Google Street View Panoramas Research Articles

Using google street view panoramas to investigate the influence of urban coastal street environment on visual walkability

Urban street walkability can effectively promote public health and the construction of livable cities. In addition, the coastal streets play a positive role in showing urban vitality and image. Due to the growing leisure needs of residents, measuring the visual walkability perception (VIWP) in urban streets and exploring the influence mechanisms of urban coastal street environments on VIWP have theoretical and practical significance. However, the methods of the previous walkability studies have limitations in terms of cost, time and measurement scale. Based on Google Street View Panoramic (GSVP) image data, this study used the semantic difference (SD) method with virtual reality (VR) technology to evaluate the VIWP of Fukuoka coastal streets. Meanwhile, the proportion of streetscape elements was extracted from GSVP images by semantic segmentation. The correlation and regression analyses were performed between the VIWP evaluation values and streetscape elements. Then, the regression model of the VIWP and the streetscape elements was established. The results showed that the natural features had a positive influence on VIWP in coastal streets. Correspondingly, trees were the strongest contribution rate for the VIWP, followed by shrubs, grasses and water, however, buildings and cars had a negative influence on VIWP. The method extends previous studies for measuring walkability, and optimization strategies were proposed to improve the visual quality of the coastal streets. It can be applied in the construction and management of walkable coastal street environments.

Streetscape and business survival: Examining the impact of walkable environments on the survival of restaurant businesses in commercial areas based on street view images

Walkable environments within commercial areas can be an important factor that vitalizes consumers' walking access, thereby increasing stores' survival. Particularly, the survival of restaurant businesses may be more sensitive to surrounding walkability than that of other businesses. Despite many studies on the relationships between walkability and restaurants' survival, prior studies have identified walkable environments at a macro-scale, not at a pedestrian's eye-level view along the street. This study addresses these gaps by investigating the impact of macro- and micro-scale walkable environments on the survival of restaurant businesses in the commercial areas of Seoul, Korea. To identify micro-scale streetscapes in commercial areas, we used deep learning technologies utilizing 82,563 Google Street View panorama images. We employed spatial lag and multiple regression models to clarify the impact of walkable environments on restaurants' survival. This study also accounted for two types of commercial areas to examine how the impact of walkability varies across commercial areas' heterogeneity. We found that streetscapes play a key role in increasing the survival of restaurants in commercial areas. This study may help policymakers develop tailored approaches to vitalize the economies of local commercial areas by considering the environmental characteristics of commercial areas and the impacts of improving the walkable environment.

Using Google Street View Panoramas to evaluate the environmental aesthetics quality of blue spaces in urban area

The water environment is considered an important element of the urban landscape. In this study, panoramas of the Google Street Map were used to evaluate the aesthetics quality of three blue spaces environment in the Tokyo, and discussed factors affecting these aesthetic qualities. The founding of the paper: 1) the environmental characteristics of the three selected UBSs are different; 2) three UBS with different environmental visual factors (SVF, BVF, and TVF); 3) the Google Street View panoramas used in the study enable viewers to perceive the differences in the aesthetic quality of different environments; 4) the most significant preference predictor for three UBS is Mystery, and “Multisensority & Nature” and “Sublimity” are two significant preference predictor for urban canal. The results of the study have practical and managerial implications for improving the environmental aesthetic quality of urban blue spaces.

Comparison of different methods to assess the distribution of alien plants along the road network and use of Google Street View panoramas interpretation in Sicily (Italy) as a case study.

