A human-machine adversarial scoring framework for urban perception assessment using street-view images

Yao, Yao; Liang, Zhaotang; Yuan, Zehao; Liu, Penghua; Bie, Yongpan; Zhang, Jinbao; Wang, Ruoyu; Wang, Jiale; Guan, Qingfeng

doi:10.1080/13658816.2019.1643024

Cited by 224 publications

(140 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the growth of urban data and the development of deep learning technology, urban researchers can collect large-scale street view images of the research area in a short time, which contain a large number of spatial information (sky, green view) [61][62][63][64] and ground object information [65], which provides more possibilities for research [66][67][68]. Street view, green space, and blue space can prevent depression in the elderly in China [63], for example, street view images were used to evaluate the perception of the built environment of the elderly in the Haidian District of Beijing through human-machine confrontation scoring process [69].…”

Section: Research Problemmentioning

confidence: 99%

The Impact of Street Space Perception Factors on Elderly Health in High-Density Cities in Macau—Analysis Based on Street View Images and Deep Learning Technology

et al. 2020

View full text Add to dashboard Cite

The urban space environment has been proven to be related to the health of the elderly. However, as a high-density city, Macau’s limited urban space must cope with the growing population and the arrival of an aging society. In the existing studies, less attention has been paid to Macau, especially the relationship between Macanese elderly and urban space. This study uses Baidu Street View (BSV) on the Macau Peninsula and conducts field surveys to obtain street view data to evaluate the openness, greenness, interface coverage, and road area ratio of street space and its association with the physical and mental health of the elderly and social health. The results show that the data truly reflect the overall street space conditions on the Macau Peninsula. The street openness, greenery rate, and interface enclosure are all related to the elderly in various evaluations in areas with a higher population dependency index and aging index. Human space perception is related to health gain, and road area ratio is weaker than other indicators. The research results have certain policy implications and have practical significance for city managers and designers.

show abstract

Section: Research Problemmentioning

confidence: 99%

The Impact of Street Space Perception Factors on Elderly Health in High-Density Cities in Macau—Analysis Based on Street View Images and Deep Learning Technology

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We assessed neighbourhood perceptions of each neighbourhood based on street view images extracted from Tencent Map (https ://map.qq.com), a web map service similar to Google Maps. Tencent Map provides a comprehensive service of streets view images, which can be retrieved with API [61]. We constructed sampling points 100 metres apart along the road network that was retrieved from OpenStreetMap [62].…”

Section: Human Perceptions Of Neighbourhood Appearancementioning

confidence: 99%

“…We constructed sampling points 100 metres apart along the road network that was retrieved from OpenStreetMap [62]. For each sampling point, we took street view images in four headings (0°, 90°, 180°, and 270°) [61]. We obtained an average of 2105.9 images (SD = 768.0) from each neighbourhood.…”

Section: Human Perceptions Of Neighbourhood Appearancementioning

confidence: 99%

“…Second, perceptions of a wealthy, safe, lively, beautiful, boring and depressing neighbourhood are similar between volunteers and local residents, who are similar in terms of cultural background and life experiences. We then applied a human-machine adversarial scoring approach to improve the accuracy of predictions of human perceptions [61]. Volunteers were asked to use a software tool that was connected to our trained scoring model.…”

Section: Human Perceptions Of Neighbourhood Appearancementioning

confidence: 99%

See 1 more Smart Citation

The linkage between the perception of neighbourhood and physical activity in Guangzhou, China: using street view imagery with deep learning techniques

