Map is an essential medium for people to understand our changing planet. Recently, research on generating and updating maps through remote sensing images has been an important and challenging task in geographic information. Traditional methods for map generation are time-consuming and labor-intensive. Besides, most supervised learning methods for map generation lack labeled training samples. It is challenging to generate maps quickly and efficiently for emergency rescue operations such as earthquakes, fire disasters, or tsunami. In this paper, we propose an unsupervised domain mapping model based on adversarial learning called MapGen-GAN. MapGen-GAN is a generative adversarial network that can do end-to-end translation from remote sensing images to general map quickly, and trained with no human annotation data. In order to improve the fidelity and the geometry precision of generated maps, we employ circularity-consistency and geometrical-consistency constraints as a part of the loss function of the proposed model. And then, an improved residual block Unet is designed and adopted as the generator of MapGen-GAN to capture the geographic structure information of buildings, roads, and topography outlines under different resolutions in the map generation. By applying the proposed model to two distinct datasets, experiments demonstrate that our model can generate maps efficiently and quickly and outperform the state-of-the-art approaches.

No abstract

Viewshed analysis is of great interest to location optimization, environmental planning, ecology and tourism. There have been plenty of viewshed analysis methods which are generally time-consuming and among these methods, the XDraw algorithm is one of the fastest algorithms and has been widely adopted in various applications. Unfortunately, XDraw suffers from chunk distortion which greatly lowers the accuracy, which limits the application of XDraw to a certain extent. Previous works failed to remove chunk distortion because they are unaware of the underlying contribution relationship. In this paper, we propose HiXDraw—an improved XDraw algorithm free of chunk distortion. We first uncover the causation of chunk distortion from an innovative contributing perspective. Instead of recording LOS (line-of-sight) height, we use a new auxiliary grid to preserve contributing points. By preventing improper terrain data from contributing to determining the visibility, we significantly improve the accuracy of the outcome viewshed. The experimental results reveal that the error rate largely decreases by 65%. Given the same computing time, HiXDraw is more accurate than previous improvements in XDraw. To validate the removal of chunk distortion, we also present a pillar experiment.

High crowd mobility is a characteristic of transportation hubs such as metro/bus/bike stations in cities worldwide. Forecasting the crowd flow for such places, known as station-level crowd flow forecast (SLCFF) in this paper, would have many benefits, for example traffic management and public safety. Concretely, SLCFF predicts the number of people that will arrive at or depart from stations in a given period. However, one challenge is that the crowd flows across hundreds of stations irregularly scattered throughout a city are affected by complicated spatio-temporal events. Additionally, some external factors such as weather conditions or holidays may change the crowd flow tremendously. In this paper, a spatio-temporal U-shape network model (ST-Unet) for SLCFF is proposed. It is a neural network-based multi-output regression model, handling hundreds of target variables, i.e., all stations’ in and out flows. ST-Unet emphasizes stations’ spatial dependence by integrating the crowd flow information from neighboring stations and the cluster it belongs to after hierarchical clustering. It learns the temporal dependence by modeling the temporal closeness, period, and trend of crowd flows. With proper modifications on the network structure, ST-Unet is easily trained and has reliable convergency. Experiments on four real-world datasets were carried out to verify the proposed method’s performance and the results show that ST-Unet outperforms seven baselines in terms of SLCFF.

No abstract