The survey by foot in the field is compared to the survey from a car, the photo-interpretation of Google Street View (GSV) panoramas continuously and at intervals of 1.5 km and the photo-interpretation of Google Earth aerial images on a 10 km stretch of road in Sicily. The survey by foot was used as reference for the other methods. The interpretation of continuous GSV panoramas gave similar results as the assessment by car in terms of the number of species identified and their location, but with lower cost. The interpretation online of aerial photos allowed the identification of a limited number of taxa, but gave a good localisation for them. Interpretation of GSV panoramas, each of 1.5 km, allowed the recognition of twice as many taxa as the interpretation of aerial photos and taking half the time, but did not allow a complete localisation.None of these methods alone seems sufficient to carry out a complete survey. A mixture of different techniques, which may vary according to the available resources and the goal to be achieved, seems to be the best compromise.To further test the capabilities of the survey using the interpretation of GSV panoramas every 1.5 km along the roads, we proceeded to study the alien plants along 3500 km of the road network on the island of Sicily. This survey identified only 10% of the known species for the region, but allowed us to trace the distribution of invasive species whose distribution is currently poorly recorded.

3D MAP SYSTEM FOR TREE MONITORING IN HONG KONG USING GOOGLE STREET VIEW IMAGERY AND DEEP LEARNING

Abstract. In densely built urban areas such as Hong Kong, the positive effect of urban trees is to help maintain high environmental and social sustainability for the city while unmanaged trees lead to negative effects such as accidents, outbreaks of pests and diseases. The public awareness of urban tree population has been increasing and preserving all the benefits offered by trees, a continuous monitoring concept would be required. In this work, an efficient 3D map system for tree inventory in Hong Kong is presented to the based on automated tree detection from publicly available Google street view (GSV) panorama images. First, Convolutional Neural Networks (CNNs) based object detector and classifier – YOLOv3 with pretrained model is adopted to learn GSV images to detect tree objects. GSV depth image has been utilized to decode depth values of each GSV panorama image and will provide accurate information to calculate the tree geographic position. A “field of view” filter was designed to remove duplicated tree detection within the overlapped areas followed by spatial clustering applied to further increase the tree localization accuracy. The average distance between the detected trees and ground truth data was achieved within 3 meters for selected roads used for the experiment. Second, a 3D Map platform prototype for facilitating the urban tree monitoring and management was developed. Currently, there is no true 3D platform for interpreting the results of tree records in Hong Kong city areas. With the help of webGL technology, contemporary browsers are able to show 3D buildings, terrain and other scene components together with the obtained tree records in an open source 3D GIS platform, the level of visualization is enhanced as all the detected trees are placed on the 3D digital terrain model. Consequently, it is easy for end-users to know the actual position of the trees and their distribution.

VR‐Rides: An object‐oriented application framework for immersive virtual reality exergames

SUMMARYExercise can improve health and well‐being. With this in mind, immersive virtual reality (VR) games are being developed to promote physical activity, and are generally evaluated through user studies. However, building such applications is time consuming and expensive. This paper introduces VR‐Rides, an object‐oriented application framework focused on the development of experiment‐oriented VR exergames. Following the modular programming pattern, this framework facilitates the integration of different hardware (such as VR devices, sensors, and physical activity devices) within immersive VR experiences that overlay game narratives on Google Street View panoramas. Combining software engineering and interaction patterns, modules of VR‐Rides can be easily added and managed in the Unity game engine. We evaluate the code efficiency and development effort across our VR exergames developed using VR‐Rides. The reliability, maintainability, and usability of our framework are also demonstrated via code metrics analysis and user studies. The results show that investing in a systematic approach to reusing code and design can be a worthwhile effort for researchers beyond software engineering.

Geocoding of trees from street addresses and street-level images

We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching. Geolocations of trees in inventories until the early 2000s where recorded using street addresses whereas newer inventories use GPS. Our method retrofits older inventories with geographic coordinates to allow connecting them with newer inventories to facilitate long-term studies on tree mortality etc. What makes this problem challenging is the different number of trees per street address, the heterogeneous appearance of different tree instances in the images, ambiguous tree positions if viewed from multiple images and occlusions. To solve this assignment problem, we (i) detect trees in Google street-view panoramas using deep learning, (ii) combine multi-view detections per tree into a single representation, (iii) and match detected trees with given trees per street address with a global optimization approach. Experiments for >50000 trees in 5 cities in California, USA, show that we are able to assign geographic coordinates to 38% of the street trees, which is a good starting point for long-term studies on the ecosystem services value of street trees at large scale.

