Reconstructing spatiotemporal trajectories from sparse data

Partsinevelos, Panagiotis; Agouris, Peggy; Stefanidis, Anthony

doi:10.1016/j.isprsjprs.2005.10.004

Cited by 5 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the trajectory reconstruction is an extremely complex and non‐linear problem due to the complicated spatiotemporal variation of the trajectories. Backpropagation (BP) neural networks have been used widely to solve such problems (Chen, Chi, Wang, Pang, & Xiao, ; Ding, Wang, Wang, & Baumann, ; Partsinevelos, Agouris, & Stefanidis, ; Xu, Li, & Claramunt, ). It was demonstrated in previous studies that BP neural networks have the ability to capture non‐linearity, and good prediction capability and flexibility.…”

Section: Related Workmentioning

confidence: 99%

Mapping hourly dynamics of urban population using trajectories reconstructed from mobile phone records

Liu

et al. 2018

Transactions in GIS

View full text Add to dashboard Cite

Understanding the spatiotemporal dynamics of urban population is crucial for addressing a wide range of urban planning and management issues. Aggregated geospatial big data have been widely used to quantitatively estimate population distribution at fine spatial scales over a given time period. However, it is still a challenge to estimate population density at a fine temporal resolution over a large geographical space, mainly due to the temporal asynchrony of population movement and the challenges to acquiring a complete individual movement record. In this article, we propose a method to estimate hourly population density by examining the time-series individual trajectories, which were reconstructed from call detail records using BP neural networks. We first used BP neural networks to predict the positions of mobile phone users at an hourly interval and then estimated the hourly population density using log-linear regression at the cell tower level. The estimated population density is linearly correlated with population census data at the sub-district level. Trajectory clustering results show five distinct diurnal dynamic patterns of population movement in the study area, revealing spatially explicit characteristics of the diurnal commuting flows, though the driving forces of the flows need further investigation.

show abstract

Section: Related Workmentioning

confidence: 99%

Mapping hourly dynamics of urban population using trajectories reconstructed from mobile phone records

Liu

et al. 2018

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Nevertheless, the matching procedure is effective even under random unknown camera movement as long as it remains relatively small. The input data sets comprise the ST trajectories of moving objects for each scene (Partsinevelos et al 2005). The main output involves the conjugate scene trajectories upon which registration is based.…”

Section: Related Work -Overviewmentioning

confidence: 99%

“…Additional object attributes such as color, size, type, and shape may be helpful in enhancing the comparison space and are tackled in Partsinevelos et al (2005).…”

Section: Matching and Registrationmentioning

confidence: 99%

Registering randomly oriented scenes through moving object attributes

Partsinevelos

2011

International Journal of Geographical Information Science

View full text Add to dashboard Cite

We present a procedure to register motion imagery scenes captured from different viewpoints and under various orientations. Spatiotemporal (ST) trajectories of moving or changing objects and phenomena comprising a scene provide a series of interrelation attributes which are used to define the scene topology. Spatial proximity, temporal algebra, arbitrary directional measures, and shape complexity descriptors construct an abstract orientation-invariant space where conjugate pairs of trajectories between scenes are matched. This topology-centric matching procedure compensates for varying scale, occlusion, random error, and data uncertainty. Scene registration is performed through least square projective transformation. The procedure is quite precise, since the matched ST trajectories consist of populated sets of points following a common geometry compared with classic single point registration prone to errors or misinterpretation. Thus, while the matching procedure is abstract in nature, registration itself uses rigid geometry to provide accurate scene correspondence. Experimentation is quite encouraging even under extreme orientation, error, and occlusion conditions.

show abstract

Multi‐modal comparison of object trajectories

Partsinevelos

2008

Journal of Spatial Science

View full text Add to dashboard Cite

Reconstructing spatiotemporal trajectories from sparse data

Cited by 5 publications

References 21 publications

Mapping hourly dynamics of urban population using trajectories reconstructed from mobile phone records

Mapping hourly dynamics of urban population using trajectories reconstructed from mobile phone records

Registering randomly oriented scenes through moving object attributes

Multi‐modal comparison of object trajectories

Contact Info

Product

Resources

About