Google Maps Images Research Articles

Synthesizing Jakarta City’s Local Wisdom: Reimagining Sidewalks with an Emotional Design and Sustainability Approach

The research objective was to design sidewalks as walking facilities and public spaces, considering comfort, safety, cleanliness, and functionality for Jakarta’s residents. The city of Jakarta, as a megapolitan center, hosted various societal activities. The high mobility of Jakarta’s population led to busy sidewalk activities, especially walking, regulated by the Director General of Highways’ guidelines. Walking could help reduce pollution, with Jakarta having the worst pollution in 2023. The research problem, based on 360-degree Google Maps images of sidewalks, was that sidewalks serve not only as footpaths but also as public gathering spaces. The qualitative research method examined digital data on sidewalk use in Jakarta (west, central, south, east, and north). The design process incorporated emotional design (visceral, behavioral, reflective) and three dimensions of sustainability (The Overlapping Spheres Model of Triple Bottom Line/TBL). The result is a 3D sidewalk model using emotional and sustainability design approaches. Synthesis of emotional design interprets visceral (sensory), behavioral (habits), and reflective (values) levels. Synthesis of sustainability includes environmental, social, and economic dimensions, focusing on air quality, water management, and energy efficiency. Social and economic aspects aim to meet Jakarta residents’ basic needs. Ultimately, these recommendations aim to make cities and neighborhoods inclusive, safe, resilient, and sustainable. However, the research is limited to design recommendations without direct implementation. Further research or implementation is needed to address these challenges and ensure Jakarta residents’ future well-being.

Horan Valley Basin Geomorphological Aspects Assessment by Integrating Hypsometric Analysis with Remotely Sensed Morphometric Characteristics

The extraction, study, and accurate interpretation of the morphology database of a basin are the basic blocks for building a valid geomorphological understanding of this basin. In this work, a new approach is presented which is to use three different GIS based methods to extract databases with specific geographical information and then use the concept of information intersection to make a realistic geomorphological perspective for the study area. In the first method, data integration of remote sensing images from Google Map and SRTM DEM images were used to identify Horan basin borders. In the second method, the principle of data integration was represented by extracting the quantitative values of the morphometric characteristics that were affected by the geomorphological condition of the studied basin, such as the shape factor, circulation factor, and relief ratio, then eliciting an optimal conception of the geomorphological condition of the basin from the meanings and connotations of these combined transactions. The third method used the same principle by taking the optimal inferences from the integration of the interpretation of the values of the Hypsometry integration coefficients for each area in the basin separately with the integration value of the drawing curve for the relative heights of the basin areas with their relative areas. It was found, from the values of the coefficients, that the areas (A, B, C, D, and F) were still in the early stages of youth. Whereas the E region was in the maturity stage and the G region was in the monadnock stage of the geomorphological cycle. As for the integral value of the curve, it indicated 48. 559 % erosion from the surface of the basin only, and that its boundaries were subject to change and widening.

Spatial Differentiation of Pond Landscapes across an Urban-Rural Gradient in the Pearl River Delta Region

The impact of ponds by urbanization has been widely discussed on the landscape scale. However, relatively few studies have explored the spatial differentiation of pond landscapes across urban-rural gradients in rapidly urbanising areas. In this study, we applied the DeepLabv3+ network to perform a semantic segmentation on Google Map images to extract ponds in the Pearl River Delta (PRD) region, China; then we employed geographic information systems to analyse the ponds changes in 665 towns along an urban-rural gradient in the PRD. Results indicate that there are clear differences in landscapes between the urban core, urban, peri-urban, agricultural, and forested zone in terms of pond area and size. In total, 57.84% and 31.33% of the ponds are distributed in the peri-urban and agricultural zone, respectively; fewer ponds are present at either end of the urban-rural gradient. Owing to the legacy effects of historical land use and river systems, urban and peri-urban zone in the central and western parts of the PRD are still rich in ponds. We propose that management measures should be implemented according to the characteristics of different pond landscapes.

Using machine learning to examine associations between the built environment and physical function: A feasibility study.

