No abstract

Urban land use is key to rational urban planning and management. Traditional land use classification methods rely heavily on domain experts, which is both expensive and inefficient. In this paper, deep neural network-based approaches are presented to label urban land use at pixel level using high-resolution aerial images and ground-level street view images. We use a deep neural network to extract semantic features from sparsely distributed street view images and interpolate them in the spatial domain to match the spatial resolution of the aerial images, which are then fused together through a deep neural network for classifying land use categories. Our methods are tested on a large publicly available aerial and street view images dataset of New York City, and the results show that using aerial images alone can achieve relatively high classification accuracy, the ground-level street view images contain useful information for urban land use classification, and fusing street image features with aerial images can improve classification accuracy. Moreover, we present experimental studies to show that street view images add more values when the resolutions of the aerial images are lower, and we also present case studies to illustrate how street view images provide useful auxiliary information to aerial images to boost performances.

Portraying urban functional zones provides useful insights into understanding complex urban systems and establishing rational urban planning. Although several studies have confirmed the efficacy of remote sensing imagery in urban studies, coupling remote sensing and new human sensing data like mobile phone positioning data to identify urban functional zones has still not been investigated. In this study, a new framework integrating remote sensing imagery and mobile phone positioning data was developed to analyze urban functional zones with landscape and human activity metrics. Landscapes metrics were calculated based on land cover from remote sensing images. Human activities were extracted from massive mobile phone positioning data. By integrating them, urban functional zones (urban center, sub-center, suburbs, urban buffer, transit region and ecological area) were identified by a hierarchical clustering. Finally, gradient analysis in three typical transects was conducted to investigate the pattern of landscapes and human activities. Taking Shenzhen, China, as an example, the conducted experiment shows that the pattern of landscapes and human activities in the urban functional zones in Shenzhen does not totally conform to the classical urban theories. It demonstrates that the fusion of remote sensing imagery and human sensing data can characterize the complex urban spatial structure in Shenzhen well. Urban functional zones have the potential to act as bridges between the urban structure, human activity and urban planning policy, providing scientific support for rational urban planning and sustainable urban development policymaking.

Passively-generated data, such as GPS data and cellular data, bring tremendous opportunities for human mobility analysis and transportation applications. Since their primary purposes are often nontransportation related, the passively-generated data need to be processed to extract trips. Most existing trip extraction methods rely on data that are generated via a single positioning technology such as GPS or triangulation through cellular towers (thereby called single-sourced data), and methods to extract trips from data generated via multiple positioning technologies (or, multi-sourced data) are absent. And yet, multi-sourced data are now increasingly common. Generated using multiple technologies (e.g., GPS, cellular network-and WiFi-based), multi-sourced data contain high variances in their temporal and spatial properties. In this study, we propose a "Divide, Conquer and Integrate" (DCI) framework to extract trips from multi-sourced data. We evaluate the proposed framework by applying it to an app-based data, which is multi-sourced and has high variances in both location accuracy and observation interval (i.e. time interval between two consecutive observations). On a manually labeled sample of the app-based data, the framework outperforms the state-of-the-art SVM model that is designed for GPS data. The effectiveness of the framework is also illustrated by consistent mobility patterns obtained from the app-based data and an externally collected household travel survey data for the same region and the same period.

No abstract

No abstract

People’s daily travels are structured and can be expressed as networks. Few studies explore how people organize their daily travels and which behavioral principles result in the choices of specific network types. In this study, we first reconstruct location networks and activity networks for numerous individuals from high-resolution mobile phone positioning data and define frequent networks as motifs. The results suggest that 99.9% of people’s travels can be characterized by a limited set of location-based motifs and activity-based motifs. The results further reveal that the least effort principle governs the preferred motif choices through quantifying the rank-frequency properties. The scaling properties of distance characteristically impact motifs, and their scaling differences by node numbers and motif types coincide with the popularities of motifs, verifying the self-adaptions in motif choices; that is, although individuals travel with unique propensities, they always tend to choose the motif with the lowest consumption that satisfies their demand.

No abstract