et al. 2019

Self Cite

View full text Add to dashboard Cite

Background: Neighbourhood environment characteristics have been found to be associated with residents' willingness to conduct physical activity (PA). Traditional methods to assess perceived neighbourhood environment characteristics are often subjective, costly, and time-consuming, and can be applied only on a small scale. Recent developments in deep learning algorithms and the recent availability of street view images enable researchers to assess multiple aspects of neighbourhood environment perceptions more efficiently on a large scale. This study aims to examine the relationship between each of six neighbourhood environment perceptual indicators-namely, wealthy, safe, lively, depressing, boring and beautiful-and residents' time spent on PA in Guangzhou, China. Methods:A human-machine adversarial scoring system was developed to predict perceptions of neighbourhood environments based on Tencent Street View imagery and deep learning techniques. Image segmentation was conducted using a fully convolutional neural network (FCN-8s) and annotated ADE20k data. A human-machine adversarial scoring system was constructed based on a random forest model and image ratings by 30 volunteers. Multilevel linear regressions were used to examine the association between each of the six indicators and time spent on PA among 808 residents living in 35 neighbourhoods.Results: Total PA time was positively associated with the scores for "safe" [Coef. = 1.495, SE = 0.558], "lively" [1.635, 0.789] and "beautiful" [1.009, 0.404]. It was negatively associated with the scores for "depressing" [− 1.232, 0.588] and "boring" [− 1.227, 0.603]. No significant linkage was found between total PA time and the "wealthy" score. PA was further categorised into three intensity levels. More neighbourhood perceptual indicators were associated with higher intensity PA. The scores for "safe" and "depressing" were significantly related to all three intensity levels of PA. Conclusions:People living in perceived safe, lively and beautiful neighbourhoods were more likely to engage in PA, and people living in perceived boring and depressing neighbourhoods were less likely to engage in PA. Additionally, the relationship between neighbourhood perception and PA varies across different PA intensity levels. A combination of Tencent Street View imagery and deep learning techniques provides an accurate tool to automatically assess neighbourhood environment exposure for Chinese large cities.

show abstract

“…The rise of Spatial Big Data has provided researchers with new data sources to study various research problems. These new kinds of datasets have been introduced into different fields, to address such issues as measuring economic activity (Dong et al 2017, Sobolevsky et al 2017, Mancini et al 2018, Sinclair et al 2018, regionalization (Gao et al 2013, Li et al 2019, Jia et al 2019, urban understanding (Zhou et al 2019, Yao et al 2019, Zhu et al 2020 and human mobility (Yang et al 2019, Chen et al 2019, Soundararaj et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Analysis of the performance and robustness of methods to detect base locations of individuals with geo-tagged social media data

Liu

Zhang

Yao

et al. 2020

International Journal of Geographical Information Science

View full text Add to dashboard Cite

Various methods have been proposed to detect the base locations of individuals, with their geo-tagged social media data. However, a common challenge relating to base-location detection methods (BDMs) is that, the rare availability of ground-truth data impedes the method assessment of accuracy and robustness, thus undermining research validity and reliability. To address this challenge, we collect users' information from unstructured online content, and evaluate both the performance and robustness of BDMs. The evaluation consists of two tasks: the detection of base locations and also the differentiation between local residents and tourists. The results show BDMs can achieve high accuracies in base-location detection but tend to overestimate the number of tourists. Evaluation conducted in this study, also shows that BDMs' accuracy is subject to the intensity of user's activities and number of countries visited by the user but are insensitive to user's gender. Temporally, BDMs perform better during weekends and summertime than during other periods, but the best performances appear with datasets that cover the whole time periods (whole day, week, and year). To the best of knowledge, this study is the first work to evaluate the performance and robustness of BDMs at individual level.

show abstract

A human-machine adversarial scoring framework for urban perception assessment using street-view images

Cited by 224 publications

References 42 publications

The Impact of Street Space Perception Factors on Elderly Health in High-Density Cities in Macau—Analysis Based on Street View Images and Deep Learning Technology

The Impact of Street Space Perception Factors on Elderly Health in High-Density Cities in Macau—Analysis Based on Street View Images and Deep Learning Technology

The linkage between the perception of neighbourhood and physical activity in Guangzhou, China: using street view imagery with deep learning techniques

Analysis of the performance and robustness of methods to detect base locations of individuals with geo-tagged social media data

Contact Info

Product

Resources

About