Linking geospatial neighbourhood design characteristics to health and behavioural data from population-representative cohorts is limited by data availability and difficulty collecting information on environmental characteristics (e.g. greenery, building setbacks, dwelling structure). As an alternative, this study examined the feasibility of Generative Adversarial Networks (GANs) - machine learning - to measure neighbourhood design using 'street view' and aerial imagery to explore the relationship between the built environment and physical function. This study included 3102 adults aged 45 years and older clustered in 200 neighbourhoods in 2016 from the How Areas in Brisbane Influence Health and Activity (HABITAT) project in Brisbane, Australia. Exposure data were Google Street View and Google Maps images from within the 200 neighbourhoods, and outcome data were self-reported physical function using the PF-10 (a subset of the SF-36). Physical function scores were aggregated to the neighbourhood level, and the highest and lowest 20 neighbourhoods respectively were used in analysis. We found that the aerial imagery retrieved was unable to be used to adequately train the model, meaning that aerial imagery failed to produce meaningful results. Of the street view images, n=56,330 images were downloaded and used to train the GAN model. Model outputs included augmented street view images between neighbourhoods classed as having high function and low function residents. The GAN model detected differences in neighbourhood design characteristics between neighbourhoods classed as high and low physical function at the aggregate level. Specifically, differences were identified in urban greenery (including tree heights) and dwelling structure (e.g. building height). This study provides important lessons for future work in this field, especially related to the uniqueness, diversity and amount of imagery required for successful applications of deep learning methods.

Map style transfer using pixel-to-pixel model

The image style transfer is a well-known task and it is applied commonly in the field of artificial intelligence, which converts an image to an image with a specific style without modifying the image content and can be applied to many fields such as changing styled automatically for photos in the cellphone and map wrapping. Recent works focus on a general image style transfer. In this paper, we aim to solve the problem in a navigation application, which is to transfer the satellite maps into map images automatically by deep learning techniques. The methodology we choose for this project is a special GAN named pix2pix model. We decide to use the satellite images as our inputs for the model and let the corresponding Google map images be the output sources. Similar to a traditional GAN, we train the discriminator and generator simultaneously and we attempt to run the training process for 50 epochs in total. PNSR and SSIM are two features we are going to use to test the performance of our results. Finally, the accuracy needs to be improved.

Identification of Potential Zones for Solid Waste Disposal in Jos South Local Government Area of Plateau State, Nigeria

Disposal is a critical phase in the management of municipal solid waste, due to unavailability of suitable facilities to treat and dispose of the large amount of municipal solid waste generated daily in metropolitan cities. Improper municipal solid waste disposal locally, cause environmental impacts such as contamination of soil, water pollution, and increase methane emissions. In this study, an attempt has been made to use GIS and remote sensing to identify high potential zones for solid waste disposal in Jos South Local Government Area of Plateau State between 2019 and 2020. Primary data and secondary data were used for this study. The position data of the existing dumpsites in the study area were acquired in-situ with a handheld Global Positioning System (GPS) receiver. The secondary data consists of NigeriaSAT-X, geological, administrative maps, Google map, hydro-geophysical data and Shuttle Radar Topographic Mission (SRTM) images. Thematic layers considered in this study include drainage, road and land use/land cover, lithology and geology. The dumpsite point (X, Y) was imported as shapefile and superimposed on the study area boundary to show the existing location. Digital image segmentation of NigeriaSAT-X and geology dataset was carried out to derive the land use/ land cover and geology classifications of the study area. Lithological analysis was carried out using Kriging Method to interpolate the hydro-geophysical data. The slope, land/use, geology, drainage, road, waterbody, built-up and lithology were reclassified and overlaid using Weighted Sum Overlay Method a Spatial Analyst tool in ArcGIS 10.4 to generate the potential zones for solid waste disposal. The result shows the potential zones for solid waste disposal and characterized into unsuitable, less suitable, moderately suitable, suitable and highly suitable.

Explorations and estimations using Google Maps images

ABSTRACT The following article deals with the possibility of discovering several parameters of the picture when using Google Maps images, e.g. time and date of taking the image. This is possible with all pictures in which buildings, trees, poles (‘objects’) can be seen with their shadows. In some cases, one can find – with a bit of luck – an aircraft shortly before landing or shortly after take-off at a big and busy airport. If one detects such a situation, the question arises whether it is possible to estimate reasonably the actual height over the ground of the aircraft. The answer is ‘yes’, and we will show several possibilities; in one of them, the concept of three-dimensional similarity will play an important role.

Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses

Automated pavement distresses detection using road images remains a challenging topic in the computer vision research community. Recent developments in deep learning have led to considerable research activity directed towards improving the efficacy of automated pavement distress identification and rating. Deep learning models require a large ground truth data set, which is often not readily available in the case of pavements. In this study, a labeled dataset approach is introduced as a first step towards a more robust, easy-to-deploy pavement condition assessment system. The technique is termed herein as the pavement image dataset (PID) method. The dataset consists of images captured from two camera views of an identical pavement segment, that is, a wide view and a top-down view. The wide-view images were used to classify the distresses and to train the deep learning frameworks, while the top-down-view images allowed calculation of distress density, which will be used in future studies aimed at automated pavement rating. For the wide view group dataset, 7,237 images were manually annotated and distresses classified into nine categories. Images were extracted using the Google application programming interface (API), selecting street-view images using a python-based code developed for this project. The new dataset was evaluated using two mainstream deep learning frameworks: You Only Look Once (YOLO v2) and Faster Region Convolution Neural Network (Faster R-CNN). Accuracy scores using the F1 index were found to be 0.84 for YOLOv2 and 0.65 for the Faster R-CNN model runs; both quite acceptable considering the convenience of utilizing Google Maps images.

Kehadiran Gelombang Soliter dan Transpor Sesaat Sedimen tersuspensi di Perairan Pantai Bengkulu Tengah

<strong>Existence of Solitary Waves and Transient Suspended Sediment Transport in the Coastal Waters of Central Bengkulu. </strong>Coastal abrasion and suspended sediment transport driven by waves is occurring dreadfully in the coastal waters of Central Bengkulu. The abrasion tends to be accelerated by solitary waves during the southeast monsoon season. The primary data were obtained on 17-26 July 2014, while the secondary data derived from Google Maps imageries obtained on 17 June 2014, representing the southeast monsoon season. The primary data were collected by 1200 KHz Acoustic Doppler Current Profiler (ADCP) for water currents, a single beam Echosounder for depths, Garmin 276C GPS receiver for coordinate positions, RBR-TWR2050 (installed at at a fixed point at 102.2219 °E and 3.6916 °S and depth of 9 m) for height and wave periods, and a compass for the direction of wave propagation. The secondary data included Astrium satellite imageries compiled by Google Earth and displayed as Google Maps images on 17 June 2014. These images were used for identifying the appearance of wave groups and by using a feature in Google Earth, it showed that the estimated distance between wave packets hitting the coast accounted for 147 m. This study showed the existence of solitary waves with height and wave period of 1.02 m and 13.85 seconds respectively, while the wave length reached 147.7 m. The wave energy and wave energy flux were 1123.12 Jm<sup>-2</sup> and 12018.94 Jm<sup>-1</sup>s<sup>-1</sup>, calculated by using the cnoidal wave theory and solved by the KdV equation. These solitary waves have large destructive forces on unstable cliffs along the coasts. Derived from coastal abrasion processes and shown by the ADCP backscatter intensity with the highest of 146 dB, the suspended sediments were likely to be transported by water currents with an average speed of 25.99 cm s<sup>-1</sup> in the dominant direction to the south - southeast; and the sediments were deposited along the coast of Bengkulu City.

Locating Optimal Coordinates of Police Deployment and Outpost in Santa Maria Bulacan using Centroid 360: An Enhanced Centroid Initialization for K means Algorithm

The number of police in the Philippines is way below than the declared number of police per population based on the Philippines Republic Act No. 6975, Chapter 3, Section 27 which states that one (1) policeman per five hundred (500) persons. Santa Maria Bulacan only have fifty-two (52) police personnel, and one (1) police outpost which is located in the town of Poblacion which is in the far south east of the whole municipality. This produces different speed when responding to incident reports. The police force’s response time vary based from the location of the incident. This research determined the optimum location to where police will be deployed as a mobile unit to be able to respond faster to more areas than staying in the outpost. Another thing that will be determined by this research is the optimum coordinates of a perfect scenario where each town in the municipality of Santa Maria Bulacan would have their own police outpost. The coordinates will be calculated based on the populations’ location by plotting all the houses and structures located in Santa Maria Bulacan based on Google Map Images, and the Optimum locations will be determined in the form of the converged centroids after applying enhanced K means clustering algorithm.