GSV2SVF-an interactive GIS tool for sky, tree and building view factor estimation from street view photographs

Sky View Factor (SVF) is a commonly used indicator of urban geometry. The availability of street-level SVF measurements has been fairly limited due to the high costs of field survey. The Google Street View (GSV) serves a massive storage of panorama data that can be utilized to obtain SVF measurements. Yet, automatic extraction of SVFs from panoramas is a complicated process that involves multiple sophisticated computation technologies including machine learning, big image data processing, SVF estimation and geographic information systems (GIS), which constitute major hurdles for the end users. In this light, we developed an easy-to-use GIS-integrated tool (GSV2SVF) to streamline the workflow of extracting SVFs from GSV images and therefore making this vast treasure trove of information conveniently available to everyone at a mouse click. As by-products in addition to the SVF, the results obtained from each GSV panorama are accompanied with the tree view factor (TVF) and the building view factor (BVF), which together can provide a more holistic characterization of the outdoor built environment. GSV2SVF is freely available with source code at https://github.com/jian9695/GSV2SVF. A video is available at https://github.com/jian9695/GSV2SVF/blob/master/Video.mp4 and https://youtu.be/k00wCnuzuvE.

ACCURACY ASSESSMENT OF 3D MODELS GENERATED FROM GOOGLE STREET VIEW IMAGERY

Abstract. Google Street View is a technology implemented in several Google services/applications (e.g. Google Maps, Google Earth) which provides the user, interested in viewing a particular location on the map, with panoramic images (represented in equi-rectangular projection) at street level. Generally, consecutive panoramas are acquired with an average distance of 5–10 m and can be compared to a traditional photogrammetric strip and, thus, processed to reconstruct portion of city at nearly zero cost. Most of the photogrammetric software packages available today implement spherical camera models and can directly process images in equi-rectangular projection. Although many authors provided in the past relevant works that involved the use of Google Street View imagery, mainly for 3D city model reconstruction, very few references can be found about the actual accuracy that can be obtained with such data. The goal of the present work is to present preliminary tests (at time of writing just three case studies has been analysed) about the accuracy and reliability of the 3D models obtained from Google Street View panoramas.

Mapping the spatio-temporal distribution of solar radiation within street canyons of Boston using Google Street View panoramas and building height model

Studying the solar radiation within street canyons would provide an important reference for increasing human thermal comfort and decreasing the potential health issues caused by too much exposure from sunlight. In this study, we used building height model and publicly accessible Google Street View panoramas to map the spatio-temporal distribution of solar radiation within street canyons of Boston, Massachusetts. Hemispherical images generated from Google Street View panoramas and building height model together with sun paths in summer and winter were used to estimate the spatio-temporal distribution of solar radiation within street canyons. Results show that street canyons in the downtown area have shorter sunshine duration and lower solar radiation to the ground compared with other regions of the study area in the whole year. The southwestern part of the study area with the abundance of vegetation canopies has relatively short direct sunshine duration and low solar radiation reaching the ground in summer, and relatively long direct sunshine duration and high solar radiation reaching the ground in winter. This study also shows that it is possible to estimate shading precisely within street canyons for a specific time and date at a specific location. Considering the public accessibility of Google Street View data in cities around the world, this study can be easily deployed in other cities. This study would give a great impetus to all studies relating the solar radiation at street level in future.

Mapping the spatial distribution of shade provision of street trees in Boston using Google Street View panoramas

Street trees provide shade and increase human thermal comfort during hot summer. In this study, we investigated the spatial distribution of shade provision of street trees in Boston, Massachusetts. The sky view factor (SVF), which influences the solar radiation to the ground and affects human thermal comfort, was used to indicate the contribution of street trees on shade provision. Google Street View (GSV) panoramas were used to calculate the photographic method based SVF (SVFP), with the consideration of all kinds of obstructions within street canyons. A building height model was used to calculate the simulation based SVF (SVFs), with consideration of obstruction of building blocks only. Considering the fact that street trees and building blocks are the two major obstructions of radiation within street canyons, therefore, the difference between the two SVF estimation results can be considered as the shade provision of street trees. The results show that street trees help to decrease the SVF by 24.61% in Boston, Massachusetts. The shading level varies spatially in the study area. Generally, the southwestern area has much higher shading level than the north and the east. We further explored the shading variation among different socioeconomic groups in the study area. Result shows that Hispanics tend to live in neighborhoods with lower shading level. This study can help to provide a reference for future urban greening projects for global climate change adaption.

