at the scene level. Additionally, we are probably the first to investigate the object level semantic mapping by incorporating high-resolution images and OSM data of urban areas. Consequently, the method presented is effective in delineating urban scenes that could further boost urban environment monitoring and planning with high-resolution images.

Geographic, geometrical and semantic reconstruction of urban scene from high resolution oblique aerial images

An effective approach is proposed for 3D urban scene reconstruction in the form of point cloud with semantic labeling. Starting from high resolution oblique aerial images, our approach proceeds through three main stages: geographic reconstruction, geometrical reconstruction and semantic reconstruction. The absolute position and orientation of all the cameras relative to the real world are recovered in the geographic reconstruction stage. Then, in the geometrical reconstruction stage, an improved multi-view stereo matching method is employed to produce 3D dense points with color and normal information by taking into account the prior knowledge of aerial imagery. Finally the point cloud is classified into three classes &#x0028 building, vegetation, and ground &#x0029 by a rule-based hierarchical approach in the semantic reconstruction step. Experiments on complex urban scene show that our proposed 3-stage approach could generate reasonable reconstruction result robustly and efficiently. By comparing our final semantic reconstruction result with the manually labeled ground truth, classification accuracies from 86.75&#x25 to 93.02&#x25 are obtained.

Improving LiDAR classification accuracy by contextual label smoothing in post-processing

We propose a contextual label-smoothing method to improve the LiDAR classification accuracy in a post-processing step. Under the framework of global graph-structured regularization, we enhance the effectiveness of label smoothing from two aspects. First, each point can collect sufficient label-relevant neighborhood information to verify its label based on an optimal graph. Second, the input label probability set is improved by probabilistic label relaxation to be more consistent with the spatial context. With this optimal graph and reliable label probability set, the final labels are computed by graph-structured regularization. We demonstrate the contextual label-smoothing approach on two separate urban airborne LiDAR datasets with complex urban scenes. Significant improvements in the classification accuracies are achieved without losing small objects (such as façades and cars). The overall accuracy is increased by 7.01% on the Vienna dataset and 6.88% on the Vaihingen dataset. Moreover, most large, wrongly labeled regions are corrected by long-range interactions that are derived from the optimal graph, and misclassified regions that lack neighborhood communications in terms of correct labels are also corrected with the probabilistic label relaxation.

Modified Superpixel Segmentation for Digital Surface Model Refinement and Building Extraction from Satellite Stereo Imagery

Superpixels, as a state-of-the-art segmentation paradigm, have recently been widely used in computer vision and pattern recognition. Despite the effectiveness of these algorithms, there are still many limitations and challenges dealing with Very High-Resolution (VHR) satellite images especially in complex urban scenes. In this paper, we develop a superpixel algorithm as a modified edge-based version of Simple Linear Iterative Clustering (SLIC), which is here called ESLIC, compatible with VHR satellite images. Then, based on the modified properties of generated superpixels, a heuristic multi-scale approach for building extraction is proposed, based on the stereo satellite imagery along with the corresponding Digital Surface Model (DSM). First, to generate the modified superpixels, an edge-preserving term is applied to retain the main building boundaries and edges. The resulting superpixels are then used to initially refine the stereo-extracted DSM. After shadow and vegetation removal, a rough building mask is obtained from the normalized DSM, which highlights the appropriate regions in the image, to be used as the input of a multi-scale superpixel segmentation of the proper areas to determine the superpixels inside the building. Finally, these building superpixels with different scales are integrated and the output is a unified building mask. We have tested our methods on building samples from a WorldView-2 dataset. The results are promising, and the experiments show that superpixels generated with the proposed ESLIC algorithm are more adherent to the building boundaries, and the resulting building mask retains urban object shape better than those generated with the original SLIC algorithm.

Vehicles detection for illumination changes urban traffic scenes employing adaptive local texture feature background model

An Adaptive Local Texture Feature Background Model (ALTF-BM) is proposed to resolve the deficiency in current background models, which are easily contaminated by sudden and gradual illumination changes in complex urban traffic scenes. Based on Weber's law, the authors first develop Adaptive Local Texture Feature (ALTF), calculated over a predefined local region around the pixel employing an adaptive distance threshold, and then the background is modelled on the base of sample consensus scheme using the calculated features. Furthermore, to label the foreground pixels, the difference between the background model and input video frames is then directly compared by ALTF encoding. Finally, the model is updated using the random update policy to adapt to the changing illumination and the dynamic background. The experimental results on real-world urban traffic videos and the public Change Detection benchmark of 2014 (CDnet2014) show that the proposed ALTF-BM offers the best performance compared to the other state-of-the-art texture-based methods, and the average F -measures and similarity results of the proposed ALTF-BM are 0.547 and 0.393 higher than benchmarks on the night traffic-light sequence, respectively. The encouraging experimental results demonstrate the efficiency of the proposed ALTF-BM in handling sudden and gradual illumination changes in urban traffic scenes.

A novel rapid point-cloud surface reconstruction algorithm for laser imaging radar

In order to obtain the fast three-dimensional surface reconstruction from given scattered point clouds, a novel improved point-cloud surface reconstruction algorithm for laser imaging radar is proposed so as to reconstruct the three-dimensional depth surface from the depth data and image data in this paper. Firstly, the three-dimensional space is partitioned into voxels with local distance points and finds outliers with point histogram features; then the Gaussian process (GP) regression is adopted to generate a plane similar to a Gaussian distribution; finally, the high-resolution gray data and three-dimensional interpolation points are fused by using Markov random fields to build a dense three-dimensional depth surface. Experimental results show that our proposed algorithm will greatly improve the robustness and reconstruction accuracy of three-dimensional surface reconstruction algorithm and can be used to assist unmanned driving in complex urban scenes.

Sky view factor as predictor of solar availability on building façades

Solar availability on urban façades varies significantly, affected by obstructions by nearby buildings as well as orientation. A convenient way to evaluate their solar energy potential is deemed to facilitate the task of architects in increasing the use of photovoltaic systems and, thus solar energy generation in the urban environment. This study explores to what extent the sky view factor (SVF), a measure of the openness of a point to the sky, can be employed for evaluating solar irradiation of façades in complex urban scenes. For this purpose, extensive statistical analysis was performed testing the correlation of SVF with solar irradiances for 30 orientations, considering three European climates (i.e. Athens, London and Helsinki), and three periods (i.e. year, January and July). Special emphasis is put on global irradiance, which expresses the sum of three solar components, i.e. direct, diffuse and reflected. The study uses 24 urban forms - of 500 × 500 m area - in London for which SVF and solar irradiance simulations were performed for nine sky models (three locations by three periods). The results reveal a strong linear relationship (R2 > 0.8) between SVF and annual global irradiance in all orientations, at all three locations. In fact, as SVF was found to correlate well with both major solar components, direct and diffuse, it can be presumably used for predicting façades' annual solar irradiation at any location within the tested range of latitudes. With respect to monthly global irradiance, the relationship appears less consistent, affected by the increased sensitivity of the relationship of SVF with monthly direct irradiance to façade orientation and location's latitude, associated with the variations of solar altitude.