Representations of Place in the Human Brain

Abstract. Cartographers have been representing places and scenes for thousands of years. We know that there is not one single way to represent place. We can use a reference map, thematic map (not to mention all the different types), large scale, small scale, oblique and overhead remotely sensed image, hand-drawn cartoon maps, street view photographs, animated maps, and digital maps. We also know that the methods and then the resulting representations can be differentiated cartographically using established criteria. But, are these methods all equally effective in conveying a sense of place?We measure “effectiveness” by comparing activation differences in the parahippocampal place area when viewing different representations of place. The parahippocampal place area (PPA) is a region in the human brain that allows humans to recognize and characterize a place (or a representation of it) (Weiner et al., in press). The PPA is a functionally, as opposed to an anatomically, defined region. It overlaps several anatomical regions, including the parahippocampal cortex, the lingual gyrus, the collateral sulcus, and the fusiform gyrus (Figure 1) (Epstein, 2014). The place recognition function of the PPA has been well-documented (Weiner et al., in press; Epstein 2014, 2008; Baldassano et al. 2013; Aguirre et al., 1998; Epstein and Kanwisher, 1998), and we now know that this region is what allows humans to differentiate between a place and other objects such as faces, chairs, or apples.In this study, we measured the effect of cartographic representation on the human brain’s recognition of “place” by comparing the activation differences in the PPA. We compared four types of place representation: a street-view photograph of an urban environment, a drawn schematic similar to a subway-style map, a Google Maps street map, and a Google Maps satellite view. (Figure 2). The Google Maps images were used because they are common cartographic representations, and thus are likely representative of a general “map” condition.

Neighborhoods That Matter: How Place and People Affect Political Participation

Well established in the literature is that social context, like the racial or partisan composition of neighborhoods, affects individual political behavior. Less understood is how the design of neighborhoods may also influence these behaviors. This article seeks to improve how physical context is measured and to examine how the built environment subsequently affects individual political participation. Using a nationally representative survey with measures of the frequency of neighbor interaction and individual voter turnout and to which I merged respondents’ census tract information and then used Google Maps images to code respondents’ neighborhood design features, I show how the physical structure of residential places—whether homes have porches, streets are tree-lined, neighborhoods have natural gathering places—promotes neighborly exchanges that subsequently affect individual voter turnout.

Seeing from Above: Observation of Contemporary Dike-Pond Landsca pe

A dike-pond landscape is characterized by asymbiotic and interacted relationship between water and land and considered an integration of human settlements with an aquacultureagriculture system. The Pearl River Delta has historically enjoyed a rich river network and been shaped by the mosaic-like constructed ponds with the meandering natural river systems, where the boundary of the constructed and the natural blurred and a resilient dike-pond landscape prevailed. However, the increasing demand for land resource during urbanization and industrial development has made such a landscape shrunk and surrounded by urban sprawl. The expansion of human settlements has not only changed the water-land symbiosis but also reshaped the pattern of the dike-pond landscape. This article, as an ongoing work, intends to observe and document the changes of such water-related landscapes from a different perspective, “seeing from above,” with historical satellite photos, Google Map images, and contemporary aerial drone photography. It discovered three important transformations: the settlement sprawl and transformation, the shrinking dike surfaces and imbalanced ratio of dike to pond, and the disappearance of the organic pond pattern. These findings can evoke critical studies on the dialectical relation between urbanization and ecology, and offer possibilities of re-creating a sustainable landscape in the Pearl River Delta.