Intensity Filtering and Group Fusion for Accurate Mobile Place Recognition

Mobile place recognition targets at matching query images captured by mobile devices with database images collected from vehicle-mounted cameras, such as Google street view panoramas, which plays an important role in many applications. However, current solutions deriving from image retrieval suffer from the problem of low precision on top results, which significantly challenges their usability. By investigating the state-of-the-art approaches, we find that the bad illumination significantly affects initial results, and these initial results are correlative in both spatial location and visual content, which can be utilized for further improvement. In this paper, we propose an effective approach to rerank initial top-ranked results to improve the recognition recall. First, initial retrieval results with low intensity are filtered as they usually depict irrelevant places with dark background. Second, the correlation between top-ranked results is modeled as a reciprocal neighborhood graph by jointly considering spatial location and visual similarity. With the graph, the initial results are reranked based on voting similarity from the query and reciprocal neighbors. In this way, the underlying structure of initial retrieval results is exploited for refining. Experimental results on the public Tokyo 24/7 and San Francisco landmark datasets demonstrate that the proposed approach can achieve persisting improvement of recognition recall over the state-of-the-art approach.

Quantifying the shade provision of street trees in urban landscape: A case study in Boston, USA, using Google Street View

Shade provision by street trees during the hot summer months is a primary factor for the thermal comfort of people in urban areas. In this study we present a novel method to estimate the shade provision of street trees in the downtown area of Boston, Massachusetts using a quantification of the sky view factor (SVF) from street-level imagery. The SVF is an indicator to quantify the level of enclosure of street canyons. It has been widely applied and has become a standard metric employed by urban designers because it relates to the amount of direct solar radiation reaching the ground and, thus, holds direct implications on the thermal comfort of citizens. In a novel methodology, Google Street View panoramas were used to represent the street canyon unit and to compute the SVF. Street-level imagery allowed us to consider obstructions along street canyons without relying on simplifications or simulations of the environment. In turn, a building height model was used to calculate the SVF, considering only the obstruction of solar radiation by building blocks. Thus with these two quantifications of the SVF, the difference between the two SVF estimations were treated as an estimate of the shading effect of street trees. In the case of Boston, the results showed that the street trees decrease the SVF by 18.52% in the downtown areas. This study can provide an important reference for future urban greening projects for urban climate moderation.

Automatic Sky View Factor Estimation from Street View Photographs—A Big Data Approach

Hemispherical (fisheye) photography is a well-established approach for estimating the sky view factor (SVF). High-resolution urban models from LiDAR and oblique airborne photogrammetry can provide continuous SVF estimates over a large urban area, but such data are not always available and are difficult to acquire. Street view panoramas have become widely available in urban areas worldwide: Google Street View (GSV) maintains a global network of panoramas excluding China and several other countries; Baidu Street View (BSV) and Tencent Street View (TSV) focus their panorama acquisition efforts within China, and have covered hundreds of cities therein. In this paper, we approach this issue from a big data perspective by presenting and validating a method for automatic estimation of SVF from massive amounts of street view photographs. Comparisons were made with SVF estimates derived from two independent sources: a LiDAR-based Digital Surface Model (DSM) and an oblique airborne photogrammetry-based 3D city model (OAP3D), resulting in a correlation coefficient of 0.863 and 0.987, respectively. The comparisons demonstrated the capacity of the proposed method to provide reliable SVF estimates. Additionally, we present an application of the proposed method with about 12,000 GSV panoramas to characterize the spatial distribution of SVF over Manhattan Island in New York City. Although this is a proof-of-concept study, it has shown the potential of the proposed approach to assist urban climate and urban planning research. However, further development is needed before this approach can be finally delivered to the urban climate and urban planning communities for practical applications.