Online versus in-person comparison of Microscale Audit of Pedestrian Streetscapes (MAPS) assessments: reliability of alternate methods

BackgroundAn online version of the Microscale Audit of Pedestrian Streetscapes (Abbreviated) tool was adapted to virtually audit built environment features supportive of physical activity. The current study assessed inter-rater reliability of MAPS Online between in-person raters and online raters unfamiliar with the regions.MethodsIn-person and online audits were conducted for a total of 120 quarter-mile routes (60 per site) in Phoenix, AZ and San Diego, CA. Routes in each city included 40 residential origins stratified by walkability and SES, and 20 commercial centers. In-person audits were conducted by raters residing in their region. Online audits were conducted by raters in the alternate location using Google Maps (Aerial and Street View) images. The MAPS Abbreviated Online tool consisted of four sections: overall route, street segments, crossings and cul-de-sacs. Items within each section were grouped into subscales, and inter-rater reliability (ICCs) was assessed for subscales at multiple levels of aggregation.ResultsOnline and in-person audits showed excellent agreement for overall positive microscale (ICC = 0.86, 95% CI [0.80, 0.90]) and grand scores (ICC = 0.93, 95% CI [0.89, 0.95]). Substantial to near-perfect agreement was found for 21 of 30 (70%) subscales, valence, and subsection scores, with ICCs ranging from 0.62, 95% CI [0.50, 0.72] to 0.95, 95% CI [0.93, 0.97]. Lowest agreement was found for the aesthetics and social characteristics scores, with ICCs ranging from 0.07, 95% CI [−0.12, 0.24] to 0.27, 95% CI [0.10, 0.43].ConclusionsResults support use of the MAPS Abbreviated Online tool to reliably assess microscale neighborhood features that support physical activity and may be used by raters residing in different geographic regions and unfamiliar with the audit areas.

AgentGeo: Multi-Agent System of Satellite Images Mining

The continuing growth, availability and demand for remote sensing data combined with human impossibility in manual and individual analysis of these data leads to a need to investigate new tools and techniques for automated analysis (or semi-automatic) and intelligent remote sensing databases. Mining images is an alternative for explore large database of remote sensing images, which are methods to discover patterns in the image repository. The multi-agent systems have features that, properly implemented, can bring significant improvements in analysis of satellite images. In this context, the aim of this paper is to present the AgentGeo, a multi-agent system of satellite image mining capable of performing the classification process with multiple images at a time. The AgentGeo implements functions such as creation, edition and selection of agents, selection and creation of the environment and use of agents mining to mine the satellite imagery. This system was developed in Java and uses features from TerraView and GeoDMA. The results of the classification process were satisfactory once the developed agents had an accuracy better than 90% when compared to Google Maps images.

Rasquache aesthetics in Alex Rivera’s “Why Cybraceros?”

This paper studies Rivera's 12-year-old spoof outsourcing website, with particular attention to the 4.5 minute 1997 video that served as its original point of departure (he is now best know for his 2008 feature film, Sleep Dealer.). Rivera’s work in general involves a practice he calls a “rasquache aesthetic” of filmmaking. In a recent interview he defines this concept more precisely, commenting on how Latinos/as channel the creativity that responds to necessity, as people with limited resources turn to repurposing and recycling for their original work. In the hands of Latino/a artists associated with rasquachismo, like Guillermo Gomez Pena, Lalo Alcaraz and Coco Fusco, all of whom have influenced Rivera profoundly, this practice of collage becomes a conscious and conscientious cultural practice. In a parallel manner, in Rivera’s work, the tearing apart and rebuilding of cultural images adds texture and depth, and both his fiction and documentary films include stock footage, rough animation, public domain google map images, and a variety of other materials.

구글 지도에 통계정보를 표현하기 위한 R 함수 개발

구글 지도는 지리 정보를 갖는 데이터에 대한 통계정보를 제공하기 위한 보편화된 수단의 하나로 자리매김하고 있다. 본 연구에서는 R에서 구글 지도를 활용하는 방법에 대해 소개하고, 구글 지도상에 다양한 통계그래프를 표현하기 위한 R 함수를 개발한다. 개발된 함수를 통하여 막대그래프, 원형그래프, 사각형그래프 등과 같은 다양한 통계그래프를 지도상에 표현할 수 있다. Google map has become one of the most recognized and comfortable means for providing statistical information of geographically referenced data. In this article, we introduce R functions to embed google map images on R interface and develop a function to represent statistical graphs such as bar graph, pie chart, and rectangle graph on a google map images.