Greenspace in the air and on the ground: comparing greenspace estimates derived from satellites and Google street view imagery

Introduction: Exposure to green space, also referred to as greenness or natural areas, is associated with several diverse positive health outcomes. One of the proposed mechanisms of action for green space is psychological and based on human observation of green space elements. To date the majority of green space health studies have utilized satellite imagery (NDVI) or land use to estimate green space exposures. However, the correlation between satellite-based measures and amount of observable green space at ground level that individuals are actually exposed to (i.e. view) is largely unknown. Methods: We developed a methodology to extract green space measures from Google street view imagery. We compared monthly Landsat 7 NDVI (50m buffer) to greenspace estimates based on 700 randomly selected Google street view panoramas (360⁰ images) in Portland, Oregon. Street view panoramas were converted to hue and saturation vectors and filtered for green pixels with hue between 85 and 155 and saturation between 5 and 250. Summary statistics for each panorama image include mean and standard deviation hue and saturation and percent green pixel coverage. Results: NDVI was positively correlated with percent green pixel coverage (r=0.27) and mean saturation (r=0.26) and negatively correlated with mean hue (r=-0.21). Correlations between NDVI and green pixel coverage significantly varied by month (r=0.18 in August and 0.66 in November). Conclusions: Low to moderate correlation was observed between satellite and street-based green space measures. Monthly variations in correlation suggest NDVI and street view are capturing different components of the greenspace environment, potentially related to different stages of the greenspace annual cycle. We are performing crowd-source surveys to compare how well NDVI and novel street view summary statistics captures human greenspace attitudes and perceptions. These measures will be incorporated into future epidemiological analyses.

Three‐dimensional positioning from Google street view panoramas

Location-based services (LBS) on web-based maps and images have come into real-time since Google launched its street view imaging services in 2007. This research employs Google Maps API and Web Service, GAE for JAVA, AJAX, Proj4js, cascading style sheets and HyperText markup language in developing a platform for accessing the orientation parameters of Google street view (GSV) panoramas in order to determine the three-dimensional (3D) position of points of interest (POIs) by intersection between two nearby GSV images and to validate the 3D position of a GSV panorama by resection from three known POIs. Extracted 3D positional information of the features are then packed in keyhole markup language format and stored in GAE Servlet for future LBS applications integrated with Google Maps and Google Earth. Experimental results from two tests on intersection and one test on resection of GSV panoramas in National Chung Hsing University campus were examined with error reports and source analyses. With automatic conjugate image-matching capability, the developed system is suitable for volumetric data collection in establishing web-based LBS applications integrated with GSV panoramas and Google Maps/Earth in which positional accuracy is not primarily concerned.

FEATURE POSITIONING ON GOOGLE STREET VIEW PANORAMAS

Abstract. Location-based services (LBS) on web-based maps and images have come into real-time since Google launched its Street View imaging services in 2007. This research employs Google Maps API and Web Service, GAE for JAVA, AJAX, Proj4js, CSS and HTML in developing an internet platform for accessing the orientation parameters of Google Street View (GSV) panoramas in order to determine the three dimensional position of interest features that appear on two overlapping panoramas by geometric intersection. A pair of GSV panoramas was examined using known points located on the Library Building of National Chung Hsing University (NCHU) with the root-mean-squared errors of ±0.522m, ±1.230m, and ±5.779m for intersection and ±0.142m, ±1.558m, and ±5.733m for resection in X, Y, and h (elevation), respectively. Potential error sources in GSV positioning were analyzed and illustrated that the errors in Google provided GSV positional parameters dominate the errors in geometric intersection. The developed system is suitable for data collection in establishing LBS applications integrated with Google Maps and Google Earth in traffic sign and infrastructure inventory by adding automatic extraction and matching techniques for points of interest (POI) from GSV panoramas.